Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-Based Artificial Intelligence for Mammography

  • Jung Hyun Yoon (Department of Radiology, Severance Hospital, Research Institute of Radiological Science) ;
  • Eun-Kyung Kim (Department of Radiology, Yongin Severance Hospital, Yonsei University, College of Medicine)
  • Received : 2020.10.05
  • Accepted : 2021.01.17
  • Published : 2021.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

During the past decade, researchers have investigated the use of computer-aided mammography interpretation. With the application of deep learning technology, artificial intelligence (AI)-based algorithms for mammography have shown promising results in the quantitative assessment of parenchymal density, detection and diagnosis of breast cancer, and prediction of breast cancer risk, enabling more precise patient management. AI-based algorithms may also enhance the efficiency of the interpretation workflow by reducing both the workload and interpretation time. However, more in-depth investigation is required to conclusively prove the effectiveness of AI-based algorithms. This review article discusses how AI algorithms can be applied to mammography interpretation as well as the current challenges in its implementation in real-world practice.

Keywords

Acknowledgement

The authors thank Medical Illustration & Design, part of the Medical Research Support Services of Yonsei University College of Medicine, for artistic support related to this work.

References

  1. World Health Organization. IARC handbooks. Breast cancer screening. Volume 15. Lyon: International Agency for Research on Cancer, 2015
  2. Myers ER, Moorman P, Gierisch JM, Havrilesky LJ, Grimm LJ, Ghate S, et al. Benefits and harms of breast cancer screening: a systematic review. JAMA 2015;314:1615-1634 https://doi.org/10.1001/jama.2015.13183
  3. Lauby-Secretan B, Scoccianti C, Loomis D, Benbrahim-Tallaa L, Bouvard V, Bianchini F, et al. Breast-cancer screening--viewpoint of the IARC Working Group. N Engl J Med 2015;372:2353-2358 https://doi.org/10.1056/NEJMsr1504363
  4. Taylor-Phillips S, Stinton C. Double reading in breast cancer screening: considerations for policy-making. Br J Radiol 2020;93:20190610
  5. Houssami N, Lee CI, Buist DSM, Tao D. Artificial intelligence for breast cancer screening: opportunity or hype? Breast 2017;36:31-33 https://doi.org/10.1016/j.breast.2017.09.003
  6. Bi WL, Hosny A, Schabath MB, Giger ML, Birkbak NJ, Mehrtash A, et al. Artificial intelligence in cancer imaging: clinical challenges and applications. CA Cancer J Clin 2019;69:127-157 https://doi.org/10.3322/caac.21552
  7. Abbasi J. Artificial intelligence improves breast cancer screening in study. JAMA 2020;323:499
  8. 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 https://doi.org/10.1148/radiol.2203001282
  9. Birdwell RL, Bandodkar P, Ikeda DM. Computer-aided detection with screening mammography in a university hospital setting. Radiology 2005;236:451-457 https://doi.org/10.1148/radiol.2362040864
  10. Fenton JJ, Abraham L, Taplin SH, Geller BM, Carney PA, D'Orsi C, et al. Effectiveness of computer-aided detection in community mammography practice. J Natl Cancer Inst 2011;103:1152-1161 https://doi.org/10.1093/jnci/djr206
  11. Lehman CD, Wellman RD, Buist DS, Kerlikowske K, Tosteson AN, Miglioretti DL. Diagnostic accuracy of digital screening mammography with and without computer-aided detection. JAMA Intern Med 2015;175:1828-1837 https://doi.org/10.1001/jamainternmed.2015.5231
  12. Khoo LA, Taylor P, Given-Wilson RM. Computer-aided detection in the United Kingdom National Breast Screening Programme: prospective study. Radiology 2005;237:444-449 https://doi.org/10.1148/radiol.2372041362
  13. Malich A, Marx C, Facius M, Boehm T, Fleck M, Kaiser WA. Tumour detection rate of a new commercially available computer-aided detection system. Eur Radiol 2001;11:2454-2459 https://doi.org/10.1007/s003300101079
  14. Fenton JJ, Taplin SH, Carney PA, Abraham L, Sickles EA, D'Orsi C, et al. Influence of computer-aided detection on performance of screening mammography. N Engl J Med 2007;356:1399-1409 https://doi.org/10.1056/NEJMoa066099
  15. Cole EB, Zhang Z, Marques HS, Edward Hendrick R, Yaffe MJ, Pisano ED. Impact of computer-aided detection systems on radiologist accuracy with digital mammography. AJR Am J Roentgenol 2014;203:909-916 https://doi.org/10.2214/AJR.12.10187
  16. Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism 2017;69S:S36-S40 https://doi.org/10.1016/j.metabol.2017.01.011
  17. Park SH, Kressel HY. Connecting technological innovation in artificial intelligence to real-world medical practice through rigorous clinical validation: what peer-reviewed medical journals could do. J Korean Med Sci 2018;33:e152
  18. Giger ML. Machine learning in medical imaging. J Am Coll Radiol 2018;15:512-520 https://doi.org/10.1016/j.jacr.2017.12.028
  19. Cabitza F, Rasoini R, Gensini GF. Unintended consequences of machine learning in medicine. JAMA 2017;318:517-518 https://doi.org/10.1001/jama.2017.7797
  20. Chang PJ. Moving artificial intelligence from feasible to real: time to drill for gas and build roads. Radiology 2020;294:432-433 https://doi.org/10.1148/radiol.2019192527
  21. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal 2017;42:60-88 https://doi.org/10.1016/j.media.2017.07.005
  22. Mendelson EB. Artificial intelligence in breast imaging: potentials and limitations. AJR Am J Roentgenol 2019;212:293-299 https://doi.org/10.2214/AJR.18.20532
  23. Kim HE, Kim HH, Han BK, Kim KH, Han K, Nam H, et al. Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multireader study. Lancet Digit Health 2020;2:e138-e148 https://doi.org/10.1016/S2589-7500(20)30003-0
  24. McKinney SM, Sieniek M, Godbole V, Godwin J, Antropova N, Ashrafian H, et al. International evaluation of an AI system for breast cancer screening. Nature 2020;577:89-94 https://doi.org/10.1038/s41586-019-1799-6
  25. Rodriguez-Ruiz A, Lang K, Gubern-Merida A, Broeders M, Gennaro G, Clauser P, et al. Stand-alone artificial intelligence for breast cancer detection in mammography: comparison with 101 radiologists. J Natl Cancer Inst 2019;111:916-922 https://doi.org/10.1093/jnci/djy222
  26. Rodriguez-Ruiz A, Krupinski E, Mordang JJ, Schilling K, Heywang-Kobrunner SH, Sechopoulos I, et al. Detection of breast cancer with mammography: effect of an artificial intelligence support system. Radiology 2019;290:305-314 https://doi.org/10.1148/radiol.2018181371
  27. Trister AD, Buist DSM, Lee CI. Will machine learning tip the balance in breast cancer screening? JAMA Oncol 2017;3:1463-1464 https://doi.org/10.1001/jamaoncol.2017.0473
  28. Kooi T, Litjens G, van Ginneken B, Gubern-Merida A, Sanchez CI, Mann R, et al. Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal 2017;35:303-312 https://doi.org/10.1016/j.media.2016.07.007
  29. Schaffter T, Buist DSM, Lee CI, Nikulin Y, Ribli D, Guan Y, et al. Evaluation of combined artificial intelligence and radiologist assessment to interpret screening mammograms. JAMA Netw Open 2020;3:e200265
  30. Salim M, Wahlin E, Dembrower K, Azavedo E, Foukakis T, Liu Y, et al. External evaluation of 3 commercial artificial intelligence algorithms for independent assessment of screening mammograms. JAMA Oncol 2020;6:1581-1588 https://doi.org/10.1001/jamaoncol.2020.3321
  31. Vedantham S, Karellas A, Vijayaraghavan GR, Kopans DB. Digital breast tomosynthesis: state of the art. Radiology 2015;277:663-684 https://doi.org/10.1148/radiol.2015141303
  32. Ciatto S, Houssami N, Bernardi D, Caumo F, Pellegrini M, Brunelli S, et al. Integration of 3D digital mammography with tomosynthesis for population breast-cancer screening (STORM): a prospective comparison study. Lancet Oncol 2013;14:583-589 https://doi.org/10.1016/S1470-2045(13)70134-7
  33. Friedewald SM, Rafferty EA, Rose SL, Durand MA, Plecha DM, Greenberg JS, et al. Breast cancer screening using tomosynthesis in combination with digital mammography. JAMA 2014;311:2499-2507 https://doi.org/10.1001/jama.2014.6095
  34. McCarthy AM, Kontos D, Synnestvedt M, Tan KS, Heitjan DF, Schnall M, et al. Screening outcomes following implementation of digital breast tomosynthesis in a general-population screening program. J Natl Cancer Inst 2014;106:dju316
  35. Conant EF, Toledano AY, Periaswamy S, Fotin SV, Go J, Boatsman JE, et al. Improving accuracy and efficiency with concurrent use of artificial intelligence for digital breast tomosynthesis. Radiol Artif Intell 2019;1:e180096
  36. Gilbert FJ, Tucker L, Gillan MG, Willsher P, Cooke J, Duncan KA, et al. Accuracy of digital breast tomosynthesis for depicting breast cancer subgroups in a UK retrospective reading study (TOMMY Trial). Radiology 2015;277:697-706 https://doi.org/10.1148/radiol.2015142566
  37. Skaane P, Bandos AI, Gullien R, Eben EB, Ekseth U, Haakenaasen U, et al. Comparison of digital mammography alone and digital mammography plus tomosynthesis in a population-based screening program. Radiology 2013;267:47-56 https://doi.org/10.1148/radiol.12121373
  38. Korhonen KE, Weinstein SP, McDonald ES, Conant EF. Strategies to increase cancer detection: review of true-positive and false-negative results at digital breast tomosynthesis screening. Radiographics 2016;36:1954-1965 https://doi.org/10.1148/rg.2016160049
  39. Balleyguier C, Arfi-Rouche J, Levy L, Toubiana PR, Cohen-Scali F, Toledano AY, et al. Improving digital breast tomosynthesis reading time: a pilot multi-reader, multi-case study using concurrent Computer-Aided Detection (CAD). Eur J Radiol 2017;97:83-89 https://doi.org/10.1016/j.ejrad.2017.10.014
  40. Benedikt RA, Boatsman JE, Swann CA, Kirkpatrick AD, Toledano AY. Concurrent computer-aided detection improves reading time of digital breast tomosynthesis and maintains interpretation performance in a multireader multicase study. AJR Am J Roentgenol 2018;210:685-694 https://doi.org/10.2214/AJR.17.18185
  41. Chae EY, Kim HH, Jeong JW, Chae SH, Lee S, Choi YW. Decrease in interpretation time for both novice and experienced readers using a concurrent computer-aided detection system for digital breast tomosynthesis. Eur Radiol 2019;29:2518-2525 https://doi.org/10.1007/s00330-018-5886-0
  42. Kyono T, Gilbert FJ, van der Schaar M. Improving workflow efficiency for mammography using machine learning. J Am Coll Radiol 2020;17:56-63 https://doi.org/10.1016/j.jacr.2019.05.012
  43. Rodriguez-Ruiz A, Lang K, Gubern-Merida A, Teuwen J, Broeders M, Gennaro G, et al. Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study. Eur Radiol 2019;29:4825-4832 https://doi.org/10.1007/s00330-019-06186-9
  44. Yala A, Schuster T, Miles R, Barzilay R, Lehman C. A deep learning model to triage screening mammograms: a simulation study. Radiology 2019;293:38-46 https://doi.org/10.1148/radiol.2019182908
  45. Dembrower K, Wahlin E, Liu Y, Salim M, Smith K, Lindholm P, et al. Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: a retrospective simulation study. Lancet Digit Health 2020;2:e468-e474 https://doi.org/10.1016/S2589-7500(20)30185-0
  46. Harvey JA, Bovbjerg VE. Quantitative assessment of mammographic breast density: relationship with breast cancer risk. Radiology 2004;230:29-41 https://doi.org/10.1148/radiol.2301020870
  47. Boyd NF, Guo H, Martin LJ, Sun L, Stone J, Fishell E, et al. Mammographic density and the risk and detection of breast cancer. N Engl J Med 2007;356:227-236 https://doi.org/10.1056/NEJMoa062790
  48. McCormack VA, dos Santos Silva I. Breast density and parenchymal patterns as markers of breast cancer risk: a meta-analysis. Cancer Epidemiol Biomarkers Prev 2006;15:1159-1169 https://doi.org/10.1158/1055-9965.EPI-06-0034
  49. Mandelson MT, Oestreicher N, Porter PL, White D, Finder CA, Taplin SH, et al. Breast density as a predictor of mammographic detection: comparison of interval- and screen-detected cancers. J Natl Cancer Inst 2000;92:1081-1087 https://doi.org/10.1093/jnci/92.13.1081
  50. Kerlikowske K, Grady D, Barclay J, Sickles EA, Ernster V. Effect of age, breast density, and family history on the sensitivity of first screening mammography. JAMA 1996;276:33-38 https://doi.org/10.1001/jama.1996.03540010035027
  51. Bahl M, Baker JA, Bhargavan-Chatfield M, Brandt EK, Ghate SV. Impact of breast density notification legislation on radiologists' practices of reporting breast density: a multistate study. Radiology 2016;280:701-706 https://doi.org/10.1148/radiol.2016152457
  52. Hooley RJ, Greenberg KL, Stackhouse RM, Geisel JL, Butler RS, Philpotts LE. Screening US in patients with mammographically dense breasts: initial experience with Connecticut Public Act 09-41. Radiology 2012;265:59-69 https://doi.org/10.1148/radiol.12120621
  53. American College of Radiology. Breast imaging reporting and data system, 5th ed. Reston, VA: American College of Radiology, 2013
  54. Spayne MC, Gard CC, Skelly J, Miglioretti DL, Vacek PM, Geller BM. Reproducibility of BI-RADS breast density measures among community radiologists: a prospective cohort study. Breast J 2012;18:326-333 https://doi.org/10.1111/j.1524-4741.2012.01250.x
  55. Gard CC, Aiello Bowles EJ, Miglioretti DL, Taplin SH, Rutter CM. Misclassification of breast imaging reporting and data system (BI-RADS) mammographic density and implications for breast density reporting legislation. Breast J 2015;21:481-489 https://doi.org/10.1111/tbj.12443
  56. Sprague BL, Conant EF, Onega T, Garcia MP, Beaber EF, Herschorn SD, et al. Variation in mammographic breast density assessments among radiologists in clinical practice: a multicenter observational study. Ann Intern Med 2016;165:457-464 https://doi.org/10.7326/M15-2934
  57. Youk JH, Gweon HM, Son EJ, Kim JA. Automated volumetric breast density measurements in the era of the BI-RADS fifth edition: a comparison with visual assessment. AJR Am J Roentgenol 2016;206:1056-1062 https://doi.org/10.2214/AJR.15.15472
  58. Brandt KR, Scott CG, Ma L, Mahmoudzadeh AP, Jensen MR, Whaley DH, et al. Comparison of clinical and automated breast density measurements: implications for risk prediction and supplemental screening. Radiology 2016;279:710-719 https://doi.org/10.1148/radiol.2015151261
  59. Kallenberg M, Petersen K, Nielsen M, Ng AY, Pengfei Diao, Igel C, et al. Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring. IEEE Trans Med Imaging 2016;35:1322-1331 https://doi.org/10.1109/TMI.2016.2532122
  60. Lee J, Nishikawa RM. Automated mammographic breast density estimation using a fully convolutional network. Med Phys 2018;45:1178-1190 https://doi.org/10.1002/mp.12763
  61. Mohamed AA, Luo Y, Peng H, Jankowitz RC, Wu S. Understanding clinical mammographic breast density assessment: a deep learning perspective. J Digit Imaging 2018;31:387-392 https://doi.org/10.1007/s10278-017-0022-2
  62. Ciritsis A, Rossi C, Vittoria De Martini I, Eberhard M, Marcon M, Becker AS, et al. Determination of mammographic breast density using a deep convolutional neural network. Br J Radiol 2019;92:20180691
  63. Mohamed AA, Berg WA, Peng H, Luo Y, Jankowitz RC, Wu S. A deep learning method for classifying mammographic breast density categories. Med Phys 2018;45:314-321 https://doi.org/10.1002/mp.12683
  64. Lehman CD, Yala A, Schuster T, Dontchos B, Bahl M, Swanson K, et al. Mammographic breast density assessment using deep learning: clinical implementation. Radiology 2019;290:52-58 https://doi.org/10.1148/radiol.2018180694
  65. Gail MH, Brinton LA, Byar DP, Corle DK, Green SB, Schairer C, et al. Projecting individualized probabilities of developing breast cancer for white females who are being examined annually. J Natl Cancer Inst 1989;81:1879-1886 https://doi.org/10.1093/jnci/81.24.1879
  66. Claus EB, Risch N, Thompson WD. The calculation of breast cancer risk for women with a first degree family history of ovarian cancer. Breast Cancer Res Treat 1993;28:115-120 https://doi.org/10.1007/BF00666424
  67. Tyrer J, Duffy SW, Cuzick J. A breast cancer prediction model incorporating familial and personal risk factors. Stat Med 2004;23:1111-1130 https://doi.org/10.1002/sim.1668
  68. Tice JA, Cummings SR, Ziv E, Kerlikowske K. Mammographic breast density and the Gail model for breast cancer risk prediction in a screening population. Breast Cancer Res Treat 2005;94:115-122 https://doi.org/10.1007/s10549-005-5152-4
  69. Brentnall AR, Harkness EF, Astley SM, Donnelly LS, Stavrinos P, Sampson S, et al. Mammographic density adds accuracy to both the Tyrer-Cuzick and Gail breast cancer risk models in a prospective UK screening cohort. Breast Cancer Res 2015;17:147
  70. Ha R, Chang P, Karcich J, Mutasa S, Pascual Van Sant E, Liu MZ, et al. Convolutional neural network based breast cancer risk stratification using a mammographic dataset. Acad Radiol 2019;26:544-549 https://doi.org/10.1016/j.acra.2018.06.020
  71. Dembrower K, Liu Y, Azizpour H, Eklund M, Smith K, Lindholm P, et al. Comparison of a deep learning risk score and standard mammographic density score for breast cancer risk prediction. Radiology 2020;294:265-272 https://doi.org/10.1148/radiol.2019190872
  72. Kontos D, Winham SJ, Oustimov A, Pantalone L, Hsieh MK, Gastounioti A, et al. Radiomic phenotypes of mammographic parenchymal complexity: toward augmenting breast density in breast cancer risk assessment. Radiology 2019;290:41-49 https://doi.org/10.1148/radiol.2018180179
  73. Yala A, Lehman C, Schuster T, Portnoi T, Barzilay R. A deep learning mammography-based model for improved breast cancer risk prediction. Radiology 2019;292:60-66 https://doi.org/10.1148/radiol.2019182716
  74. Akselrod-Ballin A, Chorev M, Shoshan Y, Spiro A, Hazan A, Melamed R, et al. Predicting breast cancer by applying deep learning to linked health records and mammograms. Radiology 2019;292:331-342 https://doi.org/10.1148/radiol.2019182622
  75. Houssami N, Lee CI. The impact of legislation mandating breast density notification - Review of the evidence. Breast 2018;42:102-112 https://doi.org/10.1016/j.breast.2018.09.001
  76. Saulsberry L, Pace LE, Keating NL. The impact of breast density notification laws on supplemental breast imaging and breast biopsy. J Gen Intern Med 2019;34:1441-1451 https://doi.org/10.1007/s11606-019-05026-2
  77. Yassin NIR, Omran S, El Houby EMF, Allam H. Machine learning techniques for breast cancer computer aided diagnosis using different image modalities: a systematic review. Comput Methods Programs Biomed 2018;156:25-45 https://doi.org/10.1016/j.cmpb.2017.12.012
  78. Kim DW, Jang HY, Kim KW, Shin Y, Park SH. Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: results from recently published papers. Korean J Radiol 2019;20:405-410 https://doi.org/10.3348/kjr.2019.0025
  79. Sechopoulos I, Mann RM. Stand-alone artificial intelligence-The future of breast cancer screening? Breast 2020;49:254-260 https://doi.org/10.1016/j.breast.2019.12.014
  80. Mendel K, Li H, Sheth D, Giger M. Transfer learning from convolutional neural networks for computer-aided diagnosis: a comparison of digital breast tomosynthesis and full-field digital mammography. Acad Radiol 2019;26:735-743 https://doi.org/10.1016/j.acra.2018.06.019
  81. Geras KJ, Mann RM, Moy L. Artificial intelligence for mammography and digital breast tomosynthesis: current concepts and future perspectives. Radiology 2019;293:246-259 https://doi.org/10.1148/radiol.2019182627
  82. Gur D, Sumkin JH, Rockette HE, Ganott M, Hakim C, Hardesty L, et al. Changes in breast cancer detection and mammography recall rates after the introduction of a computer-aided detection system. J Natl Cancer Inst 2004;96:185-190 https://doi.org/10.1093/jnci/djh067
  83. Gilbert FJ, Astley SM, McGee MA, Gillan MG, Boggis CR, Griffiths PM, 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 https://doi.org/10.1148/radiol.2411051092
  84. Morton MJ, Whaley DH, Brandt KR, Amrami KK. Screening mammograms: interpretation with computer-aided detection--prospective evaluation. Radiology 2006;239:375-383 https://doi.org/10.1148/radiol.2392042121
  85. Gilbert FJ, Astley SM, Gillan MG, Agbaje OF, Wallis MG, James J, et al. Single reading with computer-aided detection for screening mammography. N Engl J Med 2008;359:1675-1684 https://doi.org/10.1056/NEJMoa0803545
  86. Becker AS, Marcon M, Ghafoor S, Wurnig MC, Frauenfelder T, Boss A. Deep learning in mammography: diagnostic accuracy of a multipurpose image analysis software in the detection of breast cancer. Invest Radiol 2017;52:434-440 https://doi.org/10.1097/RLI.0000000000000358
  87. Al-Masni MA, Al-Antari MA, Park JM, Gi G, Kim TY, Rivera P, et al. Simultaneous detection and classification of breast masses in digital mammograms via a deep learning YOLO-based CAD system. Comput Methods Programs Biomed 2018;157:85-94 https://doi.org/10.1016/j.cmpb.2018.01.017
  88. Bandeira Diniz JO, Bandeira Diniz PH, Azevedo Valente TL, Correa Silva A, de Paiva AC, Gattass M. Detection of mass regions in mammograms by bilateral analysis adapted to breast density using similarity indexes and convolutional neural networks. Comput Methods Programs Biomed 2018;156:191-207 https://doi.org/10.1016/j.cmpb.2018.01.007
  89. Ribli D, Horvath A, Unger Z, Pollner P, Csabai I. Detecting and classifying lesions in mammograms with deep learning. Sci Rep 2018;8:4165
  90. Chougrad H, Zouaki H, Alheyane O. Deep convolutional neural networks for breast cancer screening. Comput Methods Programs Biomed 2018;157:19-30 https://doi.org/10.1016/j.cmpb.2018.01.011