Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent

Scientific Reports

Volumn 7, Issue , 2017, Pages

  Cruz Roa, Angel ^a,b   Gilmore, Hannah ^c   Basavanhally, Ajay ^d   Feldman, Michael ^e   Ganesan, Shridar ^f   Shih, Natalie N C ^e   Tomaszewski, John ^g   González, Fabio A ^a   Madabhushi, Anant ^h  

^a UNIVERSIDAD NACIONAL DE COLOMBIA   (Colombia)

^b UNIVERSIDAD DE LOS LLANOS   (Colombia)

^c UNIVERSITY HOSPITALS OF CLEVELAND   (United States)

^d Inspirata Inc   (United States)

^e HOSPITAL OF THE UNIVERSITY OF PENNSYLVANIA   (United States)

^f RUTGERS CANCER INSTITUTE OF NEW JERSEY   (United States)

^g UNIVERSITY AT BUFFALO   (United States)

^h CASE WESTERN RESERVE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADULT; AGED; ALGORITHM; BREAST TUMOR; COMPUTER ASSISTED DIAGNOSIS; DIAGNOSTIC IMAGING; FEMALE; HUMAN; MIDDLE AGED; PAGET NIPPLE DISEASE; PATHOLOGY; PROCEDURES; TUMOR INVASION; TUMOR VOLUME; YOUNG ADULT;

ADULT; AGED; ALGORITHMS; BREAST NEOPLASMS; CARCINOMA, DUCTAL, BREAST; DEEP LEARNING; FEMALE; HUMANS; IMAGE INTERPRETATION, COMPUTER-ASSISTED; MIDDLE AGED; NEOPLASM INVASIVENESS; TUMOR BURDEN; YOUNG ADULT;

EID: 85017623447     PISSN: None     EISSN: 20452322     Source Type: Journal    
DOI: 10.1038/srep46450     Document Type: Article

References (58)

1. Genestie, C., et al. Comparison of the prognostic value of Scarff-Bloom-Richardson and nottingham histological grades in a series of825 cases of breast cancer: Major importance of the mitotic count as a component of both grading systems. Anticancer Research 18, 571-576 (1998).
2. Elston, C. W., Ellis, I. O. Pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer:experience from a large study with long-term follow-up. Histopathology 19, 403-410 (1991).
3. Frierson, H. F., et al. Interobserver reproducibility of the Nottingham modification of the Bloom and Richardson histologic gradingscheme for infiltrating ductal carcinoma. American journal of clinical pathology 103, 195-8 (1995).
4. Gomes, D. S., Porto, S. S., Balabram, D., Gobbi, H. Inter-observer variability between general pathologists and a specialist in breastpathology in the diagnosis of lobular neoplasia, columnar cell lesions, atypical ductal hyperplasia and ductal carcinoma in situ of thebreast. Diagnostic pathology 9, 121 (2014).
5. Longacre, T. A., et al. Interobserver agreement and reproducibility in classification of invasive breast carcinoma: An NCI breastcancer family registry study. Modern pathology: An official journal of the United States and Canadian Academy of Pathology, Inc 19, 195-207 (2006).
6. Perez, A. A., Balabram, D., Salles, M. d. A., Gobbi, H. Consultation in breast surgical pathology: Interobserver diagnostic variabilityof atypical intraductal proliferative lesions. Revista brasileira de ginecologia e obstetrícia: Revista da Federacąõ Brasileira dasSociedades de Ginecologia e Obstetrícia 35, 164-70 (2013).
7. Dillon, D. A., Guidi, A. J., Schnitt, S. J. Pathology of invasive breast cancer. In Harris, J. R., Lippman, M. E., Morrow, M., Osborne, C. K. (eds) Diseases of the Breast chap. Chapter 28, 374-407 4th edition edn (Lippincott Williams & Wilkins, 2010).
8. DeSantis, C., Siegel, R., Bandi, P., Jemal, A. Breast cancer statistics, 2011. CA: A Cancer Journal for Clinicians 61, 408-418 (2011).
9. van Baardwijk, A., et al. PET-CT-based auto-contouring in non-small-cell lung cancer correlates with pathology and reducesinterobserver variability in the delineation of the primary tumor and involved nodal volumes. International Journal of RadiationOncology Biology Physics 68, 771-778 (2007).
10. Weaver, D. L., et al. Comparison of pathologist-detected and automated computer-assisted image analysis detected sentinel lymphnode micrometastases in breast cancer. Modern pathology: An official journal of the United States and Canadian Academy ofPathology, Inc 16, 1159-63 (2003).
11. Madabhushi, A. Digital pathology image analysis: Opportunities and challenges. Imaging In Medicine 1, 7-10 (2009).
12. Lewis, J. S., Ali, S., Luo, J., Thorstad, W. L., Madabhushi, A. A Quantitative Histomorphometric Classifier (QuHbIC)Oropharyngeal Squamous Cell Carcinoma. American Journal of Surgical Pathology 38, 128-137 (2014).
13. Ciresan, D., Giusti, A., Gambardella, L., Schmidhuber, J. Mitosis Detection in Breast Cancer Histology Images with Deep NeuralNetworks. In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2013, vol. 8150 of Lecture Notes in ComputerScience 411-418 (Springer Berlin Heidelberg, 2013).
14. Irshad, H. Automated mitosis detection in histopathology using morphological and multi-channel statistics features. Journal ofPathology Informatics 4, 10 (2013).
15. Ludovic, R., et al. Mitosis detection in breast cancer histological images An ICPR 2012 contest. Journal of Pathology Informatics 4, 8 (2013).
16. Veta, M., et al. Assessment of algorithms for mitosis detection in breast cancer histopathology images. Medical Image Analysis 20, 237-248 (2015).
17. Wang, H., et al. Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural networkfeatures. Journal of Medical Imaging 1, 34003 (2014).
18. Basavanhally, A., et al. Incorporating domain knowledge for tubule detection in breast histopathology using O'Callaghanneighborhoods. In SPIE Medical Imaging, vol. 7963 of Computer-Aided Diagnosis 796310. SPIE (SPIE, 2011).
19. Dalle, J. R., Leow, W. K., Racoceanu, D., Tutac, A. E., Putti, T. C. Automatic breast cancer grading of histopathological images. Annual International Conference of the IEEE Engineering in Medicine and Biology Society 3052-5 (2008).
20. Monaco, J. P., et al. Image segmentation with implicit color standardization using spatially constrained expectation maximization:detection of nuclei. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 15, 365-372 (2012).
21. Basavanhally, A., et al. Computerized image-based detection and grading of lymphocytic infiltration in HER2+ breast cancerhistopathology. IEEE transactions on bio-medical engineering 57, 642-653 (2010).
22. Basavanhally, A., et al. Multi-Field-of-View Framework for Distinguishing Tumor Grade in ER+ Breast Cancer From EntireHistopathology Slides. IEEE transactions on biomedical engineering 60, 2089-2099 (2013).
23. Basavanhally, A., et al. Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptorpositivebreast cancer histopathology: Comparison to Oncotype DX. Journal of pathology informatics 2, S1 (2011).
24. Beck, A. H., et al. Systematic analysis of breast cancer morphology uncovers stromal features associated with survival. Sciencetranslational medicine 3, 108-113 (2011).
25. Dundar, M. M., et al. Computerized classification of intraductal breast lesions using histopathological images. IEEE Transactions onBiomedical Engineering 58, 1977-1984 (2011).
26. Naik, S., et al. Automated gland and nuclei segmentation for grading of prostate and breast cancer histopathology. In 2008 5th IEEEInternational Symposium on Biomedical Imaging: From Nano to Macro 284-287 (IEEE, 2008).
27. Arevalo, J., Cruz-Roa, A., Arias, V., Romero, E., Gonzalez, F. A. An unsupervised feature learning framework for basal cellcarcinomaimage analysis. Artificial Intelligence in Medicine 64, 131-145 (2015).
28. Cruz-Roa, A., Arévalo, J., Basavanhally, A., Madabhushi, A., Gonzalez, F. A comparative evaluation of supervised and unsupervisedrepresentation learning approaches for anaplastic medulloblastoma differentiation. In Tenth International Symposium on MedicalInformation Processing and Analysis (SIPAIM 2014) (2014).
29. Cruz-Roa, A., Arevalo, J., Madabhushi, A., González, F. A Deep Learning Architecture for Image Representation, VisualInterpretability and Automated Basal-Cell Carcinoma Cancer Detection. In Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds) Medical Image Computing and Computer-Assisted Intervention-MICCAI 2013, vol. 8150 of Lecture Notes in Computer Science403-410 (Springer Berlin Heidelberg, 2013).
30. Cruz-Roa, A., et al. Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks. InProc. SPIE 9041, 904103-904115 (2014).
31. Le, Q. V., et al. Learning invariant features of tumor signatures. In Biomedical Imaging (ISBI), 2012 9th IEEE International Symposiumon 302-305 (IEEE, 2012).
32. Malon, C., Cosatto, E. Classification of mitotic figures with convolutional neural networks and seeded blob features. Journal ofPathology Informatics 4, 9 (2013).
33. Otálora, S., et al. Combining Unsupervised Feature Learning and Riesz Wavelets for Histopathology Image Representation: Applicationto Identifying Anaplastic Medulloblastoma, chap. Combining 581-588 (Springer International Publishing, Cham, 2015).
34. Donahue, J., et al. DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. In International Conference inMachine Learning (ICML) (2014).
35. Hinton, G., Srivastava, N. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprintarXiv:1207. 0580 (2012).
36. Krizhevsky, A., Sutskever, I., Hinton, G. E. ImageNet Classification with Deep Convolutional Neural Networks. In Advances inNeural Information Processing Systems 25, 1106-1114 (2012).
37. Le, Q., et al. Building high-level features using large scale unsupervised learning. In International Conference in Machine Learning (2012).
38. Bengio, Y., Courville, A., Vincent, P. Representation Learning: A Review and New Perspectives. IEEE Transactions on PatternAnalysis and Machine Intelligence 35, 1798-1828 (2013).
39. Bengio, Y. Learning Deep Architectures for AI. Foundations and Trends in Machine Learning 2, 1-127 (2009).
40. Deng, L., Yu, D. Deep Learning: Methods and Applications. Foundations and Trends in Signal Processing 7, 197-387 (2014).
41. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86, 2278-2324 (1998).
42. LeCun, Y. Convolutional networks and applications in vision. In Proceedings of 2010 IEEE International Symposium on Circuits andSystems 253-256 (2010).
43. Lacroix-Triki, M., et al. Mucinous carcinoma of the breast is genomically distinct from invasive ductal carcinomas of no special type. The Journal of Pathology 222, 282-298 (2010).
44. Kothari, S., et al. Removing Batch Effects From Histopathological Images for Enhanced Cancer Diagnosis. Biomedical and HealthInformatics, IEEE Journal of 18, 765-772 (2014).
45. Fuchs, T. J., Buhmann, J. M. Computational pathology: Challenges and promises for tissue analysis. Computerized medical imagingand graphics: The official journal of the Computerized Medical Imaging Society 35, 515-30 (2011).
46. Gurcan, M. N., et al. Histopathological Image Analysis: A Review. IEEE reviews in biomedical engineering 2, 147-171 (2009).
47. He, L., Long, R., Antani, S., Thoma, G. Histology image analysis for carcinoma detection and grading. Computer Methods andPrograms in Biomedicine 107, 538-556 (2012).
48. Veta, M., Pluim, J. P. W., van Diest, P. J., Viergever, M. A. Breast Cancer Histopathology Image Analysis: A Review. BiomedicalEngineering, IEEE Transactions on 61, 1400-1411 (2014).
49. McLendon, R., et al. Comprehensive genomic characterization defines human glioblastoma genes and core pathways. Nature 455, 1061-1068 (2008).
50. Weinstein, J. N., et al. The Cancer Genome Atlas Pan-Cancer analysis project. Nature Genetics 45, 1113-1120 (2013).
51. Cohen, J. A Coefficient of Agreement for Nominal Scales. Educational and Psychological Measurement 20, 37-46 (1960).
52. Viera, A., Garrett, J. Understanding interobserver agreement: The kappa statistic. Family Medicine 37, 360-363 (2005).
53. Dice, L. R. Measures of the amount of ecologic association between species. Ecology 26, 297-302 (1945).
54. Collobert, R., Kavukcuoglu, K., Farabet, C. Torch7: A matlab-like environment for machine learning. In BigLearn, NIPS Workshop (2011).
55. Doyle, S., Agner, S., Madabhushi, A., Feldman, M., Tomaszewski, J. Automated grading of breast cancer histopathology usingspectral clusteringwith textural and architectural image features. In 5th IEEE ISBI: From Nano to Macro 496-499 (IEEE, 2008).
56. Arévalo, J., Cruz-Roa, A., González, F. A. Histopathology image representation for automatic analysis: A state-of-the-art review. Revista Med 22, 79-91 (2014).
57. Dorai, C., Jain, A. Cosmos-a representation scheme for 3d free-form objects. IEEE Transactions on Pattern Analysis and MachineIntelligence 19, 1115-1130 (1997).
58. Doyle, S., Madabhushi, A., Feldman, M., Tomaszeweski, J. A Boosting Cascade for Automated Detection of Prostate Cancer fromDigitized Histology. In Larsen, R., Nielsen, M., Sporring, J. (eds) International Conference on Medical Image Computing andComputer-Assisted Intervention LNCS, 504-511 (Springer, Berlin, Heidelberg, 2006).