Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring

IEEE Transactions on Medical Imaging

Volumn 35, Issue 5, 2016, Pages 1322-1331

  Kallenberg, Michiel ^a,b   Petersen, Kersten ^a   Nielsen, Mads ^a,b   Ng, Andrew Y ^c   Diao, Pengfei ^a   Igel, Christian ^a   Vachon, Celine M ^d   Holland, Katharina ^e   Winkel, Rikke Rass ^f   Karssemeijer, Nico ^e   Lillholm, Martin ^a,b  

^a UNIVERSITY OF COPENHAGEN   (Denmark)

^b BiomedIQ A/S   (Denmark)

^c Stanford University   (United States)

^d MAYO CLINIC HOSPITAL   (United States)

^e RADBOUD UNIVERSITY MEDICAL CENTER   (Netherlands)

^f Mental Health Center Glostrup   (Denmark)

Author keywords

Breast cancer; deep learning; mammograms; prognosis; risk factor; segmentation; unsupervised feature learning

Indexed keywords

DISEASES; IMAGE SEGMENTATION; X RAY SCREENS;

BREAST CANCER; DEEP LEARNING; MAMMOGRAMS; PROGNOSIS; RISK FACTORS; UNSUPERVISED FEATURE LEARNING;

MAMMOGRAPHY;

ARTICLE; ASSESSMENT OF HUMANS; BREAST CANCER; BREAST DENSITY; CANCER PROGNOSIS; CLASSIFIER; CONTROLLED STUDY; LEARNING; MAMMOGRAPHIC TEXTURE SCORE; MAMMOGRAPHY SYSTEM; RISK FACTOR; ADULT; AGED; BREAST; BREAST NEOPLASMS; COMPUTER ASSISTED DIAGNOSIS; DIAGNOSTIC IMAGING; FEMALE; HUMAN; MAMMOGRAPHY; MIDDLE AGED; PHYSIOLOGY; PROCEDURES; UNSUPERVISED MACHINE LEARNING;

ADULT; AGED; BREAST; BREAST DENSITY; BREAST NEOPLASMS; FEMALE; HUMANS; IMAGE INTERPRETATION, COMPUTER-ASSISTED; MAMMOGRAPHY; MIDDLE AGED; RISK FACTORS; UNSUPERVISED MACHINE LEARNING;

EID: 84968572894     PISSN: 02780062     EISSN: 1558254X     Source Type: Journal    
DOI: 10.1109/TMI.2016.2532122     Document Type: Article

References (67)

1. A. Jemal et al., "Global cancer statistics," CA Cancer J. Clin., vol. 61, pp. 69-90, 2011.
2. J. Ferlay et al., "Cancer incidence and mortality patterns in Europe: Estimates for 40 countries in 2012," Eur. J. Cancer, vol. 49, pp. 1374-1403, 2013.
3. I. T. Gram, E. Funkhouser, and L. Tabár, "The tabár classification of mammographic parenchymal patterns," Eur. J. Radiol., vol. 24, pp. 131-136, 1997.
4. V. McCormack and I. dos Santos Silva, "Breast density and parenchymal patterns as markers of breast cancer risk: A meta-analysis," Cancer Epidemiol. Biomarkers Prev., vol. 15, pp. 1159-1169, 2006.
5. N. F. Boyd et al., "Breast tissue composition and susceptibility to breast cancer," J. Nat. Cancer Inst., vol. 102, pp. 1224-1237, 2010.
6. J. Cuzick et al., "Tamoxifen-induced reduction in mammographic density and breast cancer risk reduction: A nested case-control study," J. Nat. Cancer Inst., vol. 103, no. 9, pp. 744-752, 2011.
7. J. N. Wolfe, "Risk for breast cancer development determined by mammographic parenchymal pattern," Cancer, vol. 37, pp. 2486-2492, 1976.
8. L. Tabár, S. W. Duffy, B. Vitak, H.-H. Chen, and T. C. Prevost, "The natural history of breast carcinoma," Cancer, vol. 86, no. 3, pp. 449-462, 1999.
9. J. W. Byng, N. F. Boyd, E. Fishell, R. A. Jong, and M. J. Yaffe, "The quantitative analysis of mammographic densities," Phys. Med. Biol., vol. 39, pp. 1629-1638, 1994.
10. M. G. Kallenberg, M. Lokate, C. H. van Gils, and N. Karssemeijer, "Automatic breast density segmentation: An integration of different approaches," Phys. Med. Biol., vol. 56, pp. 2715-2729, 2011.
11. S. Petroudi, T. Kadir, and M. Brady, "Automatic classification of mammographic parenchymal patterns: A statistical approach," in Proc. 25th Annu. Int. Conf. IEEE EMBS, 2003, vol. 1, pp. 798-801.
12. J. J. Heine et al., "An automated approach for estimation of breast density," Cancer Epidemiol. Biomarkers Prev., vol. 17, pp. 3090-3097, 2008.
13. A. Oliver, X. Llado, R. Marti, J. Freixenet, and R. Zwiggelaar, "Classifying mammograms using texture information," Med. Image Understand. Anal., pp. 223-227, 2007.
14. J. Li et al., "High-throughput mammographic-density measurement: A tool for risk prediction of breast cancer," Breast Cancer Res., vol. 14, p. R114, 2012.
15. B. M. Keller et al., "Estimation of breast percent density in raw and processed full field digital mammography images via adaptive fuzzy c-means clustering and support vector machine segmentation," Med. Phys., vol. 39, no. 8, pp. 4903-4917, 2012.
16. H. Li, M. L. Giger, O. I. Olopade, and M. R. Chinander, "Power spectral analysis of mammographic parenchymal patterns for breast cancer risk assessment," J. Digit. Imag., vol. 21, pp. 145-152, 2008.
17. A. Manduca et al., "Texture features from mammographic images and risk of breast cancer," Cancer Epidemiol. Biomarkers Prev., vol. 18, pp. 837-845, 2009.
18. L. Häberle et al., "Characterizing mammographic images by using generic texture features," Breast Cancer Res., vol. 14, no. 2, p. R59, 2012.
19. M. Nielsen et al., "A novel and automatic mammographic texture resemblance marker is an independent risk factor for breast cancer," Cancer Epidemiol., vol. 35, pp. 381-387, 2011.
20. J. J. Heine et al., "A novel automated mammographic density measure and breast cancer risk," J. Nat. Cancer Inst., vol. 104, pp. 1028-1037, 2012.
21. M. Nielsen et al., "Mammographic texture resemblance generalizes as an independent risk factor for breast cancer," Breast Cancer Res., vol. 16, p. R37, 2014.
22. Y. Zheng et al., "Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment," Med. Phys., vol. 42, no. 7, pp. 4149-4160, 2015.
23. M. Ranzato, C. S. Poultney, S. Chopra, and Y. LeCun, "Efficient learning of sparse representations with an energy-based model," Adv. Neural Inf. Process. Syst., pp. 1137-1144, 2007.
24. M. Ranzato, F. J. Huang, Y.-L. Boureau, and Y. LeCun, "Unsupervised learning of invariant feature hierarchies with applications to object recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2007, pp. 1-8.
25. K. Petersen, K. Chernoff, M. Nielsen, and A. Ng, "Breast density scoring with multiscale denoising autoencoders," in Proc. Sparsity Tech. Med. Imag. Conjunction MICCAI 2012, 2012.
26. K. Petersen, M. Nielsen, P. Diao, N. Karssemeijer, and M. Lillholm, "Breast tissue segmentation and mammographic risk scoring using deep learning," in Proc. 12th Int. Workshop, Breast Imag., H. Fujita, T. Hara, and C. Muramatsu, Eds., 2014, vol. 8539, LNCS, pp. 88-94.
27. W. He et al., "A review on automatic mammographic density and parenchymal segmentation," Int. J. Breast Cancer, 2015.
28. R. Sivaramakrishna, N. A. Obuchowski, W. A. Chilcote, and K. A. Powell, "Automatic segmentation of mammographic density," Acad. Radiol., vol. 8, no. 3, pp. 250-256, 2001.
29. A. Torrent et al., "Breast density segmentation: A comparison of clustering and region based techniques," in Proc. 9th Int. Workshop Digital Mammogr., 2008, pp. 9-16.
30. R. J. Ferrari, R. M. Rangayyan, R. A. Borges, and A. F. Frère, "Segmentation of the fibro-glandular disc in mammograms using Gaussian mixture modelling," Med. Biol. Eng. Comput., vol. 42, pp. 378-387, 2004.
31. R. Highnam and M. Brady, Mammographic Image Analysis. New York: Kluwer, 1999.
32. S. van Engeland, P. R. Snoeren, H. Huisman, C. Boetes, and N. Karssemeijer, "Volumetric breast density estimation from full-field digital mammograms," IEEE Trans. Med. Imag., vol. 25, no. 3, pp. 273-282, Mar. 2006.
33. J. Byng, N. Boyd, E. Fishell, R. Jong, and M. Yaffe, "Automated analysis of mammographic densities," Phys. Med. Biol., vol. 41, no. 5, p. 909, 1996.
34. Z. Huo et al., "Computerized analysis of mammographic parenchymal patterns for breast cancer risk assessment: Feature selection," Med. Phys., vol. 27, pp. 4-12, 2000.
35. Y. Bengio, A. Courville, and P. Vincent, "Representation learning: A review and new perspectives," IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 8, pp. 1798-1828, Aug. 2013.
36. J. Schmidhuber, "Deep learning in neural networks: An overview," Neural Netw., vol. 61, pp. 85-117, 2015.
37. Y. Bengio, "Learning deep architectures for AI," Found. Trends Mach. Learn., vol. 2, no. 1, pp. 1-127, 2009.
38. Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proc. IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
39. C. Farabet, C. Couprie, L. Najman, and Y. LeCun, "Learning hierarchical features for scene labeling," IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 8, pp. 1915-1929, Aug. 2013.
40. F. Ning et al., "Toward automatic phenotyping of developing embryos from videos," IEEE Trans. Image Process., vol. 14, no. 9, pp. 1360-1371, Sep. 2005.
41. D. Ciresan, A. Giusti, L. M. Gambardella, and J. Schmidhuber, "Deep neural networks segment neuronal membranes in electron microscopy images," Adv. Neural Inf. Process. Syst., pp. 2843-2851, 2012.
42. S. C. Turaga et al., "Convolutional networks can learn to generate affinity graphs for image segmentation," Neural Comput., vol. 22, no. 2, pp. 511-538, 2010.
43. D. Wei, B. Sahiner, H. Chan, and N. Petrick, "Detection of masses on mammograms using a convolutional neural network," Acoust., Speech Signal Process., vol. 5, pp. 3483-3486, 1995.
44. P. Fonseca et al., "Automatic breast density classification using a convolutional neural network architecture search procedure," in Proc. SPIE Med. Imag., 2015, pp. 941 428-941 428.
45. A. R. Jamieson, R. Alam, and M. L. Giger, "Exploring deep parametric embeddings for breast CADx," in Proc. SPIE Med. Imag., 2011, pp. 79 630Y-79 630Y.
46. A. R. Jamieson, K. Drukker, and M. L. Giger, "Breast image feature learning with adaptive deconvolutional networks," in Proc. SPIE Med. Imag., 2012, pp. 831 506-831 506.
47. V. Jain et al., "Supervised learning of image restoration with convolutional networks," in Proc. IEEE 11th Int. Conf. Comput. Vis., 2007, pp. 1-8.
48. G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, vol. 313, pp. 504-507, 2006.
49. G. E. Hinton, "Learning multiple layers of representation," Trends Cogn. Sci., vol. 11, no. 10, pp. 428-434, 2007.
50. P. Vincent, H. Larochelle, Y. Bengio, and P. A. Manzagol, "Extracting and composing robust features with denoising autoencoders," in Proc. Int. Conf. Mach. Learn., 2008, pp. 1096-1103.
51. J. Masci, U. Meier, D. Cireşan, and J. Schmidhuber, "Stacked convolutional auto-encoders for hierarchical feature extraction," in Artif. Neural Netw. Mach. Learn., 2011, pp. 52-59.
52. Q. Le et al., "Building high-level features using large scale unsupervised learning," in Proc. Int. Conf. Mach. Learn., 2012.
53. T. Lindeberg, Scale-Space Theory in Computer Vision. Dordrecht, The Netherlands: Kluwer, 1994.
54. L. Florack, "A spatio-frequency trade-off scale for scale-space filtering," IEEE Trans. Pattern Anal. Mach. Intell., vol. 22, no. 9, pp. 1050-1055, Sep. 2000.
55. B. A. Olshausen et al., "Emergence of simple-cell receptive field properties by learning a sparse code for natural images," Nature, vol. 381, no. 6583, pp. 607-609, 1996.
56. H. Lee, C. Ekanadham, and A. Y. Ng, "Sparse deep belief net model for visual area V2," Adv. Neural Inf. Process. Syst., pp. 873-880, 2008.
57. V. Nair and G. E. Hinton, "Rectified linear units improve restricted Boltzmann machines," in Proc. Int. Conf. Mach. Learn., 2010, pp. 807-814.
58. J. E. Olson et al., "The influence of mammogram acquisition on the mammographic density and breast cancer association in the Mayo mammography health study cohort," Breast Cancer Res., vol. 14, no. 6, p. R147, 2012.
59. Neural Networks: Tricks of the Trade, G. Montavon, G. Orr, and M. K, Eds. New York: Springer, 2012, vol. 7700.
60. L. M. J. Florack, B. M. ter Haar Romeny, M. A. Viergever, and J. J. Koenderink, "The Gaussian scale-space paradigm and the multiscale local jet," Int. J. Comput. Vis., vol. 18, pp. 61-75, 1996.
61. C. Nickson et al., "Autodensity: An automated method to measure mammographic breast density that predicts breast cancer risk and screening outcomes," Breast Cancer Res., vol. 15, no. 5, p. R80, 2013.
62. B. M. Keller, J. Chen, D. Daye, E. F. Conant, and D. Kontos, "Preliminary evaluation of the publicly available laboratory for breast radiodensity assessment (LIBRA) software tool: Comparison of fully automated area and volumetric density measures in a case-control study with digital mammography," Breast Cancer Res., vol. 17, no. 1, pp. 1-17, 2015.
63. R. Wagner, M. Thom, R. Schweiger, G. Palm, and A. Rothermel, "Learning convolutional neural networks from few samples," in Proc. Int. Joint Conf. Neural Netw., 2013, pp. 1-7.
64. S. Tan and B. Li, "Stacked convolutional auto-encoders for steganalysis of digital images," in Proc. Annu. Summit Conf. (APSIPA) Asia-Pacific Signal Inf. Process. Assoc., 2014, pp. 1-4.
65. T. L. Paine, P. Khorrami, W. Han, and T. S. Huang, An analysis of unsupervised pre-training in light of recent advances 2014 [Online]. Available: arXiv:1412.6597, to be published
66. A. Droniou and O. Sigaud, "Gated autoencoders with tied input weights," in Int. Conf. Mach. Lear., 2013, pp. 154-162.
67. A. Coates, "Demystifying unsupervised feature learning," Ph.D. dissertation, Stanford Univ., Stanford, CA, 2012.