Home

SecondLook 7.2 Digital User Manual

1. Packing materials The materials used to pack our equipment are recyclable They must be collected and processed in accordance with the regulations in force for the country where the machines or accessories are unpacked Page no 6 Regulatory fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Table of Contents Table of Contents Regulatory requirements 0000 e ee eens 3 Table of Contents cea os Genta Sek pease id ten a tei E EE EE ETWAS SS 7 TzEOFeWOFG iio d eh hee pte dts atin SA Ove e CRUS et Pes epa RV wee aw IR 9 1 1 The Aim of This Manual lsssssleeeeee hh 9 1 2 Associated Operator Manuals 0000 00 cee 9 Tee GOSS MEET LEV MT 10 2 CAD in mammography 2 2 4025 Suse ERE a RRARURRUERR RA cena Pea Gb Pee EAS 11 2 1 What CAD can do sss bey Pee beaded Ed Y wads ye Eke OS SCIL ES 11 2 2 What CAD cannot do 11 3 GAD Principles audit ESO Orc Reset ts ee EE Eat p wi Pb s M nds 12 Using AD ou sts each ate etate en Rare Raia Pn eU Real RC Ra Rer ed OO p RD M ew ee 14 4 1 How do know if CAD is available on this system 000000 ee eee 14 4 2 CAD On Demand CAD Auto Push 20 0 0 000s 14 4 3 Which images can be CAD analyzed 00 eee 15 4 4 Which image formats can be displayed with CAD markers 15 4 5 Selecting images for CAD analysis 0 00000 eee eee 15 4 6 How ar
2. Radiology 2002 225 165 175 7 Yankaskas BC Cleveland RJ Schell MJ et al Association of recall rates with sensitivity and positive predictive values of screening mammography AJR Am J Roentgeno 2001 177 543 549 8 Kerlikowske K Carney PA Geller B et al Performance of screening mammography among women with and without a first degree relative with breast cancer Ann Intern Med 2000 133 855 863 9 Bird RE Wallace TW Yankaskas BC Analysis of cancers missed at screening mammography Radiology 1992 184 613 617 10 Fletcher SW Black W Harris R et al Special article Report of the International Workshop on Screening for Breast Cancer J Nat Cancer Inst 1993 85 1644 1656 11 Goergen SK Evans J Cohen GP et al Characteristics of breast carcinomas missed by screening radiologists Radiology 1997 204 131 135 12 Robertson CL A private breast imaging practice Medical audit of 25 788 screening and 1 077 diagnostic examinations Radiology 1993 187 75 79 13 Sickles EA Auditing your practice RSNA categorical course in breast imaging Oak Park IL RSNA 1995 81 91 14 Anderson ED Muir BB Walsh JS et al The efficacy of double reading mammograms in breast screening Clin Radiol 1994 49 248 251 15 Anttinen Pamilo M Soiva M et al Double reading of mammography screening films One radiologist or two C in Radiol 1993 48 414 421 16 Beam C Sullivan D Layde P Effect of human variability on independent double reading in scre
3. Advantage review workstation CAD Computer Aided Detection SLD SecondLook Digital SLDU SecondLook Digital Unit CAD system A product composed of the SLDU and optional features on the AWS and the review workstation RAW FOR Raw original image produced by Image Detection Controller IDC PROCESSING PROCESSED FOR Processed image processed by AWS computer PRESENTATION SCPT Secondary Capture Image ROI Region s of Interest questionable area of image containing possible abnormalities which may require investigation RTSS RadioTherapy Structure Set DICOM object type CAD analyzed image An image that has been successfully processed by the SLDU CAD overlay Results produced by the SLDU and delivered to the review workstation An overlay consists of a CAD abe always and CAD markers as required CAD Marker A symbol ellipse or rectangle used in a CAD overlay to identify a region of interest CAD Label Information on a CAD overlay indicating the image status CAD Identifier The part of a CAD label which indicates the CAD software version Page no 10 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 2 CAD in mammography 2 1 What CAD can do Detecting and diagnosing breast cancer is a complex clinical problem The combination of viewing a large number of cases 99 596 of which are expected to be non cancerous in a sc
4. Page no 39 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Case Summary History 62 yo female with palpable mass in upper outer quadrant of right breast No family history of breast cancer Mammographic findings 3 cm circumscribed mass with partially obscured borders in the right breast at 100 clock shown to be a cyst on ultrasound Linear distribution of pleomorphic calcifications in the right breast at 2 o clock posteriorly Pathology Ductal carcinoma in situ arrows show location Page no 40 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 6 6 Summary of Radiologist use of SecondLook Digital The radiologist uses the SecondLook Digital CAD marks with mammography according to the following steps 1 The radiologist first reviews the GE mammograms without viewing the CAD marks following her or his existing procedures of clinical practice The radiologist will make an initial determination if a work up is indicated for the patient prior to turning on and viewing the CAD marks with the softcopy review workstation The radiologist turns on and views the CAD marks with the softcopy review workstation after determining whether or not a work up is indicated from her or his initial review of the patient mammograms The radiologist will take a SecondLook at the mammograms corresponding to any CAD marks From
5. assist only in detection and not in interpretation Therefore SecondLook Digital can assist a radiologist in detecting areas of concern that would have been missed without its use but used properly it cannot cause a radiologist to miss areas of concern that would have been detected without SecondLook Digital SecondLook Digital was developed by leaders in the fields of image processing and artificial intelligence Below is a description of how SecondLook Digital s Computer Aided Detection CAD works 1 The GEMS Senographe full field digital mammograms are processed by the system Image processing is used to identify all the potential cancerous locations in the image 2 These locations are analyzed using radiologic and proprietary measures as well as a feature selection process to determine the most likely locations to be cancer 3 The most likely locations are evaluated in the context of the patient and highlighted with CAD marks displayed overlying the mammograms on the review workstation used by the radiologist for softcopy reading It is important to remember that SecondLook Digital will not necessarily mark what a radiologist would work up This is an important consideration as every radiologist works up different areas based on her or his own criteria SecondLook Digital does not function on its own but always with a radiologist Therefore if SecondLook Digital highlights a mass or microcalcifications in one view only the radiolo
6. the Introduction of a Computer Aided Detection System JNCI 2004 96 3 185 190 45 Birdwell RL Bandodkar P Ikeda DM Computer Aided Detection With Screening Mammography in a University Hospital Setting Radiology 2005 236 451 457 46 Cupples TE Cunningham JE Reynolds JC Impact of Computer Aided Detection in a Regional Screening Mammography Program AJR 2005 185 944 950 47 Khoo LAL Taylor P Given Wilson RM Computer Aided Detection in the United Kingdom National Breast Screening Programme Prospective Study Radiology 2005 237 444 449 48 Morton MJ Whaley DH Brandt KR et al Screening Mammograms linterpretation With Computer Aided Detection Prospective Evaluation Radiology 2006 239 375 383 49 Dean JC Ilvento CC Improved Cancer Detection Using Computer Aided Detection With Diagnostic and Screening Mammography Prospective Study of 104 Cancers AJR 2006 187 20 28 50 Ko JM Nicholas MJ Mendel JB Slanetz PJ Prospective Assessment of Computer Aided Detection in Interpretation of Screening Mammography AJR 2006 187 1483 1491 51 Fenton JJ Taplin SH Carney PA et al Influence of Computer Aided Detection on Performance of Screening Mammography NEJM 2007 356 1399 1409 52 Georgian Smith D Moore RH Halpern E et al Blinded Comparison of Computer Aided Detection With Human Second Reading in Screening Mammography AJR 2007 189 1135 1141 53 Gromet M Comparison of Computer Aided Detection to Doubl
7. 0 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 5 2 Equipment Labels and Symbols RA N Symbols Protective ground earth Ground earth Dangerous voltage Type B equipment This symbol indicates that waste electrical and electronic equipment must not be disposed of as unsorted municipal waste and must be collected separately Please contact an authorized representative of the manufacturer for information concerning the decommissioning of your equipment This symbol indicates that the product contains hazardous materials in excess of the limits 10 established by the Chinese standard SJ T11363 2006 Requirements for Concentration Limits for Certain Hazardous Substances in Electronic Information Products O m 6 CAD fm Page no 21 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 5 2 2 SLDU labels WARNING Connect only to a properly earth grounded outlet PRODUCT CODE TOP ASSEMBLY NO SERIAL NO Page no 22 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 6 Radiologist Training and SLD CAD Algorithm Descriptions 6 1 Overview This section is intended to describe the SecondLook Digital Computer Aided Detection algorithms and provide training to radiologists using the SecondLook Digital system in breast cancer d
8. D SecondLook with the GE FFDM system is intended to be used by a radiologist as follows The radiologist must always first perform a full conventional read of the mammogram and only after completing the conventional read the radiologist may choose to display the CAD marks which may prompt to areas that were or were not examined during the first read It is crucial to understand that 99 6 of all CAD marks will be placed over areas that are normal breast tissue or benign findings Be aware that the SecondLook is not a diagnostic device as the CAD marks are intended to be used to assist only in detection and not to assist with interpretation 6 3 3 Warnings A 6 3 3 1 Warnings Radiological Interpretation The radiologist must always first perform a full conventional read of the mammogram and only after completing the conventional read the radiologist may choose to display the CAD marks which may prompt to areas that were or were not examined during the first read The presence or absence of a CAD mark should not in any manner influence your diagnostic decision as to the nature of a mammographic finding i e normal vs benign vs malignant or the clinical action to be taken e g additional imaging or biopsy Do not rely on the size or shape of the CAD mark as it may not be representative of the actual extent or shape of the breast lesion Upon re evaluation for the original mammogram at the locations indicated by SecondLook t
9. GE Healthcare Senographe SecondLook Digital CAD System Operator Manual CE Raw and or processed images DTM103 Revision B Copyright 2011 by iCAD Inc Manufactured by iCAD All Rights Reserved GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 This page is intentionally left blank Page no 2 Cover fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Regulatory requirements Regulatory requirements This product complies with the regulatory requirements of the following Council Directive 93 42 EEC concerning medical devices the CE label affixed to the product testifies compliance to the Directive For a system the location of the CE marking label is described in the system manual iCAD European registered place of business Medical Device Safety Service GmbH Attn Ludger Moeller Schiffgraben 41 30175 Hannover Germany Phone 49 511 62628630 Fax 49 511 62628633 Underwriters Laboratories Inc UL an independent testing laboratory Canadian Standards Association CSA International Electrotechnical Commission IEC international standards organization when applicable Compliance with these standards is evidenced by the presence of the appropriate labels on the exterior of the computer unit cabinet USA HHS United States Federal law restricts this device to use by or on t
10. If there were no CAD marks no re evaluation of the mammograms would be necessary Work up decisions are not based solely upon the CAD marks All work up decisions are based upon review of the mammograms supporting clinical information and CAD marks by the radiologist 3 The third page then presents a summary of the case which includes the case history the mammographic findings and the resulting pathology An arrow points to the location of the tumor in printed versions of the mammograms CAD fm Page no 37 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 6 5 2 Sample Case Case History and Mammograms History 62 yo female with palpable mass in upper outer quadrant of right breast No family history of breast cancer bl DURING CLINICAL USE THE INITIAL MAMMOGRAPHY REVIEW AND mE TRES INITIAL WORK UP DECISION WOULD BE ACCOMPLISHED aid Page no 38 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Mammograms with CAD Marks Note The softcopy review workstation may use symbols other than rectangles calcifications and ellipses masses for the CAD marks eee DURING CLINICAL USE THE AREAS OF CONCERN HIGHLIGHTED BY iiid ee THE CAD MARKS WOULD BE RE EVALUATED USING THE SOFTCOPY mE dd REVIEW WORKSTATION FROM THIS RE EVALUATION OF THE dc d MAMMOGRAMS THE RADIOLOGIST MAKES THE FINAL WORK UP eee een DECISION idu CAD fm
11. analysis but a transfer or Check for CAD overlays in the Browser lists network failure occurred push the image to the SLDU again 4 The CAD overlay has been removed from the review Check for CAD overlays in the Browser lists workstation push the image to the SLDU again 5 The CAD licence is not valid for the workstation which Consult your GEMS Field Engineer created the image this problem should be indicated by a Network problem message when trying to push the image s to the SLDU CAD fm Page no 17 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 4 6 3 CAD This image can not be processed The CAD label is S P MB BOT NITET Ne a ale eT e eje sro Possible cause What to do 1 The image is not a type suitable for CAD processing Use a suitable type of image see section 4 3 2 The CAD algorithm was unable to create an overlay within the pre determined time normally 30 seconds Use another image of the same patient Page no 18 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 4 7 Printing CAD results Make the CAD overlay visible and print the image using the Print screen option on the review workstation Any CAD markers and labels present are printed 4 8 Transferring the CAD overlay The CAD overlay can be pushed to other S
12. at the mammograms corresponding to any CAD marks From this re evaluation of the mammograms the radiologist determines if any additional work up is required If there are no CAD marks no re evaluation of the mammograms is necessary Work up decisions are not based solely upon the CAD marks All work up decisions are based upon review of the mammograms supporting clinical information and CAD marks by the radiologist Areas of concern marked by SecondLook Digital include suspicious clusters of microcalcifications spiculated and non spiculated masses architectural distortions and focal asymmetric densities Below is the recommended case review process with SecondLook Digital 1 Review patient history and evaluate GE mammograms prior to turning on and viewing CAD marks with softcopy review workstation 2 Make initial interpretation 3 Turnon and view CAD marks with softcopy review workstation and identify potential areas of concern 4 Review mammograms re evaluating areas of concern highlighted by CAD marks with softcopy review workstation 5 Render decision It is very important to remember that it is the radiologist who makes the final decision about a case When a radiologist decides to work up a case the CAD marks must not change the decision however the CAD marks can identify locations for further work up that were initially undetected by the radiologist Page no 36 CAD fm GE Healthcare Senographe SecondLook Digital CAD Sys
13. condLook CAD marks each 4 image case can include Simultaneous analysis of all areas of concern detected in the patient allows the locations most likely to be cancer to be highlighted by the CAD marks Page no 34 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Illustration 4 Region Growing to Determine Shape of Density 6 3 8 Conformance to Standards Refer to the SecondLook Digital Service Manual for the CE Declaration of Conformity DTB060 6 3 9 How Supplied The SecondLook system includes the following components Computer CAD fm Page no 35 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 6 4 Radiologist Use of SecondLook Digital 6 4 1 Radiologist Review Prior to Viewing CAD Marks The radiologist first reviews the GE mammograms without viewing the SecondLook Digital CAD marks following her or his existing procedures of clinical practice The radiologist will make an initial determination if a work up is indicated for the patient prior to turning on and viewing the CAD marks with the softcopy review workstation 6 4 2 Radiologist Review with CAD Marks The radiologist turns on and views the SecondLook Digital CAD marks with the softcopy review workstation after determining whether or not a work up is indicated from her or his initial review of the patient mammograms The radiologist will take a SecondLook
14. e CAD overlays Displayed 20 20 0000 cee eee eee 16 4 7 Printing GAD result ipie ia okie de ew ae aa bk dee ke wa ee eee see ee 19 4 8 Transferring the CAD overlay 0 0 eee ee eee 19 4 9 Storing the CAD overlay s eu cue ex SEP be wher dle a paw rude eda x CR do eed Menu 19 4 10 Access to historic CAD information llle 19 5 SDecITICatioOris x52 tere Rer ete IO ice Cen CH Ron Govind ae Ap denies 20 5 1 Technical Specifications 2l leen 20 5 2 Equipment Labels and Symbols 0000 cece ee eee eee eens 21 Se VION Sih EE as less eas Ad Boe ae ee es BO E Bh es eee Ln DIE 21 9 2 3 SL DU labels EM Accel Baek ee Bot RW Im 22 6 Radiologist Training and SLD CAD Algorithm Descriptions 23 C WOVOIVICW s cuente caet dia ee dae t RC E E E EETA Uh ee CUR OR Ree den a 23 6 2 Second Look Digital in Breast Cancer Detection 00000005 23 6 2 1 Background s sss s 22825 odas ad REESE Pa ERU ea ede ee bee 23 6 2 2 Description of Second Look Digital 0 0 0 0 eee eee 24 6 3 Second Look Digital Device Labeling 0 0 00 eee eee 26 6 3 1 Indications for USC sin essi hb Cb bw L3 Nee Eee he ps 26 6 3 2 Brief Device Description 000 ee 26 03 3 Warnings 32 5 soa eoe itus futt See fit dec Rita ce buo i Se file Sect tects See ete 26 6 3 4 Precautions ossee eaa e e ae E a ie E rre 27 6 3 5 Adverse Effects ioi
15. e Reading of Screening Mammograms Review of 231 221 Mammograms AJR 2008 190 854 859 54 Brem RF Baum J Lechner M et al Improvement in Sensitivity of Screening Mammography With Computer Aided Detection A Multiinstitutional Trial AJR 2003 181 687 693 55 Destounis SV DiNitto P Logan Young W et al Can Computer Aided Detection With Double Reading of Screening Mammograms Help Decrease the False Negative Rate Initial Experience Radiology 2004 232 578 584 56 Gilbert FJ Astley SM McGee MA et al Single Reading with Computer Aided Detection and Double Reading of Screening Mammograms in the United Kingdom National Breast Screening Program Radiology 2006 241 47 53 57 Balleyguier C Kinkel K Fermanian J et al Computer Aided Detection CAD in Mammography Does it Help the Junior or the Senior Radiologist European Journal of Radiology 2005 54 90 96 58 Marx C Malich A Facius M et al Are Unnecessary Follow up Procedures Induced by Computer Aided Diagnosis CAD in Mammography Comparison of Mammographic Diagnosis With and Without Use of CAD European Journal of Radiology 2004 51 66 72 59 Hukkinen K Vehmas T Pamilo M Kivisaari L Effect of Computer Aided Detection on Mammographic Performance Experimental Study onReaders With Different Levels of Experience Acta Radiologica 2006 47 257 263 60 Taplin SH Rutter CM Lehman CD Testing the Effect of Computer Assisted Detection on Interpretive Performance i
16. eas that could be individual microcalcifications and densities In the case of directly acquired images the digital images are first transformed into images that resemble digitized film in order to accommodate variations in inter pixel spacing gray level mapping and bit depth It should be noted that the Modulation Transfer Function MTF for GE images deviates from the MTF specified for SecondLook in the high frequency range While the MTF is not directly used in the calculations performed by SecondLook this deviation may impact the calculation of subtle features along the margins of lesions The microcalcification and density detectors then identify the areas that are most likely to be individual microcalcifications and densities based on an initial analysis of morphological and intensity measurements The types of densities detected are depicted in ustration 2and include spiculated and non spiculated masses architectural distortions and focal densities Circumscribed Masses Round Oval Lobular s Irregular Mass with Microlobulated Mass Obscured Mass Indistinct Margins y a j Spiculated Mass Architectural Distortion rN CAD fm Page no 33 Illustration 2 Densities Detected by SecondLook GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Further analysis of detected areas is accomplished by clustering individual microcalcifications and region growing dens
17. ening mammography Acad Radio 1996 3 891 897 17 Ciatto S Del Turco M Morrone D et al Independent double reading of screening mammograms J Med Screen 1995 2 99 101 18 Warren RM Duffy SW Comparison of single reading with double reading of mammograms and change in effectiveness with experience Br J Radiol 1995 68 958 962 19 Brown J Bryan S Warren R Mammography screening An incremental cost effectiveness analysis of double versus single reading of mammograms BM 1996 312 809 812 20 Bird RE Professional quality assurance for mammographic screening programs Radiology 1990 177 587 21 Kopans DB Breast imaging 2nd Ed Philadelphia Lippincott Raven 1998 214 Page no 42 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 22 Tabar L Fagerberg G Duffy SW et al Update of the Swedish two country program of mammographic screening of breast cancer Radiol Clin North Am 1992 30 187 210 23 Thurjell EL Lernevall KA Taube AA Benefit of independent double reading in a population based mammography screening program Radiology 1994 191 241 244 24 Hendee WR Beam C Hendrick E Proposition All mammograms should be double read Med Phys 1999 26 115 118 25 Kopans DB Double reading Radiol Clin North Am 2000 38 719 724 26 Birdwell RL Ikeda DM O Shaughnessy KF et al Mammographic characteristics of 115 missed cancer later detected with screening mammography and the p
18. enographe review workstations If the corresponding images are also present on the workstation the CAD results can be displayed 4 9 Storing the CAD overlay The CAD overlay itself can be saved as an image of type RTSS Displayed images RAW processed and Premium View with CAD overlays can be stored as SCPT images 4 10 Access to historic CAD information If you may require access to CAD information at a later date after current images have been deleted from the system there are two possibilities Save images with associated CAD overlays as SCPT images Save the raw images so that they can be processed again when required CAD fm Page no 19 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 5 Specifications 5 1 Technical Specifications Power Requirements 550 watts 90 264 VAC 50 60 Hz Dimensions and weights Main unit SLDU approximate may vary h 458 mm 18 in w 235 mm 9 25 in d 483 mm 19 in according to the type of weight 20 4 kg 45 Ibs without peripherals processor Environmental Temperature Operating temperature range 5 to 40 C non operating temperature range 40 to 70 C Environmental Humidity Non operating humidity 35 C at 95 RH non condensing over full temperature range Environmental Altitude Max operating altitude 1500m Signal connections 10 100 1000 Mb s Base T ethernet Page no 2
19. etection Section 6 2 SecondLook Digital in Breast Cancer Detection gives an overview of the role of SecondLook Digital in breast cancer detection The SecondLook Digital Device Labeling is included in section 6 3 SeconaLook Digital Device Labeling which provides a brief description of the system indications for use contraindications warnings and precautions adverse effects summary of clinical studies a description of the principles of operation for the Computer Aided Detection CAD algorithms a list of conformance to standards and how the system is supplied The procedures for a radiologist using the SecondLook Digital CAD marks are described in Section 6 4 Radiologist Use of SeconaLook Digital Sample cases are provided in Section 6 5 Radiologist Training with Sample Cases to familiarize the radiologist with the SecondLook Digital system prior to clinical use Section 6 6 Summary of Radiologist use of SecondLook Digital summarizes a radiologist s use of SecondLook Digital 6 2 SecondLook Digital in Breast Cancer Detection 6 2 1 Background SecondLook a Computer Aided Detection CAD system for mammography has been developed by iCAD Inc to identify and mark regions of interest on screening and diagnostic mammograms to bring them to the attention of radiologists after the initial reading has been completed Thus the system assists the radiologist in minimizing observational oversights by identifying areas on the origina
20. ge the overlay includes a marker to indicate each ROI SecondLook Digital CAD markers The system uses two different markers to identify ROls for the radiologist s review Arectangle surrounding a cluster of bright spots corresponding to a cluster of possible microcalcifications An ellipse surrounding a density with or without radiating lines corresponding to a possible mass or architectural distortion CAD label with software identifier 2 markers iCAD SecondLook V7 2 CAD markers are linked to specific points on the image and cannot be moved Changing the image orientation zooming drawing objects adding text etc does not change the display of the markers relative to the image they move with the image as it is rotated Note CAD markers are automatically sized according to the size of the ROI Page no 16 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 4 6 2 CAD Result not available The CAD label is G2 Y M STU Ee Te EZ TTE Te S Possible cause What to do 1 The image has not been submitted for analysis Check for CAD overlays in the Browser lists push the image to the SLDU 2 The CAD overlay is not yet available on the review Wait for process completion workstation because analysis has not been completed it takes an average of 30 seconds to process an image 2 minutes for a 4 view exam 3 The image was submitted for
21. gist can look for it in the other view to determine if there is a lesion that warrants work up CAD fm Page no 25 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 6 3 SecondLook Digital Device Labeling 6 3 1 Indications for Use The SecondLook Computer Aided Detection CAD system for mammography is intended to identify and mark regions of interest on screening and diagnostic mammograms from GE full field digital mammography FFDM systems to bring them to the attention of the radiologist after an initial reading has been completed Thus the system prompts the radiologist to areas on GE mammograms for second review only 6 3 2 Brief Device Description SecondLook is a mammographic CAD system that prompts radiologists to areas on GE mammograms for a second review only The CAD algorithm version 7 2 includes image processing feature computations and pattern recognition technology to detect regions of interest The algorithm was originally trained on digitized film screen mammograms and intended to more specifically identify potential breast lesions appearing as clusters of microcalcifications and or masses The CAD system was adapted to run on GE images but the CAD algorithm design remained unchanged and was not otherwise retrained on the GE mammograms For hardcopy reading the SecondLook output can be presented on a paper printout showing the CAD marks within the mammogram How to Use the CA
22. h the SecondLook Digital SLD Computer Aided Detection CAD system option It describes the flow of images and explains how to use the CAD options on the Acquisition Workstation AWS and GE Healthcare the review workstations RWS or Seno Advantage It also provides guidelines for the use of CAD in different situations and information on problem solving This manual provides training information for radiologists including descriptions of the SLD CAD algorithms This manual does not contain information on CAD installation or configuration Please refer to the appropriate service manuals for information on these subjects This manual assumes that the reader is familiar with the Senographe Acquisition Workstation and the GE Healthcare review workstations to be used 1 2 Associated Operator Manuals Senographe Essential Acquisition System Operator Manual 5307915 3 8991EN r1 Sirius M48 Technical Release e Senographe DS Acquisition System Operator Manual 5307907 3 S 1EN r1 Nephtys M413 Technical Release Senographe review workstation RWS Operator Manual 2370487 100 e Senographe review workstation Seno Advantage Operator Manual 5182593 4 S 1EN CAD fm Page no 9 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 1 3 Glossary Terms used in this document Term Definition AWS Acquisition workstation RWS Senographe RWS review workstation Seno Advantage Seno
23. he radiologist must use their interpretative skills to determine if the area should be worked up based on its mammographic appearance e SecondLook is neither designed nor intended to prompt to interval change s between mammographic exams asymmetry between the left and right breast e tubular density solitary dilated duct Skin thickening or nipple retraction Page no 26 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 6 3 3 2 Warnings System Operation A Do not use the SecondLook system if you suspect any electrical component is defective or inoperable Do not place liquids on or near SecondLook If a liquid is accidentally spilled on electrical components immediately turn off the computer which will automatically shut down the system to prevent any potential electrical shock Contact iCAD Inc at 1 866 280 2239 for further instructions Ensure that the system is connected to a properly wired and grounded power receptacle Ensure that the voltage and current requirements are within system specifications to avoid bodily injury from electrical shock or fire hazard 6 3 3 3 Warnings Installation and Maintenance A EMC Warning This SecondLook system has been tested and found to comply with EN 60950 1 EN 55022 and EN 55024 This system generates uses and can radiate radio frequency energy and if not installed and used in accordance with our installation inst
24. he SecondLook Digital CAD System Revision B Operator Manual DTM103 4 3 Which images can be CAD analyzed All images to be analyzed by the SLDU must have been generated on a licensed Senographe system The SLDU algorithm will analyze any raw RAW full breast mammographic image The following images cannot be analyzed Processed PROCESSED and secondary capture SCPT images System performance is not assured for the following views Segmented views of the breast Implant views with the full implant imaged Implant Displaced views with a maximum of 25 mm 1 of breast implant imaged can be analyzed Special diagnostic images e g magnification views or spot compression views Cleavage views mages with hook wires Collimated images Coned images 4 4 Which image formats can be displayed with CAD markers The following image formats can be displayed with CAD markers RAW images Processed images Premium View images for users who have the Premium View Option on the review workstation 4 5 Selecting images for CAD analysis You can choose to use CAD to process an individual image a set of images a series or an entire patient case Only rawimages can be CAD processed If you send an entire patient case to the SLDU the raw images are CAD processed other images present processed or secondary capture images are ignored but increase the time required to obtain the overlays Toobtain t
25. he best analysis of available information send entire patient cases rather than individual images to be CAD processed The SLDU takes advantage of all available information during analysis If different views of the same breast are present the SLDU uses all screening views in its analysis just as a clinician would However note that this increases the time required to obtain the overlays processing a 4 view exam takes two minutes as opposed to 30 seconds for a single view Tominimize the elapsed time before CAD overlays are available send only raw images CAD fm Page no 15 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 4 6 How are CAD overlays Displayed Each image being viewed is displayed with its associated CAD overlay if one exists A CAD abe at the bottom of each image gives its status Refer to the following sections for more information CAD label Refer to 2 markers iCAD SecondLook V7 2 Section 4 6 7 This indicates that the image has been successfully analyzed CAD Result not available Section 4 6 2 CAD This image can not be processed Section 4 6 3 4 6 1 Image successfully analyzed Ifthe image has been successfully analyzed the CAD label is in the form 2 markers CAD SeconaLook V7 2 t indicates the number of CAD markers present as well as the CAD software version in use When the SLDU identifies ROIs regions of interest on an ima
26. he order of a physician The original document was written in English Image annotations Note Since the equipment allows the physician to store information on the patient with the function IMAGE ANNOTATIONS the European Directive regarding the protection of the people with regard of data management on their private life and to the free circulation of these data requests the computerized file users radiologists physicians not to store data related to their race philosophical opinions religious opinions political opinions etc Regulatory fm Page no 3 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Regulatory requirements Electromagnetic Compatibility EMC This equipment complies with e FCC ICES 003 e CISPR 22 e EN55022 EN55024 EN61000 3 2 EN610003 3 e VCCI e AS NZS 3548 BSMI CNS13438 e GOST R 29216 91 GOST R 50628 95 Belarus License Ukraine License e RRL MIC Notice No 1997 41 EMC amp 1997 42 EMI GB 9254 GB 17625 CNCA Certification This equipment generates uses and can radiate radio frequency energy The equipment may cause radio frequency interference to other medical and non medical devices and radio communications To provide reasonable protection against such interference this product complies with radiated emissions as per CISPR22 Class A standard limits Detailed requirements and recommendations about power suppl
27. hy reduces breast cancer mortality by 16 The IARC International Agency for Research on Cancer which is part of the WHO World Health Organization concluded that these randomized trials show that mammography reduces breast cancer mortality by 25 35 in women aged 50 69 years CAD fm Page no 23 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 The sensitivity of mammography ranges from 70 to 9096 6 7 amp 9 10 11 12 12 Thus for a woman with breast cancer there is about a 70 to 90 probability that her cancer will be detected by screening mammography and a 1096 to 3096 probability it will not Therefore even though mammography is an effective tool to detect breast cancer and reduce mortality there is need for further improvement in mammographic sensitivity Studies have shown that the accuracy of mammographic interpretation increases when a mammogram is evaluated by 2 radiologists double reading Double reading improves breast cancer detection by 596 to 15 6 16 17 16 19 20 21 22 23 24 25 However double reading is not currently advocated as a standard of care and requires substantial additional resources which are often not available A cancer can be missed because it is not mammographically visible or because of an oversight or misinterpretation Clinical studies have shown that 3096 to 7096 of breast cancers diagnosed at screening mammography are visible
28. in retrospect on prior examinations and that detection errors are responsible for approximately half of missed breast cancers with interpretation errors accounting for the other half 2 26 27 28 29 30 31 32 33 In view of the frequency of missed cancers and of the lack of general support for double reading as a standard of care CAD of breast lesions on mammograms is a method to increase the sensitivity of mammography and possibly further reduce breast cancer mortality CAD in combination with review by a single radiologist is an alternative to double reading for reducing the number of detection errors that lead to missed breast cancers 6 2 2 Description of SecondLook Digital SecondLook Digital is a mammographic CAD system that identifies and highlights potential areas of concern to assist radiologists in breast cancer detection The CAD algorithms used in the SecondLook Digital computer system include image processing feature computations and pattern recognition technology to detect mammographic features indicative of malignancies Areas of concern marked include suspicious clusters of microcalcifications spiculated and non spiculated masses architectural distortions and focal asymmetric densities SecondLook Digital does not distinguish between benign and malignant processes and may highlight technical artifacts SecondLook Digital integrates with the GEMS Senographe FFDM system to process FFDM images The resulting CAD marks are typica
29. ion B Operator Manual DTM103 6 3 7 Detailed Device Description SecondLook uses computer aided detection CAD algorithms to identify regions of interest on mammograms that may contain suspicious finding The CAD algorithms use advanced image processing feature computations and pattern recognition technology to analyze the images for potential areas of concern These potential areas of concern are displayed for the radiologist by overlaying CAD marks at the appropriate locations of the mammography images within the softcopy review workstation or on a paper printout The CAD marks are used by the radiologist as an additional tool in breast cancer detection An overview of the SecondLook CAD algorithms is shown in ustration 7 Standard Mammography Images Y Lx MicroCalc Density Algorithm Algorithm Calc Image Density Image Enhancement Enhancement y Y MicroCalc Density Detector Detector y Y Clustering Region Growing Y Y MicroCalc Density Classifier Classifier Y Context Based Patient Evaluation Y Areas of Concern Highlighted by CAD Marks Illustration 1 SecondLook CAD Algorithms Overview Page no 32 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 The CAD algorithms begin with image enhancement of the digitized mammographic images to accentuate all ar
30. ious Mammograms in Patients with Impalpable Breast Carcinoma Retrospective vs Blinded Interpretation AJR 1993 161 1167 1172 37 Martin JE Moskowitz M Milbrath JR Breast Cancer Missed by Mammography AJR 1979 132 737 739 38 Schmidt RA Nishikawa RM Digital Screening Mammography PPO Updates 8 7 pp 1 16 1994 39 Thurfjell EL Lernevall KA Taube AAS Benefit of Independent Double Reading in a Population based Mammography Screening Program Radiology 1994 191 241 244 40 Economic Impact Analysis of Regulations Under the Mammography Quality Standards Act of 1992 U S Food and Drug Administration and Eastern Research Group Inc Task Order No 1 Contract No 223 94 8031 October 7 1997 41 Quality Determinants of Mammography Clinical Practice Guideline Number 13 Agency for Health Care Policy and Research Publication No 95 0632 October 1994 42 Warren Burhenne LJ Wood SA D Orsi CJ et al Potential Contribution of Computer Aided Detection to the Sensitivity of Screening Mammography Radiology 2000 215 554 562 43 Freer TW Ulissey MJ Screening Mammography with Computer Aided Detection Prospective Study of 12 860 Patients in a Community Breast Center Radiology 2001 220 781 786 CAD fm Page no 43 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 44 Gur D Sumkin JH Rockette HE et al Changes in Breast Cancer Detection and Mammography Recall Rates After
31. ities Clusters include 3 or more individual microcalcifications that are each no more than 4 1 millimeters apart ustration 3 depicts portions of three different mammography images showing how the SecondLook system would highlight microcalcifications clusters in these examples These examples use CAD marks that are rectangular and correspond to the approximate size of the microcalcifications Region growing determines the shape of potential densities as shown in Illustration 4 Illustration 3 CalcMarks Highlighting Microcalcifications Clusters with a The minimum number of calcifications b The extent of the CalcMark enclosing all calcifications considered as part of the cluster c Overlapping CalcMarks are distinctly highlighted even when clusters are close to each other After clustering for microcalcifications analysis and region growing for density analysis clinically relevant and mathematical features are then computed to describe each detected cluster of microcalcifications and density For example the variability in size and shape of the calcifications in a cluster are good features to describe clusters of microcalcifications These features are used by microcalcifications and density classifiers which are specifically designed to select the areas most likely to have features that may be seen with cancer Further analysis uses the context of all areas selected for the patient For example there is a maximum total number of Se
32. l 83 70 95 Percentage Detected High 95 Confidence Interval 83 70 95 Overall Percentage Detected Medium 95 Confidence Interval 70 65 75 Percentage Detected High 95 Confidence Interval 7396 68 78 Marker Rate Analysis The false marker rate analysis of the SecondLook version 7 2 with GE images was measured in two separate ways 1 Averaging the number of marks in all 4 views of a set of BI RADS 1 cases and 2 By averaging the number of marks in all 4 views of a separate set of screening cases without proven cancers all BI RADS For this analysis all GE images were assumed not to contain a mammographically visible cancer and therefore all CAD marks were considered false positive marks This includes marks on benign or otherwise mammographically interesting regions that are ultimately determined to not be cancer The false marker rate was calculated per case i e per patient and per image i e per mammographic view separately Associated 95 Cl were estimated using a statistical resampling technique 5000 sample bootstrapping Per case false marker rate calculation is simply the total number of false positive marks for the case Page no 30 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Per image false marker rate calculation is the total number of false positive marks divided by the tota
33. l number of mammographic views The results for the false marker rate are summarized in Tables 4 and 5 Table 4 Case Based False Marker Rate Calculations for SecondLook Digital on GE Digital Images Cases Enrolled Total 157 Contained Standard 4 Views Screening Dataset 157 Contained Standard 4 Views BIRADS 1 Dataset 127 Scoring Results Screening Dataset Average CAD Marks per Case Medium 95 Confidence Interval 2 0 1 7 2 3 Average CAD Marks per Case High 95 Confidence Interval 2 3 2 0 2 6 BIRADS 1 Dataset Average CAD Marks per Case Medium 9596 Confidence Interval 1 7 1 4 2 0 Average CAD Marks per Case High 95 Confidence Interval 2 0 1 7 2 3 Table 5 Image Based False Marker Rate Calculations for SecondLook Digital on GE Digital Images Cases Enrolled Total 628 Contained Standard 4 Views Screening Dataset 628 Contained Standard 4 Views BIRADS 1 Dataset 508 Scoring Results Screening Dataset Average CAD Marks per Case Medium 95 Confidence Interval 0 5 0 4 0 6 Average CAD Marks per Case High 95 Confidence Interval 0 6 0 5 0 6 BIRADS 1 Dataset Average CAD Marks per Case Medium 9596 Confidence Interval 0 4 0 4 0 5 Average CAD Marks per Case High 95 Confidence Interval 0 5 0 4 0 6 CAD fm Page no 31 GE Healthcare Senographe SecondLook Digital CAD System Revis
34. l mammogram that may warrant a second review The SecondLook system was first developed for use with screen film mammography SFM For SecondLook to process full field digital mammography FFDM from the General Electric Medical Systems GEMS Senographe a new optional system component has been developed SecondLook Digital SecondLook Digital can be configured as a stand alone system that only processes FFDM In the U S in 2002 invasive breast cancer is expected to be newly diagnosed in 203 500 women and an additional 54 300 women will be diagnosed with in situ breast cancer Therefore breast cancer will be the cause of death in 39 600 women in 2002 making it the second highest cause of cancer death in U S women The lifetime risk of a woman in the U S developing breast cancer has been estimated to be one in nine Although recent analysis of the 8 randomized breast cancer screening trials has questioned the reduction in mortality from screening with mammography and the PDQ Physician Data Query panel sponsored by the NCI National Cancer Institute concurred with this uncertainty other U S and international organizations still affirm that screening with mammography and or clinical breast examination is effective in reducing breast cancer mortality The USPSTF U S Preventive Services Task Force sponsored by HHS Health amp Human Services commissioned an evaluation of the 8 mammography screening trials and concluded that mammograp
35. lly displayed overlying the appropriate locations of the mammogram on the review workstation used by the radiologist for softcopy reading When the CAD marks are displayed within the review workstation the radiologist can turn on or off the display of CAD marks overlying the mammogram Although the remainder of this manual is written with the assumption that the CAD marks are viewed on a review workstation a paper printout of the CAD marks is another possible option The radiologist using a paper printout follows similar procedures Typical screening mammography includes four mammographic views left and right craniocaudal projections L CC and R CC and left and right mediolateral oblique projections L MLO and R MLO SecondLook Digital assists radiologists with these mammographic views and full breast diagnostic views On occasion other views are obtained for screening or diagnostic purposes such as left and right exaggerated craniocaudal projections rotated laterally L XCCL and R XCCL and left and right straight mediolateral projections L ML and R ML When additional screening or diagnostic views are taken SecondLook Digital may process more than 4 views for each patient SecondLook Digital is not used to assist the radiologist in evaluating magnification compression views or specimen radiography For patients with breast implants SecondLook Digital is used with implant displaced views only When SecondLook Digital processes magnification compres
36. n Screening Mammography AJR 2006 187 1475 1482 61 Brem RF Baum J Kaplan S Improvement in Sensitivity of Screening Mammography with Computer Aided Detection A Multiinstitutional Trial AJR 2003 181 687 693 Page no 44 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 7 Maintenance 7 1 Planned maintenance performed by the Field Service Engineer Planned Maintenance PM procedures should be performed regularly by your service representative or similarly qualified and trained personnel The procedures and their frequency are listed below Task Title Interval months Clean and check the CAD computer 12 CAD fm Page no 45 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 This page is intentionally left blank Page no 46 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Revision History This table is intentionally left in English REF DATE REASON FOR CHANGE DTM103 REV A February 2011 Release DTM103 REV B August 2011 Correction of language on page 27 section 6 3 4 1 Revision History fm Page no 47 Manufactured by iCAD 98 Spit Brook Rd Suite 100 Nashua NH 03062 U S A Imagination at work
37. ny interaction with a radiologist Standalone performance measures how often the CAD device places prompts over regions that contain or do not contain known breast abnormalities i e microcalcifications and or masses in the absence of radiologist interaction Page no 28 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Sensitivity Analysis The sensitivity of SecondLook version 7 2 with GE images was estimated using electronic truth and scoring that was manually confirmed by a radiologist Electronic truth consists of an experienced mammography radiologist drawing an electronic truth box on each lesion using pertinent data from the mammography and pathology reports The lesion type mass microcalcification mixed is also noted Electronic scoring takes the CAD marks generated by SecondLook and compares their locations to the electronic truth boxes to determine if each CAD mark is a cancer hit or a false positive A CAD mark is assessed as a true positive detection if the CAD mark of a given type mass microcalcification hits a truth box of the same type mixed lesions can be hit by a CAD mark of either type A microcalcification CAD mark is a hit if the CAD mark has any overlap with a microcalcification or mixed truth box A mass CAD mark is a hit if its center falls within a mass or mixed truth box Any CAD mark that is not a hit is counted as a false positive Sensitivity i
38. on Manual pim shipped with your system Keep the power to this type of devices turned off when near this equipment The medical staff in charge of this equipment is required to instruct technicians patients and other people who may be around this equipment to comply fully with the above requirement Further data and recommendations for meeting Electromagnetic Compatibility requirements for a typical installation are given in the Pre Installation Manual pim shipped with your system Note that the magnetic field of an MRI device located nearby may cause a risk of interference Page no 4 Regulatory fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Regulatory requirements Magnetic field amplitude limits are specified in the Pre Installation Manual pim shipped with your system Regulatory fm Page no 5 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Regulatory requirements Recycling Machines or accessories at end of life The elimination of machines and accessories must be in accordance with national regulations for waste processing All materials and components that could pose a risk to the environment must be removed from the end of life machines and accessories examples dry and wet cell batteries transformer oil etc Please consult your local General Electric Medical Systems representative before discarding these products
39. orkstation before results can be viewed 2 The SLDU performs its analysis on each image and delivers the results of the analysis to the review workstation in the form of a CAD overlay CAD processing of an image is not instantaneous The SLDU takes an average of 30 seconds maximum 120 seconds to process a 19 x 23 cm RAW image and generate a CAD overlay or 2 minutes for a group of four images Additional time may be required if there are multiple processing requests 3 The CAD overlay is displayed with the associated images in the form of markers and labels Page no 12 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 CAD Image workflow Step 1 The raw image is pushed to the SLDU for analysis The image raw and or processed must also be pushed to the review workstation before CAD results can be viewed The user first views the processed image on the review workstation without CAD markers Original raw image created by a licensed AWS Raw or processed image Image from storage or archiving device PACS RADSTORE etc SLDU review monitors Raw and or processed images Raw or processed image Step 2 When the SLDU has performed its analysis on each image it sends an overlay to the review workstation showing the location and type of any regions of interest that were found Step 3 While viewing the image the user presses the CAD button or the U2 bu
40. ote that standalone performance testing of SecondLook version 7 2 on GE images cannot be directly compared to standalone performance testing of SecondLook on digitized film screen images The benchmark testing did not measure the effect of the device on radiologist performance and cannot measure or predict any change in radiologist s cancer detection rates when using the device as intended GE Database Description Table 1 provides the mammographic and pathologic characteristics on the GE cases This database included 152 cases with cancer and 157 free of cancer Of the cancer cases there were 70 mass cases 61 microcalcification cases and 21 mixed mass microcalcification cases Cases were stratified whereby various types of radiographic findings of positive and negative cases within the dataset were representative of a screening population However the dataset was enriched with more positive cases than a screening population Table 1 GE Database Demographics Cancers TOTAL NUMBER OF CANCER CASES 152 Number of Primarily Mass Cases Percentage 70 46 Number of Primarily Microcalcification Cases percentage 61 40 Number of Mixed Mass Microcalcification Cases 21 14 SecondLook Standalone Testing with GE Images Standalone testing of the SecondLook version 7 2 with GE images provides a performance measure i e sensitivity and average number of false positives per image or case in the absence of a
41. otential utility of Computer Aided Detection Radiology 2001 219 192 202 27 keda DM Andersson I Wattsgard C et al Interval carcinomas in the Malmo mammographic screening trial Radiographic appearance and prognostic considerations AJR Am J Roentgenol 1992 159 287 294 28 Baines CJ McFarlane DV Miller AB The role of the reference radiologist Estimates of inter observer agreement and potential delay in cancer detection in the National Breast Screening Study Invest Radiol 1990 25 97 1 976 29 Harvey JA Fajardo LL Innis CA Previous mammograms in patients with impalpable breast carcinoma Retrospective vs blinded interpretation AJR Am J Roentgenol 1993 161 1167 1172 30 Kopans DB Breast imaging 2 d Ed Philadelphia Lippincott Raven 1998 793 31 Martin JE Moskowitz M Milbrath JR Breast cancer missed by mammography AJR Am J Roentgenol 1979 132 737 739 32 Schmidt RA Nishikawa RM Digital screening mammography PPO Updates 1994 8 1 16 33 van Dijck JA Verbeek AL Hendriks JH et al The current detectability of breast cancer in a mammographic screening program A review of the previous mammograms of interval and screen detected cancers Cancer 1993 72 1933 1938 34 Bird RE Wallace TW Yankaskas BC Analysis of Cancers Missed at Screening Mammography Radiology 1992 184 613 617 35 Sickles EA Auditing Your Practice RSNA Categorical Course in Breast Imaging 1995 pp 81 91 36 Harvey JA Fajardo LL Innis CA Prev
42. rcentage Detected Medium 95 Confidence Interval 82 72 92 Percentage Detected High 95 Confidence Interval 85 77 94 With Mixed Masses Microcalcifications Percentage Detected Medium 95 Confidence Interval 95 86 100 Percentage Detected High 95 Confidence Interval 95 86 100 CAD fm Page no 29 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Overall Percentage Detected Medium 95 Confidence Interval 83 77 89 Percentage Detected High 95 Confidence Interval 86 81 92 Table 3 Image Based Sensitivity Results for SecondLook Digital on GE Digital Images Total Images Enrolled 321 Images with Clearly Identifiable Lesion s 321 Predominant Type of Most Suspicious Lesion Images with Masses 151 Images with Microcalcifications 130 Images with Mixed Masses Microcalcifications 40 Scoring Results True Positive Cases With Masses Percentage Detected Medium 95 Confidence Interval 6696 5896 74 Percentage Detected High 95 Confidence Interval 68 61 76 With Microcalcifications Percentage Detected Medium 95 Confidence Interval 72 64 80 Percentage Detected High 95 Confidence Interval 7596 68 83 With Mixed Masses Microcalcifications Percentage Detected Medium 95 Confidence Interva
43. reening population radiologist fatigue and the resulting observational oversights the complex image structure of the breast on a mammogram and the subtle nature of certain observational characteristics of the disease may result in false negative mammographic readings The SecondLook Digital Computer Aided Detection system developed for use with GE s Full Field Digital Mammography system is designed to minimize observational oversights made by the radiologist Intended to be an aid for a radiologist reading routine screening and diagnostic mammograms SecondLook Digital identifies areas or regions of interest ROIs on the digital image which show features that may be associated with cancer and may warrant a second review These ROIs are brought to the attention of the radiologist after he or she has completed normal interpretation of the digital mammogram 2 2 What CAD cannot do It is important to note that CAD is not meant to be used for primary diagnosis CAD is not meant to replace the expertise of the radiologist It is meant to be used as an aid to defection and not as an interpretive aid CAD should be used only after the initial reading by the radiologist Only the mammogram images provided directly by the GE Senographe may be used for interpretation by the radiologist By design the Senographe Review Workstations only allows the display of ROI markers after the images are presented free of markers to the radiologist for his her p
44. rimary diagnostic interpretation CAD is a highly sophisticated system but it cannot identify all abnormalities You should base your interpretation upon the original mammogram images and use CAD only as an aid to detection Individual practice patterns may influence the results obtained when using this system Therefore each facility and radiologist should carefully monitor the results that this device has on their practice of mammography in order to optimize its effectiveness CAD fm Page no 11 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 3 CAD Principles The CAD system includes three sub systems the SecondLook Digital Unit SLDU the Review Workstation RWS or Seno Advantage and the Acquisition Workstation AWS CAD processing functions are provided by the SLDU a dedicated computer which runs the CAD processing algorithms and generates the CAD results as an overlay The review workstation displays the overlay with the associated image The CAD image workflow illustrated below includes three main steps 1 RAW images are pushed to the SeconaLook Digital Unit SLDU from the AWS or the review workstation or from an image storage system if present Each image must have been produced by a licensed workstation declared in the CAD configuration Images may be pushed individually or in groups Corresponding images RAW or PROCESSED from the AWS must also be pushed to the review w
45. ructions may cause or be subject to harmful interference with other devices in the vicinity If the SecondLook system appears to cause or be subject to harmful interference try the following steps to correct the problem Reorient or relocate the SecondLook system or the interface device Increase the separation between the SecondLook system and the interfering device Plug the SecondLook system into an outlet on a different circuit from the interfering device Contact iCAD Inc at 1 866 280 2239 for further instructions Temperature and Humidity Warning SecondLook system operations must be performed within the following temperature and humidity ranges Temperature 50 95 Fahrenheit 10 35 Celsius Humidity 20 8096 6 3 4 Precautions AY 6 3 4 1 Precautions System Operation To prevent damage to the system maintain equipment in a well ventilated air conditioned environment Effectiveness and safety in patients with breast implants has not been established for views that include the implant When non displaced implant views are analyzed by the system any resulting CAD marks should not be used by the radiologist in evaluating the patient Effectiveness and safety have not been for non standard mammographic views e g magnification compression views When these views are analyzed by the system any resulting CAD marks should not be used by the radiologist in evaluating the patient The performance of
46. s a count of the true positive detection divided by the total number of cases with mammographically visible cancer and was calculated separately on a per case i e per patient and per images i e mammographic view basis True positive detection was defined as follows For each scoring method if any lesion on an image was scored as a hit answered Yes then the image was scored as a true positive and the case was scored as a true positive Per case sensitivity was computed as the number of true positive cases divided by the total number of cases with mammographically visible cancer with 95 confidence intervals Per image sensitivity was computed as the number of true positive images divided by the total number of images with mammographically visible cancer with 95 CI The 95 Cl were computed using a statistical resampling technique 5000 sample bootstrapping Results of the sensitivity analysis are summarized in Tables 2 and 3 Table 2 Case Based Sensitivity Results for SecondLook Digital on GE Digital Images Total Cases Enrolled 152 Cases with Clearly Identifiable Lesion s 152 Case Type Cases with Masses 70 Cases with Microcalcifications 61 Cases with Mixed Masses Microcalcifications 21 Scoring Results True Positive Cases With Masses Percentage Detected Medium 95 Confidence Interval 80 71 89 High 95 Confidence Interval 84 75 93 Percentage Detected With Microcalcifications Pe
47. sion views specimen radiography or non displaced implant views any resulting CAD marks should not be used by the radiologist in evaluating the patient Page no 24 CAD fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 SecondLook Digital is intended to be used by a radiologist as follows The radiologist must first review the mammogram in the normal manner and only afterward consult the CAD marks to determine if SecondLook Digital has marked any areas of concern that were not observed on the initial review To view the CAD marks prior to the initial unassisted review of the mammogram risks the so called satisfaction of search error in which the radiologist s vigilance for other areas on the mammogram may be lowered by virtue of seeing one or more areas highlighted by SecondLook Digital The absence of a CAD mark at a lesion initially detected without the assistance of SecondLook Digital should not be used by the radiologist to override the decision to further evaluate the lesion SecondLook Digital is designed to mark areas with the mammographic appearance of cancer however many of the marked areas will not contain a malignancy and it is up to the radiologist to decide using conventional clinical judgment and reviewing the mammogram itself if the area is suspicious enough to warrant further work up SecondLook Digital is not a diagnostic device as the CAD marks are intended to be used to
48. soe Sa Oh OS So ea RUE Saw A 28 6 3 6 Clinical Studies rani eda RR DEIA RE RR AUR ROO ae G 28 6 3 7 Detailed Device Description 0 0000s 32 6 3 8 Conformance to Standards 2 2 2408 4 e RRELA WR be a Er ERR RES PERS 35 6 3 9 How Supplied 2 0 0 0 0 eee ene 35 6 4 Radiologist Use of Second Look Digital 0 0 00 cece ee 36 6 4 1 Radiologist Review Prior to Viewing CAD Marks 0000 36 6 4 2 Radiologist Review with CAD Marks 0 0002 cece eee 36 Table of Contents fm Page no 7 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 Table of Contents 6 5 Radiologist Training with Sample Cases 0 0002 cece eee 37 6 5 1 Training Instructions 4 cuta i etym RIS Dos Gre oo as CERA ET beue 37 06 5 2 Sample Cases sau e eb EUER ee rad CR RE Ae ES 38 6 6 Summary of Radiologist Use of Second Look Digital 41 7 Maintenance leer 45 7 1 Planned maintenance performed by the Field Service Engineer 45 Revision FISIOMY ic eod EE EE ne eee wth E ONUS E d De eee bas dese Ra ead eg 47 Page no 8 Table of Contents fm GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 1 Foreword 1 1 The Aim of This Manual This manual is provided for operators using Senographe Acquisition Full Field Digital Mammography FFDM systems equipped wit
49. tem Revision B Operator Manual DTM103 6 5 Radiologist Training with Sample Cases 6 5 1 Training Instructions One sample case demonstrates the use of SecondLook Digital for the radiologist prior to clinical use This case is intended to familiarize the radiologist with the procedures for using the SecondLook Digital CAD marks The case review procedures are emphasized Therefore the training is accomplished by following the case presentation in Section 6 5 2 of this manual without requiring use of the softcopy review station For the example case in the manual the procedures for using SecondLook Digital CAD marks are demonstrated to the radiologist with the following steps 1 The first page will provide the case history and printed versions of the GE mammograms without CAD marks During clinical use the radiologist would first review the mammograms without viewing the CAD marks following her or his existing procedures of clinical practice The radiologist would make an initial determination if a work up were indicated for the patient prior to turning on and viewing the CAD marks with the softcopy review workstation 2 The second page contains printed versions of the mammograms with CAD marks turned on During clinical use the radiologist would take a SecondLook at the mammograms corresponding to any CAD marks From this re evaluation of the mammograms the radiologist would determine if any additional work up was required
50. the SecondLook V7 2 device has not been established for XCC views ML views and breast implants and may differ from those derived using conventional views of the breast i e CC and MLO views CAD fm Page no 27 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 6 3 4 2 Precautions Installation and Maintenance A This product contains no independently user serviceable parts To prevent damage to the system do not attempt to install or repair the SecondLook system Only trained personnel are qualified to install or repair the system For service training contact iCAD Inc at 1 866 280 2239 e Disconnect power cord before moving or servicing 6 3 5 Adverse Effects SecondLook may increase your false positive rates for both screening and diagnostic mammography Increased false positives may lead to unnecessary additional imaging radiation exposure biopsy patient anxiety etc 6 3 6 Clinical Studies Refer to the SecondLook Analog for further details regarding the testing studies used to support the safety and effectiveness of the original approval of the SecondLook analog device for use with digitized film screen mammograms Benchmark testing Benchmark testing consisted of a limited standalone analysis i e analysis of the device without radiologist interaction on a sample of GE mammograms 152 cancers 70 masses 61 microcalcification clusters and 21 mixed mass microcalcification N
51. this re evaluation of the mammograms the radiologist determines if any additional work up is required If there are no CAD marks no re evaluation of the mammograms is necessary Work up decisions are not based solely upon the CAD marks All work up decisions are based upon review of the mammograms supporting clinical information and CAD marks by the radiologist CAD fm Page no 41 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 References 1 National Alliance of Breast Cancer Organizations NABCO Facts about breast cancer in the USA Available at http www nabco org index php index php 137 dated February 2002 accessed October 21 2002 2 Gotzsche PC Olsen O Is screening for breast cancer with mammography justifiable Lancet 2000 355 129 134 3 Breast Cancer PDQ Screening http cancer gov cancerinfo pdq screening breast healthprofessional date last modified September 2002 accessed October 16 2002 4 Humphrey LL Helfand M Chan BK et al Breast cancer screening A summary of the evidence for the U S Preventive Services Task Force Ann ntern Med 2002 137 347 360 5 IARC handbooks of cancer prevention Breast cancer screening vol 7 IARC Press 2002 6 Kolb TM Lichy J Newhouse JH Comparison of the performance of screening mammography physical examination and breast US and evaluation of the factors that influence them An analysis of 27 825 patient evaluations
52. tton on the dedicated keypad if configured to display the E amp E CAD overlay CAD overlay Image displayed with overlay review monitors Raw and or processed images CAD fm Page no 13 GE Healthcare Senographe SecondLook Digital CAD System Revision B Operator Manual DTM103 4 Using CAD 4 1 How dol know if CAD is available on this system 4 2 CAD On Demand CAD Auto Push When the CAD option is installed and operational CAD icons are displayed in the Network Panels of the AWS and review workstation Browser screens RWSViewerAdvanced Card CAD on demand manual triggering of CAD analysis is always available CAD analysis of an image may be requested whenever CAD evaluation is required on a case by case basis If you wish to use CAD only from time to time for help in detecting abnormalities in individual questionable images use CAD On Demand CAD Auto Push may be configured at installation time by the GE installation Engineer When CAD Auto Push is configured CAD processing is applied automatically to all images as soon as they are acquired by the AWS and pushed to the SLDU so that the CAD information is systematically available when reviewing the results on the review workstation The CAD overlay however is not displayed until after the original mammogram images generated by the Senographe without CAD markers have been presented for interpretation by the radiologist Page no 14 CAD fm GE Healthcare Senograp
53. y distribution and installation are listed in the Pre Installation Manual pim shipped with your system However there is no guarantee that interference will not occur in a particular installation If this equipment is found to cause interference which may be determined by turning the equipment on and off the user or qualified service personnel should attempt to correct the problem by one or more of the following measure s reorient or relocate the affected device s increase the separation between the equipment and the affected device power the equipment from a source different from that of the affected device consult the point of purchase or service representative for further suggestions The manufacturer is not responsible for any interference caused by using other than recommended interconnect cables or by unauthorized changes or modifications to this equipment Unauthorized changes or modifications could void the users authority to operate the equipment All interconnect cables to peripheral devices must be shielded and properly grounded Use of cables not properly shielded and grounded may result in the equipment causing radio frequency interference Do not use devices which intentionally transmit RF Signals Cellular Phones Transceivers or Radio Controlled Products in the vicinity of this equipment as it may cause performance outside the published specifications Recommended separation distances are detailed in the Pre Installati

SecondLook 7.2 Digital User Manual

Contents

Download Pdf Manuals

Related Search

Related Contents