Mass detection in digital breast tomosynthesis: Deep convolutional neural network with transfer learning from mammography

Medical Physics

Volumn 43, Issue 12, 2016, Pages 6654-6666

  Samala, Ravi K ^a   Chan, Heang Ping ^a   Hadjiiski, Lubomir ^a   Helvie, Mark A ^a   Wei, Jun ^a   Cha, Kenny ^a  

^a UNIVERSITY OF MICHIGAN MEDICAL SCHOOL   (United States)

Author keywords

computer aided detection; convolutional neural network; deep learning; digital breast tomosynthesis; mass; transfer learning

Indexed keywords

COMPUTER AIDED DIAGNOSIS; COMPUTER AIDED INSTRUCTION; CONVOLUTION; DATA REDUCTION; DEEP NEURAL NETWORKS; E-LEARNING; FEATURE EXTRACTION; IMAGE SEGMENTATION; STATISTICAL TESTS; TOMOGRAPHY; X RAY SCREENS;

COMPUTER AIDED DETECTION; COMPUTER AIDED DETECTION SYSTEMS; CONVOLUTIONAL NEURAL NETWORK; DATA SET; DEEP-LEARNING; DIGITAL BREAST TOMOSYNTHESIS; MASS; MASS DETECTION; PERFORMANCE; TRANSFER LEARNING;

MAMMOGRAPHY;

CLASSIFIER; CLINICAL ARTICLE; DIAGNOSTIC TEST ACCURACY STUDY; DIGITAL BREAST TOMOSYNTHESIS; HUMAN; LEARNING; NERVOUS SYSTEM; RADIOLOGIST; RECEIVER OPERATING CHARACTERISTIC; SCREENING; STATISTICAL MODEL; STATISTICAL SIGNIFICANCE; ARTIFICIAL NEURAL NETWORK; BREAST TUMOR; COMPUTER ASSISTED DIAGNOSIS; DIAGNOSTIC IMAGING; IMAGE PROCESSING; MACHINE LEARNING; MAMMOGRAPHY; PROCEDURES;

BREAST NEOPLASMS; DIAGNOSIS, COMPUTER-ASSISTED; IMAGE PROCESSING, COMPUTER-ASSISTED; MACHINE LEARNING; MAMMOGRAPHY; NEURAL NETWORKS (COMPUTER);

EID: 85000788384     PISSN: 00942405     EISSN: 24734209     Source Type: Journal    
DOI: 10.1118/1.4967345     Document Type: Article

References (65)

1. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, and M. Bernstein, "ImageNet large scale visual recognition challenge," Int. J. Comput. Vision 115, 211-252 (2015). 10.1007/s11263-015-0816-y
2. J. Yosinski, J. Clune, Y. Bengio, and H. Lipson, "How transferable are features in deep neural networks?," in Advances in Neural Information Processing Systems (Red Hook, NY, 2014), pp. 3320-3328.
3. See breastscreening.cancer.gov for NCI-funded breast Cancer Surveillance Consortium (HHSN261201100031C), downloaded from the Breast Cancer Surveillance Consortium, 23 September 2013.
4. M. Broeders, S. Moss, L. Nyström, S. Njor, H. Jonsson, E. Paap, N. Massat, S. Duffy, E. Lynge, and E. Paci, "The impact of mammographic screening on breast cancer mortality in Europe: A review of observational studies," J. Med. Screening 19, 14-25 (2012). 10.1258/jms.2012.012078
5. B. Lauby-Secretan, C. Scoccianti, D. Loomis, L. Benbrahim-Tallaa, V. Bouvard, F. Bianchini, and K. Straif, "Breast-cancer screening-Viewpoint of the IARC Working Group," N. Engl. J. Med. 372, 2353-2358 (2015). 10.1056/NEJMsr1504363
6. L. T. Niklason et al., "Digital tomosynthesis in breast imaging," Radiology 205, 399-406 (1997). 10.1148/radiology.205.2.9356620
7. T. Wu et al., "Tomographic mammography using a limited number of low-dose cone-beam projection images," Med. Phys. 30, 365-380 (2003). 10.1118/1.1543934
8. I. Sechopoulos, "A review of breast tomosynthesis. Part I. The image acquisition process," Med. Phys. 40, 014301 (12pp.) (2013). 10.1118/1.4770279
9. K. Fukunaga and R. R. Hayes, "Effects of sample size on classifier design," IEEE Trans. Pattern Anal. Mach. Intell. 11, 873-885 (1989). 10.1109/34.31448
10. H.-P. Chan, B. Sahiner, R. F. Wagner, and N. Petrick, "Classifier design for computer-aided diagnosis: Effects of finite sample size on the mean performance of classical and neural network classifiers," Med. Phys. 26, 2654-2668 (1999). 10.1118/1.598805
11. H.-C. Shin, H. R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, J. Yao, D. Mollura, and R. M. Summers, "Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning," IEEE Trans. Med. Imaging 35, 1285-1298 (2016). 10.1109/TMI.2016.2528162
12. J. J. Näppi, T. Hironaka, D. Regge, and H. Yoshida, "Deep transfer learning of virtual endoluminal views for the detection of polyps in CT colonography," Proc. SPIE 9785, 97852B-1-97852B-8 (2016). 10.1117/12.2217260
13. A. Cruz-Roa, J. Arévalo, A. Judkins, A. Madabhushi, and F. González, "A method for medulloblastoma tumor differentiation based on convolutional neural networks and transfer learning," Proc. SPIE 9681, 968103-1-968103-8 (2015). 10.1117/12.2208825
14. N. Tajbakhsh, J. Y. Shin, S. R. Gurudu, R. T. Hurst, C. B. Kendall, M. B. Gotway, and J. Liang, "Convolutional neural networks for medical image Analysis: Full training or fine tuning?," IEEE Trans. Med. Imaging 35, 1299-1312 (2016). 10.1109/TMI.2016.2535302
15. H.-P. Chan, S. C. B. Lo, B. Sahiner, K. L. Lam, and M. A. Helvie, "Computer-aided detection of mammographic microcalcifications: Pattern recognition with an artificial neural network," Med. Phys. 22, 1555-1567 (1995). 10.1118/1.597428
16. B. Sahiner, H.-P. Chan, N. Petrick, D. Wei, M. A. Helvie, D. D. Adler, and M. M. Goodsitt, "Classification of mass and normal breast tissue: A convolution neural network classifier with spatial domain and texture images," IEEE Trans. Med. Imaging 15, 598-610 (1996). 10.1109/42.538937
17. J. Ge, B. Sahiner, L. M. Hadjiiski, H.-P. Chan, J. Wei, M. A. Helvie, and C. Zhou, "Computer aided detection of clusters of microcalcifications on full field digital mammograms," Med. Phys. 33, 2975-2988 (2006). 10.1118/1.2211710
18. R. K. Samala, H.-P. Chan, Y. Lu, L. Hadjiiski, J. Wei, and M. A. Helvie, "Digital breast tomosynthesis: Computer-aided detection of clustered microcalcifications on planar projection images," Phys. Med. Biol. 59, 7457-7477 (2014). 10.1088/0031-9155/59/23/7457
19. R. K. Samala, H.-P. Chan, Y. Lu, L. M. Hadjiiski, J. Wei, and M. A. Helvie, "Computer-aided detection system for clustered microcalcifications in digital breast tomosynthesis using joint information from volumetric and planar projection images," Phys. Med. Biol. 60, 8457-8479 (2015). 10.1088/0031-9155/60/21/8457
20. S. C. Lo, S. L. Lou, J. S. Lin, M. T. Freedman, and S. K. Mun, "Artificial convolution neural network techniques and applications to lung nodule detection," IEEE Trans. Med. Imaging 14, 711-718 (1995). 10.1109/42.476112
21. S. C. B. Lo, H.-P. Chan, J. S. Lin, H. Li, M. Freedman, and S. K. Mun, "Artificial convolution neural network for medical image pattern recognition," Neural Networks 8, 1201-1214 (1995). 10.1016/0893-6080(95)00061-5
22. R. K. Samala, H.-P. Chan, L. Hadjiiski, and M. Helvie, "Analysis of computer-aided detection techniques and signal characteristics for clustered microcalcifications on digital mammography and digital breast tomosynthesis," Phys. Med. Biol. 61, 7092-7112 (2016). 10.1088/0031-9155/61/19/7092
23. T. Kooi, A. Gubern-Merida, J.-J. Mordang, R. Mann, R. Pijnappel, K. Schuur, A. den Heeten, and N. Karssemeijer, "A comparison between a deep convolutional neural network and radiologists for classifying regions of interest in mammography," in Proceedings of the 13th International Workshop on Digital Mammography (Springer International Publishing, Switzerland, 2016), pp. 51-56.
24. K. H. Cha, L. Hadjiiski, R. K. Samala, H.-P. Chan, E. M. Caoili, and R. H. Cohan, "Urinary bladder segmentation in CT urography using deep-learning convolutional neural network and level sets," Med. Phys. 43, 1882-1896 (2016). 10.1118/1.4944498
25. M. Gao, U. Bagci, L. Lu, A. Wu, M. Buty, H.-C. Shin, H. Roth, G. Z. Papadakis, A. Depeursinge, and R. M. Summers, "Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks," Comput. Methods Biomech. Biomed. Eng.: Imaging Visualization 1-6 (2016). 10.1080/21681163.2015.1124249
26. F. Ciompi, B. de Hoop, S. J. van Riel, K. Chung, E. T. Scholten, M. Oudkerk, P. A. de Jong, M. Prokop, and B. van Ginneken, "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. 26, 195-202 (2015). 10.1016/j.media.2015.08.001
27. M. L. Zuley, A. I. Bandos, G. S. Abrams, C. Cohen, C. M. Hakim, J. H. Sumkin, J. Drescher, H. E. Rockette, and D. Gur, "Time to diagnosis and performance levels during repeat interpretations of digital breast tomosynthesis: Preliminary observations," Acad. Radiol. 17, 450-455 (2010). 10.1016/j.acra.2009.11.011
28. S. Astley et al., "A comparison of image interpretation times in full field digital mammography and digital breast tomosynthesis," Proc. SPIE 8673, 86730S-1-86730S-8 (2013). 10.1117/12.2006039
29. D. Bernardi, S. Ciatto, M. Pellegrini, V. Anesi, S. Burlon, E. Cauli, M. Depaoli, L. Larentis, V. Malesani, and L. Targa, "Application of breast tomosynthesis in screening: Incremental effect on mammography acquisition and reading time," Br. J. Radiol. 85, e1174-e1178 (2014). 10.1259/bjr/19385909
30. M. G. Wallis, E. Moa, F. Zanca, K. Leifland, and M. Danielsson, "Two-view and single-view tomosynthesis versus full-field digital mammography: High-resolution x-ray imaging observer study," Radiology 262, 788-796 (2012). 10.1148/radiol.11103514
31. H.-P. Chan, J. Wei, B. Sahiner, E. A. Rafferty, T. Wu, M. A. Roubidoux, R. H. Moore, D. B. Kopans, L. M. Hadjiiski, and M. A. Helvie, "Computer-aided detection system for breast masses on digital tomosynthesis mammograms-preliminary experience," Radiology 237, 1075-1080 (2005). 10.1148/radiol.2373041657
32. H.-P. Chan, J. Wei, Y. H. Zhang, M. A. Helvie, R. H. Moore, B. Sahiner, L. Hadjiiski, and D. B. Kopans, "Computer-aided detection of masses in digital tomosynthesis mammography: Comparison of three approaches," Med. Phys. 35, 4087-4095 (2008). 10.1118/1.2968098
33. J. Wei, H.-P. Chan, B. Sahiner, L. M. Hadjiiski, M. A. Helvie, C. Zhou, and Y. Lu, "Computer-aided detection of breast masses in digital breast tomosynthesis (DBT): Improvement of false positive reduction by optimization of object segmentation," Proc. SPIE 7963, 796311-1-796311-6 (2011). 10.1117/12.878214
34. M. Heath, K. Bowyer, D. Kopans, R. Moore, and P. Kegelmeyer, "The digital database for screening mammography," in Digital Mammography; IWDM 2000, edited by M. J. Yaffe (Medical Physics Publishing, Toronto, Canada, 2001).
35. H.-P. Chan, Y. T. Wu, B. Sahiner, J. Wei, M. A. Helvie, Y. Zhang, R. H. Moore, D. B. Kopans, L. Hadjiiski, and T. Way, "Characterization of masses in digital breast tomosynthesis: Comparison of machine learning in projection views and reconstructed slices," Med. Phys. 37, 3576-3586 (2010). 10.1118/1.3432570
36. Y. Zhang, H.-P. Chan, B. Sahiner, J. Wei, M. M. Goodsitt, L. M. Hadjiiski, J. Ge, and C. Zhou, "A comparative study of limited-angle cone-beam reconstruction methods for breast tomosynthesis," Med. Phys. 33, 3781-3795 (2006). 10.1118/1.2237543
37. J. Wei et al., "Computer aided detection systems for breast masses: Comparison of performances on full-field digital mammograms and digitized screen-film mammograms," Acad. Radiol. 6, 659-669 (2007). 10.1016/j.acra.2007.02.017
38. C. Zhou, H.-P. Chan, C. Paramagul, M. A. Roubidoux, B. Sahiner, L. M. Hadjiiski, and N. Petrick, "Computerized nipple identification for multiple image analysis in computer-aided diagnosis," Med. Phys. 31, 2871-2882 (2004). 10.1118/1.1800713
39. Y.-T. Wu, C. Zhou, L. M. Hadjiiski, J. Shi, J. Wei, C. Paramagul, B. Sahiner, and H.-P. Chan, "A dynamic multiple thresholding method for automated breast boundary detection in digitized mammograms," Proc. SPIE 6512, 65122U1-65122U8 (2007). 10.1117/12.710198
40. R. K. Samala, J. Wei, H.-P. Chan, L. M. Hadjiiski, K. Cha, and M. A. Helvie, "First and second-order features for detection of masses in digital breast tomosynthesis," Proc. SPIE 9785, 978523-1-978523-7 (2016). 10.1117/12.2216327
41. B. Sahiner, H.-P. Chan, N. Petrick, M. A. Helvie, and M. M. Goodsitt, "Computerized characterization of masses on mammograms: The rubber band straightening transform and texture analysis," Med. Phys. 25, 516-526 (1998). 10.1118/1.598228
42. T. Way, B. Sahiner, L. Hadjiiski, and H.-P. Chan, "Effect of finite sample size on feature selection and classification: A simulation study," Med. Phys. 37, 907-920 (2010). 10.1118/1.3284974
43. H.-P. Chan, B. Sahiner, K. L. Lam, N. Petrick, M. A. Helvie, M. M. Goodsitt, and D. D. Adler, "Computerized analysis of mammographic microcalcifications in morphological and texture feature space," Med. Phys. 25, 2007-2019 (1998). 10.1118/1.598389
44. M. A. Ranzato, F. J. Huang, Y.-L. Boureau, and Y. Lecun, "Unsupervised learning of invariant feature hierarchies with applications to object recognition," in IEEE Conference on Computer Vision and Pattern Recognition, 2007 (IEEE, 2007), pp. 1-8. 10.1109/CVPR.2007.383157
45. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," Adv. Neural Inf. Proc. Syst. 1097-1105 (2012).
46. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, "Imagenet: A large-scale hierarchical image database," in IEEE Conference on Computer Vision and Pattern Recognition, 2009 (IEEE, 2009), pp. 248-255. 10.1109/CVPR.2009.5206848
47. K. H. Cha, L. Hadjiiski, H.-P. Chan, R. K. Samala, R. H. Cohan, and E. M. Caoli, "Deep-learning-based bladder segmentation in CT urography," in RSNA Program Book, SSG16-02, 2015.
48. K. H. Cha, L. M. Hadjiiski, R. K. Samala, H.-P. Chan, R. H. Cohan, and E. M. Caoili, "Comparison of bladder segmentation using deep-learning convolutional neural network with and without level sets," Proc. SPIE 9785, 978512-1-978512-7 (2016). 10.1117/12.2216852
49. K. H. Cha, L. Hadjiiski, H.-P. Chan, R. K. Samala, R. H. Cohan, E. M. Caoili, A. Weizer, and A. Alva, "Deep-learning bladder cancer treatment response assessment in CT urography," in RSNA Program Book, SSQ18-01, 2016.
50. K. H. Cha, L. Hadjiiski, R. K. Samala, H.-P. Chan, R. H. Cohan, E. M. Caoili, C. Paramagul, A. Alva, and A. Weizer, "Bladder cancer segmentation in CT for treatment response assessment: Application of deep-learning convolution neural network-A pilot study," Tomography (2016) (accepted).
51. K. H. Cha, L. M. Hadjiiski, H.-P. Chan, E. M. Caoili, R. H. Cohan, A. Weizer, and C. Zhou, "Computer-aided detection of bladder mass within non-contrast-enhanced region of CT Urography (CTU)," Proc. SPIE 9785, 97853W-1-97853W-6 (2016). 10.1117/12.2216289
52. R. K. Samala, H.-P. Chan, L. M. Hadjiiski, K. Cha, and M. A. Helvie, "Deep-learning convolution neural network for computer-aided detection of microcalcifications in digital breast tomosynthesis," Proc. SPIE 9785, 97850Y-1-97850Y-7 (2016). 10.1117/12.2217092
53. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: A simple way to prevent neural networks from overfitting," J. Mach. Learn. Res. 15, 1929-1958 (2014).
54. A. E. Burgess, "On the noise variance of a digital mammography system," Med. Phys. 31, 1987-1995 (2004). 10.1118/1.1758791
55. H.-P. Chan, D. Wei, M. A. Helvie, B. Sahiner, D. D. Adler, M. M. Goodsitt, and N. Petrick, "Computer-aided classification of mammographic masses and normal tissue: Linear discriminant analysis in texture feature space," Phys. Med. Biol. 40, 857-876 (1995). 10.1088/0031-9155/40/5/010
56. F. W. Samuelson, N. Petrick, and S. Paquerault, "Advantages and examples of resampling for CAD evaluation," in 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2007 (IEEE, 2007), pp. 492-495.
57. F. W. Samuelson and N. Petrick, "Comparing image detection algorithms using resampling," in 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006 (IEEE, 2006), pp. 1312-1315.
58. G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov, "Improving neural networks by preventing co-adaptation of feature detectors," preprint arXiv:1207.0580 (2012).
59. R. K. Samala, H.-P. Chan, L. Hadjiyski, J. Wei, K. Cha, and M. Helvie, "Comparison of mass detection for digital breast tomosynthesis (DBT) with and without transfer learning of deep-learning convolution neural network (DLCNN) from digitized screen-film mammography (SFM) and digital mammography (DM)," in RSNA Program Book, PH256-SD-WEB5, 2016.
60. S. V. Fotin, Y. Yin, H. Haldankar, J. W. Hoffmeister, and S. Periaswamy, "Detection of soft tissue densities from digital breast tomosynthesis: Comparison of conventional and deep learning approaches," Proc. SPIE 9785, 97850X-97850X-6 (2016). 10.1117/12.2217045
61. L. Morra, D. Sacchetto, M. Durando, S. Agliozzo, L. A. Carbonaro, S. Delsanto, B. Pesce, D. Persano, G. Mariscotti, and V. Marra, "Breast cancer: Computer-aided detection with digital breast tomosynthesis," Radiology 277, 56-63 (2015). 10.1148/radiol.2015141959
62. G. van Schie, M. G. Wallis, K. Leifland, M. Danielsson, and N. Karssemeijer, "Mass detection in reconstructed digital breast tomosynthesis volumes with a computer-aided detection system trained on 2D mammograms," Med. Phys. 40, 041902 (11pp.) (2013). 10.1118/1.4791643
63. H.-P. Chan, J. Wei, Y. Zhang, M. A. Helvie, L. M. Hadjiiski, and B. Sahiner, "Digital breast tomosynthesis (DBT) mammography: Effect of number of projection views on computerized mass detection using 2D and 3D approaches," in RSNA Program Book, 2008 (RSNA, Oak Brook, IL, 2008), p. 560.
64. R. K. Samala, H.-P. Chan, Y. Lu, L. Hadjiiski, J. Wei, and M. Helvie, "Digital breast tomosynthesis: Effects of projection-view distribution on computer-aided detection of microcalcification clusters," Proc. SPIE 9035, 90350Y (2014). 10.1117/12.2043513
65. H.-P. Chan, J. Wei, Y. H. Zhang, B. Sahiner, L. Hadjiiski, and M. A. Helvie, "Detection of masses in digital breast tomosynthesis mammography: Effects of the number of projection views and dose," in Proceedings of the 9th International Workshop on Digital Mammography IWDM-2008 (Springer, Berlin Heidelberg, 2008), pp. 279-285.