link
Bookmarks
CAD and Double Reading: Mammography and Tomosynthesis
Lauren Q. Chang Sen, MDWendie A. Berg, MD, PhD, FACR, FSBI
To access 4,300 diagnoses written by the world's leading experts in radiology.Try it free - 15 days
0
10
4
0

KEY FACTS

  • Terminology

    • Imaging

      • Clinical Issues

        TERMINOLOGY

        • Abbreviations

          • Computer-aided/-assisted detection (CAD)
            • Distinguish from computer-aided diagnosis
          • CAD + R: CAD + single reader
        • Definitions

          • CAD
            • Neural network-generated prompts (marks) highlight areas of concern, directing attention of interpreting radiologist
            • Analog films must be digitized and then processed with a CAD algorithm; digitally acquired images directly interface with the CAD system
              • CAD marks are displayed on low-resolution workstation images by pushing button or on paper printout
            • For digital mammography, CAD systems interface directly with workstation on which mammograms are interpreted
              • CAD engaged by pushing button on workstation console; CAD marks displayed directly over mammographic images
            • Recognized marks (e.g., asterisks or triangles) project over/near findings recognized by neural network
            • Interpreting radiologist makes final determination as to assessment
              • Negative or benign, return to screening interval (BI-RADS 1, 2)
              • Abnormal, requires additional imaging evaluation (BI-RADS 0); probably benign (BI-RADS 3); recommend biopsy (BI-RADS 4, 5)
              • Vast majority of CAD prompts are dismissed by interpreting radiologist
            • False-positive (FP) prompts: CAD-generated prompts in areas where no cancer is present
          • Computer-aided diagnosis: Computer-generated statistical assessment of imaging findings suggesting likelihood of malignancy based on comparison with large number of similar findings
          • Double reading: ≥ 2 independent radiologists interpret same group of images
            • Discordant readings assigned assessment by consensus or arbitration
              • Consensus: Discussion among interpreting radiologists
              • Arbitration: 3rd radiologist makes independent decision
              • ↑ perception (sensitivity) and ↑ specificity
            • May act on all cases indicated as abnormal from either reading
              • ↑ perception (sensitivity) and ↓ specificity
          • Screening mammography
            • Asymptomatic standard MLO and CC screening mammograms performed and evaluated for quality assurance by technologists
            • Women arrive and leave center without waiting for either verbal or written reports, not monitored by physician
            • Mammograms "batch-read" by radiologist in concentrated and focused setting
            • Mammograms are either deemed negative, benign (BI-RADS 1, 2), or incomplete (BI-RADS 0)
            • Women receive via mail or phone call either standard negative report or recommendation to return for additional imaging or biopsy
          • Recall rate: Percentage of women with recommendation to return for further imaging or biopsy prior to next screening examination
            • Desired goal (benchmarks) < 10% recall rate
              • When prior, recent comparisons available, recall rate 30% lower than for baseline (1st mammogram) or no priors
            • Costs (financial and emotional) related to recall rates must be considered
            • Most recalled cases do not undergo biopsy: 10% recall → 1-2% biopsy rate; 15-35% PPV of biopsy

        IMAGING

        • General Features

          PATHOLOGY

          • General Pathologic Considerations

            CLINICAL ISSUES

            • Clinical Importance

              • Expected Performance

                DIAGNOSTIC CHECKLIST

                • Consider

                  • Image Interpretation Pearls

                    Selected References

                    1. Henriksen EL et al: The efficacy of using computer-aided detection (CAD) for detection of breast cancer in mammography screening: a systematic review. Acta Radiol. 60(1):13-8, 2019
                    2. Conant E et al: Improving accuracy and efficiency with concurrent use of artificial intelligence for digital breast tomosynthesis screening. Radiological Society of North America 2018 Scientific Assembly and Annual Meeting, November 26, 2018, Chicago IL (abstr)
                    3. Benedikt RA et al: Concurrent computer-aided detection improves reading time of digital breast tomosynthesis and maintains interpretation performance in a multireader multicase study. AJR Am J Roentgenol. 210(3):685-94, 2018
                    4. James JJ et al: Evaluation of a computer-aided detection (CAD)-enhanced 2D synthetic mammogram: comparison with standard synthetic 2D mammograms and conventional 2D digital mammography. Clin Radiol. 73(10):886-92, 2018
                    5. Katzen J et al: A review of computer aided detection in mammography. Clin Imaging. 52:305-9, 2018
                    6. Keen JD et al: Utilization of computer-aided detection for digital screening mammography in the United States, 2008 to 2016. J Am Coll Radiol. 15(1 Pt A):44-8, 2018
                    7. Balleyguier C et al: Improving digital breast tomosynthesis reading time: a pilot multi-reader, multi-case study using concurrent Computer-Aided Detection (CAD). Eur J Radiol. 97:83-89, 2017
                    8. Cho KR et al: Breast cancer detection in a screening population: comparison of digital mammography, computer-aided detection applied to digital mammography and breast ultrasound. J Breast Cancer. 19(3):316-23, 2016
                    9. Lehman CD et al: Diagnostic accuracy of digital screening mammography with and without computer-aided detection. JAMA Intern Med. 175(11):1828-37, 2015
                    10. Morra L et al: Breast cancer: computer-aided detection with digital breast tomosynthesis. Radiology. 141959, 2015
                    11. Bargalló X et al: Single reading with computer-aided detection performed by selected radiologists in a breast cancer screening program. Eur J Radiol. 83(11):2019-23, 2014
                    12. Cole EB et al: Impact of computer-aided detection systems on radiologist accuracy with digital mammography. AJR Am J Roentgenol. 203(4):909-16, 2014
                    13. Bargalló X et al: Role of computer-aided detection in very small screening detected invasive breast cancers. J Digit Imaging. 26(3):572-7, 2013
                    14. Fenton JJ et al: Short-term outcomes of screening mammography using computer-aided detection: a population-based study of medicare enrollees. Ann Intern Med. 158(8):580-7, 2013
                    15. Murakami R et al: Detection of breast cancer with a computer-aided detection applied to full-field digital mammography. J Digit Imaging. 26(4):768-73, 2013
                    16. Park CS et al: Detection of breast cancer in asymptomatic and symptomatic groups using computer-aided detection with full-field digital mammography. J Breast Cancer. 16(3):322-8, 2013
                    17. Destounis SV et al: CAD may not be necessary for microcalcifications in the digital era, CAD may benefit radiologists for masses. J Clin Imaging Sci. 2:45, 2012
                    18. Geller BM et al: Is confidence of mammographic assessment a good predictor of accuracy? AJR Am J Roentgenol. 199(1):W134-41, 2012
                    19. Nishikawa RM et al: Clinically missed cancer: how effectively can radiologists use computer-aided detection? AJR Am J Roentgenol. 198(3) :708-16, 2012
                    20. Scaranelo AM et al: Evaluation of breast amorphous calcifications by a computer-aided detection system in full-field digital mammography. Br J Radiol. 85:517-22, 2012
                    21. Waldmann A et al: Benefits of the quality assured double and arbitration reading of mammograms in the early diagnosis of breast cancer in symptomatic women. Eur Radiol. 22(5):1014-22, 2012
                    22. Berlin L: Mammographic CAD markings: archive or discard? AJR Am J Roentgenol. 196:W659, 2011
                    23. Fenton JJ et al: Effectiveness of computer-aided detection in community mammography practice. J Natl Cancer Inst. 103(15):1152-61, 2011
                    24. Glynn CG et al: Effect of transition to digital mammography on clinical outcomes. Radiology. 260(3):664-70, 2011
                    25. Cho N et al: Features of prospectively overlooked computer-aided detection marks on prior screening digital mammograms in women with breast cancer. AJR Am J Roentgenol. 195(5):1276-82, 2010
                    26. James JJ et al: Mammographic features of breast cancers at single reading with computer-aided detection and at double reading in a large multicenter prospective trial of computer-aided detection: CADET II. Radiology. 256(2):379-86, 2010
                    27. Cawson JN et al: Invasive breast cancers detected by screening mammography: a detailed comparison of computer-aided detection-assisted single reading and double reading. J Med Imaging Radiat Oncol. 53(5):442-9, 2009
                    28. Duijm LE et al: Inter-observer variability in mammography screening and effect of type and number of readers on screening outcome. Br J Cancer. 100(6):901-7, 2009
                    29. Malich A et al: The performance of computer-aided detection when analyzing prior mammograms of newly detected breast cancers with special focus on the time interval from initial imaging to detection. Eur J Radiol. 69:574-8, 2009
                    30. Noble M et al: Computer-aided detection mammography for breast cancer screening: systematic review and meta-analysis. Arch Gynecol Obstet. 279(6):881-90, 2009
                    31. Gromet M: Comparison of computer-aided detection to double reading of screening mammograms: review of 231,221 mammograms. AJR Am J Roentgenol. 190(4):854-9, 2008
                    32. Kim SJ et al: Computer-aided detection in full-field digital mammography: sensitivity and reproducibility in serial examinations. Radiology. 246(1):71-80, 2008
                    33. Fenton JJ et al: Influence of computer-aided detection on performance of screening mammography. N Engl J Med. 356(14):1399-409, 2007
                    34. Skaane P et al: Effect of computer-aided detection on independent double reading of paired screen-film and full-field digital screening mammograms. AJR Am J Roentgenol. 188(2):377-84, 2007
                    35. Yang SK et al: Screening mammography-detected cancers: sensitivity of a computer-aided detection system applied to full-field digital mammograms. Radiology. 244(1):104-11, 2007
                    36. Dean JC et al: Improved cancer detection using computer-aided detection with diagnostic and screening mammography: prospective study of 104 cancers. AJR Am J Roentgenol. 187(1):20-8, 2006
                    37. Ko JM et al: Prospective assessment of computer-aided detection in interpretation of screening mammography. AJR Am J Roentgenol. 187(6):1483-91, 2006
                    38. Lindfors KK et al: Computer-aided detection of breast cancer: a cost-effectiveness study. Radiology. 239(3):710-7, 2006
                    39. Morton MJ et al: Screening mammograms: interpretation with computer-aided detection--prospective evaluation. Radiology. 239(2):375-83, 2006
                    40. Birdwell RL et al: Computer-aided detection with screening mammography in a university hospital setting. Radiology. 236(2):451-7, 2005
                    41. Burhenne LJW: Proficiency in mammography: interpretive skills, computer-aided detection, and double reading. Breast Imaging: RSNA Categorical Course in Diagnostic Radiology. 93-106, 2005
                    42. Cupples TE et al: Impact of computer-aided detection in a regional screening mammography program. AJR Am J Roentgenol. 185(4):944-50, 2005
                    43. Khoo LA et al: Computer-aided detection in the United Kingdom National Breast Screening Programme: prospective study. Radiology. 237(2):444-9, 2005
                    44. Soo MS et al: Computer-aided detection of amorphous calcifications. AJR Am J Roentgenol. 184(3):887-92, 2005
                    45. Destounis SV et al: Can computer-aided detection with double reading of screening mammograms help decrease the false-negative rate? Initial experience. Radiology. 232(2):578-84, 2004
                    46. Feig SA et al: Re: Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system. J Natl Cancer Inst. 96(16):1260-1; author reply 1261, 2004
                    47. Helvie MA et al: Sensitivity of noncommercial computer-aided detection system for mammographic breast cancer detection: pilot clinical trial. Radiology. 231(1):208-14, 2004
                    48. Baker JA et al: Computer-aided detection (CAD) in screening mammography: sensitivity of commercial CAD systems for detecting architectural distortion. AJR Am J Roentgenol. 181(4):1083-8, 2003
                    49. Beam CA et al: Association of volume and volume-independent factors with accuracy in screening mammogram interpretation. J Natl Cancer Inst. 95(4):282-90, 2003
                    50. Beam CA: Interpretation error in mammography: taxonomy and measurement. Semin Breast Dis. 6:153-5, 2003
                    51. Ciatto S et al: Comparison of standard reading and computer aided detection (CAD) on a national proficiency test of screening mammography. Eur J Radiol. 45(2):135-8, 2003
                    52. Harvey SC et al: Increase in cancer detection and recall rates with independent double interpretation of screening mammography. AJR Am J Roentgenol. 180(5):1461-7, 2003
                    53. Malich A et al: Influence of breast lesion size and histologic findings on tumor detection rate of a computer-aided detection system. Radiology. 228(3):851-6, 2003
                    54. Sickles EA et al: Performance parameters for screening and diagnostic mammography: specialist and general radiologists. Radiology. 224(3):861-9, 2002
                    55. Brem RF et al: Radiologist detection of microcalcifications with and without computer-aided detection: a comparative study. Clin Radiol. 56(2):150-4, 2001
                    56. Freer TW et al: Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. Radiology. 220(3):781-6, 2001
                    Related Anatomy
                    Loading...
                    Related Differential Diagnoses
                    Loading...
                    References
                    Tables

                    Tables

                    KEY FACTS

                    • Terminology

                      • Imaging

                        • Clinical Issues

                          TERMINOLOGY

                          • Abbreviations

                            • Computer-aided/-assisted detection (CAD)
                              • Distinguish from computer-aided diagnosis
                            • CAD + R: CAD + single reader
                          • Definitions

                            • CAD
                              • Neural network-generated prompts (marks) highlight areas of concern, directing attention of interpreting radiologist
                              • Analog films must be digitized and then processed with a CAD algorithm; digitally acquired images directly interface with the CAD system
                                • CAD marks are displayed on low-resolution workstation images by pushing button or on paper printout
                              • For digital mammography, CAD systems interface directly with workstation on which mammograms are interpreted
                                • CAD engaged by pushing button on workstation console; CAD marks displayed directly over mammographic images
                              • Recognized marks (e.g., asterisks or triangles) project over/near findings recognized by neural network
                              • Interpreting radiologist makes final determination as to assessment
                                • Negative or benign, return to screening interval (BI-RADS 1, 2)
                                • Abnormal, requires additional imaging evaluation (BI-RADS 0); probably benign (BI-RADS 3); recommend biopsy (BI-RADS 4, 5)
                                • Vast majority of CAD prompts are dismissed by interpreting radiologist
                              • False-positive (FP) prompts: CAD-generated prompts in areas where no cancer is present
                            • Computer-aided diagnosis: Computer-generated statistical assessment of imaging findings suggesting likelihood of malignancy based on comparison with large number of similar findings
                            • Double reading: ≥ 2 independent radiologists interpret same group of images
                              • Discordant readings assigned assessment by consensus or arbitration
                                • Consensus: Discussion among interpreting radiologists
                                • Arbitration: 3rd radiologist makes independent decision
                                • ↑ perception (sensitivity) and ↑ specificity
                              • May act on all cases indicated as abnormal from either reading
                                • ↑ perception (sensitivity) and ↓ specificity
                            • Screening mammography
                              • Asymptomatic standard MLO and CC screening mammograms performed and evaluated for quality assurance by technologists
                              • Women arrive and leave center without waiting for either verbal or written reports, not monitored by physician
                              • Mammograms "batch-read" by radiologist in concentrated and focused setting
                              • Mammograms are either deemed negative, benign (BI-RADS 1, 2), or incomplete (BI-RADS 0)
                              • Women receive via mail or phone call either standard negative report or recommendation to return for additional imaging or biopsy
                            • Recall rate: Percentage of women with recommendation to return for further imaging or biopsy prior to next screening examination
                              • Desired goal (benchmarks) < 10% recall rate
                                • When prior, recent comparisons available, recall rate 30% lower than for baseline (1st mammogram) or no priors
                              • Costs (financial and emotional) related to recall rates must be considered
                              • Most recalled cases do not undergo biopsy: 10% recall → 1-2% biopsy rate; 15-35% PPV of biopsy

                          IMAGING

                          • General Features

                            PATHOLOGY

                            • General Pathologic Considerations

                              CLINICAL ISSUES

                              • Clinical Importance

                                • Expected Performance

                                  DIAGNOSTIC CHECKLIST

                                  • Consider

                                    • Image Interpretation Pearls

                                      Selected References

                                      1. Henriksen EL et al: The efficacy of using computer-aided detection (CAD) for detection of breast cancer in mammography screening: a systematic review. Acta Radiol. 60(1):13-8, 2019
                                      2. Conant E et al: Improving accuracy and efficiency with concurrent use of artificial intelligence for digital breast tomosynthesis screening. Radiological Society of North America 2018 Scientific Assembly and Annual Meeting, November 26, 2018, Chicago IL (abstr)
                                      3. Benedikt RA et al: Concurrent computer-aided detection improves reading time of digital breast tomosynthesis and maintains interpretation performance in a multireader multicase study. AJR Am J Roentgenol. 210(3):685-94, 2018
                                      4. James JJ et al: Evaluation of a computer-aided detection (CAD)-enhanced 2D synthetic mammogram: comparison with standard synthetic 2D mammograms and conventional 2D digital mammography. Clin Radiol. 73(10):886-92, 2018
                                      5. Katzen J et al: A review of computer aided detection in mammography. Clin Imaging. 52:305-9, 2018
                                      6. Keen JD et al: Utilization of computer-aided detection for digital screening mammography in the United States, 2008 to 2016. J Am Coll Radiol. 15(1 Pt A):44-8, 2018
                                      7. Balleyguier C et al: Improving digital breast tomosynthesis reading time: a pilot multi-reader, multi-case study using concurrent Computer-Aided Detection (CAD). Eur J Radiol. 97:83-89, 2017
                                      8. Cho KR et al: Breast cancer detection in a screening population: comparison of digital mammography, computer-aided detection applied to digital mammography and breast ultrasound. J Breast Cancer. 19(3):316-23, 2016
                                      9. Lehman CD et al: Diagnostic accuracy of digital screening mammography with and without computer-aided detection. JAMA Intern Med. 175(11):1828-37, 2015
                                      10. Morra L et al: Breast cancer: computer-aided detection with digital breast tomosynthesis. Radiology. 141959, 2015
                                      11. Bargalló X et al: Single reading with computer-aided detection performed by selected radiologists in a breast cancer screening program. Eur J Radiol. 83(11):2019-23, 2014
                                      12. Cole EB et al: Impact of computer-aided detection systems on radiologist accuracy with digital mammography. AJR Am J Roentgenol. 203(4):909-16, 2014
                                      13. Bargalló X et al: Role of computer-aided detection in very small screening detected invasive breast cancers. J Digit Imaging. 26(3):572-7, 2013
                                      14. Fenton JJ et al: Short-term outcomes of screening mammography using computer-aided detection: a population-based study of medicare enrollees. Ann Intern Med. 158(8):580-7, 2013
                                      15. Murakami R et al: Detection of breast cancer with a computer-aided detection applied to full-field digital mammography. J Digit Imaging. 26(4):768-73, 2013
                                      16. Park CS et al: Detection of breast cancer in asymptomatic and symptomatic groups using computer-aided detection with full-field digital mammography. J Breast Cancer. 16(3):322-8, 2013
                                      17. Destounis SV et al: CAD may not be necessary for microcalcifications in the digital era, CAD may benefit radiologists for masses. J Clin Imaging Sci. 2:45, 2012
                                      18. Geller BM et al: Is confidence of mammographic assessment a good predictor of accuracy? AJR Am J Roentgenol. 199(1):W134-41, 2012
                                      19. Nishikawa RM et al: Clinically missed cancer: how effectively can radiologists use computer-aided detection? AJR Am J Roentgenol. 198(3) :708-16, 2012
                                      20. Scaranelo AM et al: Evaluation of breast amorphous calcifications by a computer-aided detection system in full-field digital mammography. Br J Radiol. 85:517-22, 2012
                                      21. Waldmann A et al: Benefits of the quality assured double and arbitration reading of mammograms in the early diagnosis of breast cancer in symptomatic women. Eur Radiol. 22(5):1014-22, 2012
                                      22. Berlin L: Mammographic CAD markings: archive or discard? AJR Am J Roentgenol. 196:W659, 2011
                                      23. Fenton JJ et al: Effectiveness of computer-aided detection in community mammography practice. J Natl Cancer Inst. 103(15):1152-61, 2011
                                      24. Glynn CG et al: Effect of transition to digital mammography on clinical outcomes. Radiology. 260(3):664-70, 2011
                                      25. Cho N et al: Features of prospectively overlooked computer-aided detection marks on prior screening digital mammograms in women with breast cancer. AJR Am J Roentgenol. 195(5):1276-82, 2010
                                      26. James JJ et al: Mammographic features of breast cancers at single reading with computer-aided detection and at double reading in a large multicenter prospective trial of computer-aided detection: CADET II. Radiology. 256(2):379-86, 2010
                                      27. Cawson JN et al: Invasive breast cancers detected by screening mammography: a detailed comparison of computer-aided detection-assisted single reading and double reading. J Med Imaging Radiat Oncol. 53(5):442-9, 2009
                                      28. Duijm LE et al: Inter-observer variability in mammography screening and effect of type and number of readers on screening outcome. Br J Cancer. 100(6):901-7, 2009
                                      29. Malich A et al: The performance of computer-aided detection when analyzing prior mammograms of newly detected breast cancers with special focus on the time interval from initial imaging to detection. Eur J Radiol. 69:574-8, 2009
                                      30. Noble M et al: Computer-aided detection mammography for breast cancer screening: systematic review and meta-analysis. Arch Gynecol Obstet. 279(6):881-90, 2009
                                      31. Gromet M: Comparison of computer-aided detection to double reading of screening mammograms: review of 231,221 mammograms. AJR Am J Roentgenol. 190(4):854-9, 2008
                                      32. Kim SJ et al: Computer-aided detection in full-field digital mammography: sensitivity and reproducibility in serial examinations. Radiology. 246(1):71-80, 2008
                                      33. Fenton JJ et al: Influence of computer-aided detection on performance of screening mammography. N Engl J Med. 356(14):1399-409, 2007
                                      34. Skaane P et al: Effect of computer-aided detection on independent double reading of paired screen-film and full-field digital screening mammograms. AJR Am J Roentgenol. 188(2):377-84, 2007
                                      35. Yang SK et al: Screening mammography-detected cancers: sensitivity of a computer-aided detection system applied to full-field digital mammograms. Radiology. 244(1):104-11, 2007
                                      36. Dean JC et al: Improved cancer detection using computer-aided detection with diagnostic and screening mammography: prospective study of 104 cancers. AJR Am J Roentgenol. 187(1):20-8, 2006
                                      37. Ko JM et al: Prospective assessment of computer-aided detection in interpretation of screening mammography. AJR Am J Roentgenol. 187(6):1483-91, 2006
                                      38. Lindfors KK et al: Computer-aided detection of breast cancer: a cost-effectiveness study. Radiology. 239(3):710-7, 2006
                                      39. Morton MJ et al: Screening mammograms: interpretation with computer-aided detection--prospective evaluation. Radiology. 239(2):375-83, 2006
                                      40. Birdwell RL et al: Computer-aided detection with screening mammography in a university hospital setting. Radiology. 236(2):451-7, 2005
                                      41. Burhenne LJW: Proficiency in mammography: interpretive skills, computer-aided detection, and double reading. Breast Imaging: RSNA Categorical Course in Diagnostic Radiology. 93-106, 2005
                                      42. Cupples TE et al: Impact of computer-aided detection in a regional screening mammography program. AJR Am J Roentgenol. 185(4):944-50, 2005
                                      43. Khoo LA et al: Computer-aided detection in the United Kingdom National Breast Screening Programme: prospective study. Radiology. 237(2):444-9, 2005
                                      44. Soo MS et al: Computer-aided detection of amorphous calcifications. AJR Am J Roentgenol. 184(3):887-92, 2005
                                      45. Destounis SV et al: Can computer-aided detection with double reading of screening mammograms help decrease the false-negative rate? Initial experience. Radiology. 232(2):578-84, 2004
                                      46. Feig SA et al: Re: Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system. J Natl Cancer Inst. 96(16):1260-1; author reply 1261, 2004
                                      47. Helvie MA et al: Sensitivity of noncommercial computer-aided detection system for mammographic breast cancer detection: pilot clinical trial. Radiology. 231(1):208-14, 2004
                                      48. Baker JA et al: Computer-aided detection (CAD) in screening mammography: sensitivity of commercial CAD systems for detecting architectural distortion. AJR Am J Roentgenol. 181(4):1083-8, 2003
                                      49. Beam CA et al: Association of volume and volume-independent factors with accuracy in screening mammogram interpretation. J Natl Cancer Inst. 95(4):282-90, 2003
                                      50. Beam CA: Interpretation error in mammography: taxonomy and measurement. Semin Breast Dis. 6:153-5, 2003
                                      51. Ciatto S et al: Comparison of standard reading and computer aided detection (CAD) on a national proficiency test of screening mammography. Eur J Radiol. 45(2):135-8, 2003
                                      52. Harvey SC et al: Increase in cancer detection and recall rates with independent double interpretation of screening mammography. AJR Am J Roentgenol. 180(5):1461-7, 2003
                                      53. Malich A et al: Influence of breast lesion size and histologic findings on tumor detection rate of a computer-aided detection system. Radiology. 228(3):851-6, 2003
                                      54. Sickles EA et al: Performance parameters for screening and diagnostic mammography: specialist and general radiologists. Radiology. 224(3):861-9, 2002
                                      55. Brem RF et al: Radiologist detection of microcalcifications with and without computer-aided detection: a comparative study. Clin Radiol. 56(2):150-4, 2001
                                      56. Freer TW et al: Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. Radiology. 220(3):781-6, 2001