Discriminating solitary cysts from soft tissue lesions in mammography using a pretrained deep convolutional neural network

Medical Physics

Volumn 44, Issue 3, 2017, Pages 1017-1027

  Kooi, Thijs ^a   van Ginneken, Bram ^a   Karssemeijer, Nico ^a   Den Heeten, Ard ^b  

^a RADBOUD UNIVERSITY MEDICAL CENTER   (Netherlands)

^b ACADEMIC MEDICAL CENTER   (Netherlands)

Author keywords

breast cancer; computer aided diagnosis; deep learning; solitary cysts; transfer learning

Indexed keywords

CLASSIFICATION (OF INFORMATION); COMPUTER AIDED INSTRUCTION; CONVOLUTION; DECISION SUPPORT SYSTEMS; DEEP NEURAL NETWORKS; DISEASES; LARGE DATASET; MAMMOGRAPHY; MEDICAL PROBLEMS; TISSUE;

AREA UNDER THE ROC CURVE; BREAST CANCER; CONVOLUTIONAL NEURAL NETWORK; DEEP LEARNING; FOLLOW UP; MALIGNANT MASS; PERFORMANCE; SOFT TISSUE; SOLITARY CYST; TRANSFER LEARNING;

COMPUTER AIDED DIAGNOSIS;

AREA UNDER THE CURVE; ARTIFICIAL NEURAL NETWORK; BREAST CYST; BREAST TUMOR; COMPUTER ASSISTED DIAGNOSIS; DIAGNOSTIC IMAGING; DIFFERENTIAL DIAGNOSIS; FALSE POSITIVE RESULT; FEMALE; HUMAN; INFORMATION PROCESSING; MAMMOGRAPHY; PROCEDURES; RECEIVER OPERATING CHARACTERISTIC;

AREA UNDER CURVE; BREAST CYST; BREAST NEOPLASMS; DATASETS AS TOPIC; DIAGNOSIS, DIFFERENTIAL; FALSE POSITIVE REACTIONS; FEMALE; HUMANS; MAMMOGRAPHY; NEURAL NETWORKS (COMPUTER); RADIOGRAPHIC IMAGE INTERPRETATION, COMPUTER-ASSISTED; ROC CURVE;

EID: 85016248526     PISSN: 00942405     EISSN: 24734209     Source Type: Journal    
DOI: 10.1002/MP.12110     Document Type: Article

References (43)

1. Dixon JM, McDonald C, Elton R, Miller W. Risk of breast cancer in women with palpable breast cysts: A prospective study. Lancet. 1999;353:1742–1745.
2. Erhard K, Kilburn-Toppin F, Willsher P, et al. Characterization of cystic lesions by spectral mammography: Results of a clinical pilot study. Invest Radiol. 2016;51:340–347.
3. Sickles EA. Probably benign breast lesions: When should follow-up be recommended and what is the optimal follow-up protocol? Radiology. 1999;213:11–14.
4. Brodersen J, Siersma VD. Long-term psychosocial consequences of false-positive screening mammography. Ann Fam Med. 2013;112:106– 115.
5. Kunio D. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential. Comput Med Imaging Graph. 2007;31:198–211.
6. Van Ginneken B, Schaefer-Prokop C, Prokop M. Computer-aided diag-nosis: How to move from the laboratory to the clinic. Radiology. 2011;261:719–732.
7. Rao VM, Levin DC, Parker L, Cavanaugh B, Frangos AJ, Sunshine JH. How widely is computer-aided detection used in screening and diagnostic mammography? J Am Coll Radiol. 2010;7:802–805.
8. Malich A, Fischer DR, Bottcher J. CAD for mammography: The tech-nique, results, current role and further developments. Eur Radiol. 2006;16:1449–1460.
9. Fenton JJ, Abraham L, Taplin SH, et al. Effectiveness of computer-aided detection in community mammography practice. J Natl Cancer Inst. 2011;103:1152–1161.
10. Lehman CD, Wellman RD, Buist DS, Kerlikowske K, Tosteson AN, Miglioretti DL, and Breast Cancer Surveillance Consortium. Diagnostic accuracy of digital screening mammography with and without computer-aided detection. JAMA Intern Med. 2015;175:1828–1837.
11. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436– 444.
12. Schmidhuber J. Deep learning in neural networks: An overview. Neural Netw. 2015;61:85–117.
13. Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning. Nature. 2015;518:529–533.
14. Silver D, Huang A, Maddison CJ, et al. Mastering the game of go with deep neural networks and tree search. Nature. 2016;529:484– 489.
15. Ciresßan DC, Giusti A, Gambardella LM, Schmidhuber J. Mitosis detection in breast cancer histology images with deep neural networks. In: Medical Image Computing and Computer-Assisted Intervention. vol 8150 of Lecture Notes in Computer Science. Berlin, Heidelberg: Springer; 2013:411–418.
16. Prasoon A, Petersen K, Igel C, Lauze F, Dam E, Nielsen M. Deep fea-ture learning for knee cartilage segmentation using a triplanar convolu-tional neural network. Med Image Comput Comput Assist Interv. 2013;16:246–253.
17. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer Assisted Intervention. Munich, Germany: Springer International Pub-lishing; 2015;234–241.
18. Lake BM, Ullman TD, Tenenbaum JB, Gershman SJ. Building machines that learn and think like people. 2016. arXiv:1604.00289.
19. Ciompi F, De Hoop B, Van Riel SJ, et al. Automatic classification of pulmonary peri-fissural nodules in computed tomography using an ensemble of 2d views and a convolutional neural network out-of-the-box. Med Image Anal. 2015;26:195–202.
20. Bar Y, Diamant I, Wolf L, Greenspan H. Deep learning with non-medi-cal training used for chest pathology identification. In: Medical Imaging. Proceedings of the SPIE, page 94140V. International Society for Optics and Photonics, 2015.
21. Hofmanninger J, Langs G. Mapping visual features to semantic profiles for retrieval in medical imaging. In: Computer Vision and Pattern Recognition. Boston, MA: IEEE Publishing; 2015;457–465.
22. Shin HC, Lu L, Kim L, Seff A, Yao J, Summers RM. Interleaved text/ image deep mining on a very large-scale radiology database. In: Computer Vision and Pattern Recognition. Boston, MA: IEEE Publishing; 2015;1090–1099.
23. Shin HC, Roth HR, Gao M, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging. 2016;35:1285–1298.
24. Tajbakhsh N, Shin JY, Gurudu SR, et al. Convolutional neural networks for medical image analysis: Fine tuning or full training? IEEE Trans Med Imaging. 2016;35:1299–1312.
25. Russakovsky O, Deng J, Su H, et al. Imagenet large scale visual recognition challenge. Int J Comput Vision. 2014;115:1–42.
26. Oquab M, Bottou L, Laptev I, Sivic J. Learning and transferring midle-vel image representations using convolutional neural networks. In: Computer Vision and Pattern Recognition. Columbus, OH: IEEE publishing; 2014;1717–1724 p.
27. Yue-Hei Ng J, Hausknecht M, Vijayanarasimhan S, Vinyals O, Monga R, Toderici G. Beyond short snippets: Deep networks for video classifi-cation. 2015. arXiv:150308909.
28. Karssemeijer N, te Brake G. Detection of stellate distortions in mammo-grams. IEEE Trans Med Imaging. 1996;15:611–619.
29. Kooi T, Karssemeijer N. Invariant features for discriminating cysts from solid lesions in mammography. In: Breast Imaging. Gifu: Springer, 2014:573–580.
30. Timp S, Karssemeijer N. A new 2D segmentation method based on dynamic programming applied to computer aided detection in mammog-raphy. Med Phys. 2004;31:958–971.
31. James B, Olivier B, Frederic B, et al. Theano: A CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference (SciPy). vol 4, 2010;3.
32. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. arXiv:14091556.
33. Kooi T, Litjens G, Van Ginneken B, et al. Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal. 2016;35:303–312.
34. Kooi T, Gubern-Merida A, Mordang JJ, et al. A comparison between a deep convolutional neural network and radiologists for classifying regions of interest in mammography. In: Tingberg A, et al., editor, Breast Imaging. vol 9699 of Lecture Notes in Computer Science, Malmo: Springer International Publishing Switzerland, 2016;51–56.
35. Kingma D, Ba J. ADAM: A method for stochastic optimization. 2015. arXiv:14126980.
36. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15:1929–1958.
37. He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Computer Vision and Pattern Recognition. 2015;1026–1034.
38. Friedman JH. Greedy function approximation: A gradient boosting machine. Annals of Statistics. 2001:1189–1232.
39. Efron B. Bootstrap methods: Another look at the jackknife. Ann Stat. 1979;7:1–26.
40. Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. 2015. arXiv:14114038.
41. Bruna J, Mallat S. Invariant scattering convolution networks. IEEE Trans Pattern Anal Mach Intell. 2013;35:1872–1886.
42. Cohen TS, Welling M. Transformation properties of learned visual rep-resentations. 2014. arXiv:1412.7659.
43. Dieleman S, De Fauw J, Kavukcuoglu K. Exploiting cyclic symmetry in convolutional neural networks. 2016. arXiv:1602.02660.