An unsupervised feature learning framework for basal cell carcinoma image analysis

Artificial Intelligence in Medicine

Volumn 64, Issue 2, 2015, Pages 131-145

  Arevalo, John ^a   Cruz Roa, Angel ^a   Arias, Viviana ^a   Romero, Eduardo ^a   González, Fabio A ^a  

^a UNIVERSIDAD NACIONAL DE COLOMBIA   (Colombia)

Author keywords

Basal cell carcinoma; Digital pathology; Representation learning; Unsupervised feature learning

Indexed keywords

DISCRETE COSINE TRANSFORMS; INDEPENDENT COMPONENT ANALYSIS; NEURAL NETWORKS;

BASAL CELL CARCINOMA; CLASSIFICATION PERFORMANCE; CONVOLUTIONAL NEURAL NETWORK; DIGITAL PATHOLOGIES; RECEIVER OPERATING CHARACTERISTIC CURVES; REPRESENTATION LEARNING; TOPOGRAPHIC INDEPENDENT COMPONENT ANALYSIS; UNSUPERVISED FEATURE LEARNING;

IMAGE ANALYSIS;

ARTICLE; AUTOANALYSIS; AUTOMATION; BASAL CELL CARCINOMA; CANCER DIAGNOSIS; CLINICAL CLASSIFICATION; CLINICAL EVALUATION; CLINICAL FEATURE; COMPARATIVE STUDY; COMPUTER ASSISTED DIAGNOSIS; CONCEPTUAL FRAMEWORK; HISTOPATHOLOGY; HUMAN; IMAGE ANALYSIS; IMAGE PROCESSING; INDEPENDENT COMPONENT ANALYSIS; LANGUAGE PROCESSING; LEARNING ALGORITHM; MACHINE LEARNING; MATHEMATICAL ANALYSIS; NERVE CELL NETWORK; PATTERN RECOGNITION; PRIORITY JOURNAL; RADIOLOGICAL PARAMETERS; RECEIVER OPERATING CHARACTERISTIC; RECONSTRUCT INDEPENDENT COMPONENT ANALYSIS; TOPOGRAPHIC INDEPENDENT COMPONENT ANALYSIS; UNSUPERVISED FEATURE LEARNING; VISUAL CORTEX; VISUAL SYSTEM; AREA UNDER THE CURVE; BIOPSY; CLASSIFICATION; DECISION SUPPORT SYSTEM; DISCRIMINANT ANALYSIS; EVALUATION STUDY; LABORATORY AUTOMATION; PATHOLOGY; PREDICTIVE VALUE; PROCEDURES; REPRODUCIBILITY; SKIN TUMOR; STAINING; UNSUPERVISED MACHINE LEARNING;

AREA UNDER CURVE; AUTOMATION, LABORATORY; BIOPSY; CARCINOMA, BASAL CELL; DECISION SUPPORT SYSTEMS, CLINICAL; DECISION SUPPORT TECHNIQUES; DISCRIMINANT ANALYSIS; HUMANS; IMAGE INTERPRETATION, COMPUTER-ASSISTED; PATHOLOGY, CLINICAL; PREDICTIVE VALUE OF TESTS; REPRODUCIBILITY OF RESULTS; ROC CURVE; SKIN NEOPLASMS; STAINING AND LABELING; UNSUPERVISED MACHINE LEARNING;

EID: 84930576933     PISSN: 09333657     EISSN: 18732860     Source Type: Journal    
DOI: 10.1016/j.artmed.2015.04.004     Document Type: Article

References (72)

1. Madabhushi A. Digital pathology image analysis: opportunities and challenges. Imaging Med 2009, 1(1):7-10. 10.2217/iim.09.9.
2. He L., Long R., Antani S., Thoma G. Histology image analysis for carcinoma detection and grading. Comput Methods Programs Biomed 2012, 107(3):538-556. 10.1016/j.cmpb.2011.12.007.
3. Gurcan M., Boucheron L., Can A., Madabhushi A., Rajpoot N., Yener B. Histopathological image analysis: a review. IEEE Rev Biomed Eng 2009, 2:147-171.
4. Hinton G., Osindero S., Teh Y.-W. A fast learning algorithm for deep belief nets. Neural Comput 2006, 18(7):1527-1554.
5. Bengio Y., Courville A., Vincent P. Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 2013, 35(8):1798-1828. 10.1109/TPAMI.2013.50.
6. McLendon R., Friedman A., Bigner D., Van Meir E., Brat D., Mastrogianakis G., et al. Comprehensive genomic characterization defines human glioblastoma genes and core pathways. Nature 2008, 455(7216):1061-1068.
7. Marinelli R., Montgomery K., Liu C., Shah N., Prapong W., Nitzberg M., et al. The Stanford tissue microarray database. Nucleic Acids Res 2008, 36(Suppl. 1):D871-D877.
8. Fuchs T., Buhmann J. Computational pathology: challenges and promises for tissue analysis. Comput Med Imaging Graph 2011, 35(7):515-530.
9. Boucheron L., Object- Spatial-level quantitative analysis of multispectral histopathology images for detection and characterization of cancer 2008, [Ph.D. thesis], University of California, Santa Barbara, March.
10. Albert R., Schindewolf T., Baumann I., Harms H. Three-dimensional image processing for morphometric analysis of epithelium sections. Cytometry 1992, 13(7):759-765. 10.1002/cyto.990130712.
11. Bilgin C., Demir C., Nagi C., Yener B. Cell-graph mining for breast tissue modeling and classification. 29th annual international conference of the IEEE engineering in medicine and biology society, 2007. EMBS 2007 2007, 5311-5314. Institute of Electrical & Electronics Engineers (IEEE), Lyon, France. 10.1109/IEMBS.2007.4353540. M. Akay, G. Delhomme, J. Rousseau (Eds.).
12. Doyle S., Hwang M., Shah K., Madabhushi A., Feldman M., Tomaszeweski J. Automated grading of prostate cancer using architectural and textural image features. 4th IEEE international symposium on biomedical imaging: from nano to macro, 2007. ISBI 2007 2007, 1284-1287. Institute of Electrical & Electronics Engineers (IEEE), Washington, USA. 10.1109/ISBI.2007.357094. J. Fessler, M. Wernick (Eds.).
13. Doyle S., Madabhushi A., Feldman M., Tomaszeweski J. A boosting cascade for automated detection of prostate cancer from digitized histology. Proceedings of the 9th international conference on medical image computing and computer-assisted intervention - volume Part II, MICCAI'06 2006, 504-511. Springer-Verlag, Berlin, Heidelberg. 10.1007/11866763_62. R. Larsen, M. Nielsen, J. Sporring (Eds.).
14. Sertel O., Kong J., Shimada H., Catalyurek U., Saltz J., Gurcan M. Computer-aided prognosis of neuroblastoma on whole-slide images: classification of stromal development. Pattern Recognit 2009, 42(6):1093-1103. 10.1016/j.patcog.2008.08.027.
15. Basavanhally A., Ganesan S., Feldman M., Shih N., Mies C., Tomaszeweski J., et al. Multi-field-of-view framework for distinguishing tumor grade in ER+ breast cancer from entire histopathology slides. IEEE Trans Biomed Eng 2013, 60(8):2089-2099. 10.1109/TBME.2013.2245129.
16. Martínez A., Kak A. PCA versus LDA. IEEE Trans Pattern Anal Mach Intell 2001, 23(2):228-233. 10.1109/34.908974.
17. Jolliffe I. Principal component analysis 2002, Springer. 2nd ed., 10.1002/0470013192.bsa501.
18. Rajpoot N., Arif M., Bhalerao A. Unsupervised learning of shape manifolds. Procedings of the British Machine Vision Conference 2007, British Machine Vision Association 2007, University of Warwick, UK. 10.5244/c.21.90. N. Rajpoot, A. Bhalerao (Eds.).
19. Hyvärinen A., Oja E. Independent component analysis: algorithms and applications. Neural Netw 2000, 13(4):411-430.
20. Cristianini N., Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods 2000, Cambridge University Press.
21. Bengio Y., Lamblin P., Popovici D., Larochelle H. Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst 2007, 19:153.
22. Seide F., Li G., Yu D. Conversational speech transcription using context-dependent deep neural networks. Interspeech 2011, International Speech Communication Association 2011, R. Pieraccini, A. Colombo (Eds.).
23. Le Q., Ranzato M., Monga R., Devin M., Chen K., Corrado G., et al. Building high-level features using large scale unsupervised learning. 2013 IEEE international conference on acoustics, speech and signal processing (ICASSP) 2013, 8595-8598. Institute of Electrical & Electronics Engineers (IEEE), Vancouver, Canada. 10.1109/ICASSP.2013.6639343. M. Adams, V. Zhao (Eds.).
24. Krizhevsky A., Sutskever I., Hinton G.E. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 2012, 1097-1105. Curran Associates, Inc. F. Pereira, C. Burges, L. Bottou, K. Weinberger (Eds.).
25. Malon C., Miller M., Burger H.C., Cosatto E., Graf H.P Identifying histological elements with convolutional neural networks. Proceedings of the 5th international conference on soft computing as transdisciplinary science and technology, CSTST '08 2008, 450-456. ACM, Cergy-Pontoise, France. 10.1145/1456223.1456316. Y. Badr, A. Abraham, Y. Ohsawa (Eds.).
26. Pang B., Zhang Y., Chen Q., Gao Z., Peng Q., You X. Cell nucleus segmentation in color histopathological imagery using convolutional networks. Chinese conference on pattern recognition (CCPR), IEEE 2010, 1-5. Institute of Electrical & Electronics Engineers (IEEE), Chongqing, China. 10.1109/CCPR.2010.5659313. Y. Tang, C.Y. Suen, H. He (Eds.).
27. Montavon G. A machine learning approach to classification of low resolution histological samples. École Polytechnique Fédérale de Lausanne 2009, [Master's thesis], EPFL, Switzerland.
28. Le Q., Han J., Gray J., Spellman P., Borowsky A., Parvin B. Learning invariant features of tumor signatures. 9th IEEE international symposium on biomedical imaging 2012, 10.1109/ISBI.2012.6235544.
29. Le Q., Zou W., Yeung S., Ng A. Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. 2011 IEEE conference on computer vision and pattern recognition (CVPR) 2011, 3361-3368. Institute of Electrical & Electronics Engineers (IEEE), Colorado Springs, USA. 10.1109/CVPR.2011.5995496. N. Pinto, T. Boult, T. Kanade, S. Peleg (Eds.).
30. Cruz-Roa A., Basavanhally A., González F., Gilmore H., Feldman M., Ganesan S., et al. Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks. Medical imaging: digital pathology 2014, SPIE, San Diego, CA, USA. 10.1117/12.2043872. M.N. Gurcan, A. Madabhushi (Eds.).
31. Malon C., Cosatto E. Classification of mitotic figures with convolutional neural networks and seeded blob features. J Pathol Inform 2013, 4(1):9.
32. Cireşan D., Giusti A., Gambardella L., Schmidhuber J. Mitosis detection in breast cancer histology images with deep neural networks. Medical image computing and computer-assisted intervention - MICCAI, vol. 8150 of lecture notes in computer science 2013, 411-418. Springer, Berlin, Heidelberg/Nagoya, Japan. 10.1007/978-3-642-40763-5_51. K. Mori, I. Sakuma, Y. Sato, C. Barillot, N. Navab (Eds.).
33. Wang H., Cruz-Roa A., Basavanhally A., Gilmore H., Shih N., Feldman M., et al. Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection. Medical imaging: digital pathology 2014, vol. 9041. SPIE, San Diego, CA, USA. 10.1117/12.2043902. M.N. Gurcan, A. Madabhushi (Eds.).
34. Wang H., Cruz-Roa A., Basavanhally A., Gilmore H., Shih N., Feldman M., et al. Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features. J Med Imaging 2014, 1(3):034003. 10.1117/1.jmi.1.3.034003.
35. Roux L., Racoceanu D., Loménie N., Kulikova M., Irshad H., Klossa J., et al. Mitosis detection in breast cancer histological images: an ICPR 2012 contest. J Pathol Inform 2013, 4:8. 10.4103/2153-3539.112693.
36. Fletcher C. Diagnostic histopathology of tumors 2007, Churchill Livingstone. 3rd ed.
37. Miller S., Alam M., Andersen J., Berg D., Bichakjian C., Bowen G., et al. Basal cell and squamous cell skin cancers. J Natl Compr Cancer Netw 2010, 8(8):836-864.
38. Wong C., Strange R., Lear J. Basal cell carcinoma. Br Med J (Clin Res Ed) 2003, 327(7418):794-798. 10.1136/bmj.327.7418.794.
39. Caicedo J., González F., Romero E. A semantic content-based retrieval method for histopathology images. Information retrieval technology, vol. 4993 of lecture notes in computer science 2008, 51-60. Springer, Berlin, Heidelberg/Harbin, China. 10.1007/978-3-540-68636-1_6. H. Li, T. Liu, W.-Y. Ma, T. Sakai, K.-F. Wong, G. Zhou (Eds.).
40. Caicedo J., Cruz-Roa A., González F. Histopathology image classification using bag of features and kernel functions. Artificial intelligence in medicine, vol. 5651 of lecture notes in computer science 2009, 126-135. Springer, Berlin, Heidelberg/Verona, Italy. 10.1007/978-3-642-02976-9_17. C. Combi, Y. Shahar, A. Abu-Hanna (Eds.).
41. Cruz-Roa A., Caicedo J., González F. Visual pattern mining in histology image collections using bag of features. Artif Intell Med 2011, 52(2):91-106. 10.1016/j.artmed.2011.04.010.
42. Díaz G., Romero E. Histopathological image classification using stain component features on a pLSA model. Progress in pattern recognition, image analysis, computer vision, and applications, vol. 6419 of lecture notes in computer science 2010, 55-62. Springer, Berlin, Heidelberg/Sao Paulo, Brazil. 10.1007/978-3-642-16687-7_12. I. Bloch, R. Cesar (Eds.).
43. Cruz-Roa A., Díaz G., González F. A framework for semantic analysis of histopathological images using nonnegative matrix factorization. 6th Colombian computing congress (CCC) 2011, 1-7. Institute of Electrical & Electronics Engineers (IEEE), Manizales, Colombia. 10.1109/COLOMCC.2011.5936285. L.E. Castillo, N.D. Duque (Eds.).
44. Cruz-Roa A., Díaz G., Romero E., González F.A. Automatic annotation of histopathological images using a latent topic model based on non-negative matrix factorization. J Pathol Inform 2011, 2(2). 10.4103/2153-3539.92031.
45. Gutiérrez R., Gómez F., Roa-Peña L., Romero E. A supervised visual model for finding regions of interest in basal cell carcinoma images. Diagn Pathol 2011, 6:26. 10.1186/1746-1596-6-26.
46. Díaz G., Romero E. Micro-structural tissue analysis for automatic histopathological image annotation. Microsc Res Tech 2011, 75(3):343-358. 10.1002/jemt.21063.
47. Cruz-Roa A., Arevalo J., Madabhushi A., González F. A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection. Medical image computing and computer-assisted intervention - MICCAI, vol. 8150 of lecture notes in computer science 2013, 403-410. Springer, Berlin, Heidelberg/Nagoya, Japan. 10.1007/978-3-642-40763-5_50. K. Mori, I. Sakuma, Y. Sato, C. Barillot, N. Navab (Eds.).
48. Arevalo J., Cruz-Roa A., González F. Hybrid image representation learning model with invariant features for basal cell carcinoma detection. IX international seminar on medical information processing and analysis 2013, SPIE, Mexico City, Mexico. 10.1117/12.2035530. J. Brieva, B. Escalante-Ramírez (Eds.).
49. Hyvärinen A., Hurri J., Hoyer P. Natural image statistics, vol. 39 2009, Springer.
50. Le Q., Karpenko A., Ngiam J., Ng A. ICA with reconstruction cost for efficient overcomplete feature learning. Advances in neural information processing systems 24 2011, 1017-1025. Curran Associates, Inc. J. Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, K. Weinberger (Eds.).
51. Liu D., Nocedal J. On the limited memory BFGS method for large scale optimization. Math Program 1989, 45(1-3):503-528. 10.1007/BF01589116.
52. Coates A., Huval B., Wang T., Wu D., Catanzaro B., Andrew N. Deep learning with cots hpc systems. Proceedings of the 30th international conference on machine learning, no. 3, JMLR workshop and conference proceedings 2013, S. Dasgupta, D. Mcallester (Eds.).
53. Field D.J. What the statistics of natural images tell us about visual coding. Human vision, visual processing, and digital display 1989, 269-276. International Society for Optics and Photonics, SPIE, Los Angeles, USA. 10.1117/12.952724. B.E. Rogowitz (Ed.).
54. Fei-Fei L., Perona P A bayesian hierarchical model for learning natural scene categories. IEEE computer society conference on computer vision and pattern recognition 2005, vol. 2:524-531. Institute of Electrical & Electronics Engineers (IEEE), San Diego, CA, USA. 10.1109/CVPR.2005.16. C. Schmid, S. Soatto, C. Tomas (Eds.).
55. LeCun Y., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998, 86(11):2278-2324. 10.1109/5.726791.
56. Duan K., Keerthi S., Chu W., Shevade S., Poo A.N. Multi-category classification by soft-max combination of binary classifiers. Multiple classifier systems, vol. 2709 of lecture notes in computer science 2003, 125-134. Springer, Berlin, Heidelberg/Guildford, UK. 10.1007/3-540-44938-8_13. T. Windeatt, F. Roli (Eds.).
57. Erhan D., Bengio Y., Courville A., Vincent P. Visualizing higher-layer features of a deep network. Tech. rep. 2009, University of Montreal.
58. Haralick R.M., Shanmugam K., Dinstein I.H. Textural features for image classification. IEEE Trans Syst Man Cybern 1973, 3(6):610-621. 10.1109/TSMC.1973.4309314.
59. Rennie J.D.M. Regularized logistic regression is strictly convex. Tech. rep. 2005, MIT.
60. Coates A., Lee H., Ng A. An analysis of single-layer network in unsupervised feature learning. Proceedings of the fourteenth international conference on artificial intelligence and statistics 2010, 215-223. JMLR W&CP, Ft. Lauderdale, FL, USA. G. Gordon, D. Dunson, M. Dudík (Eds.).
61. LeCun Y. Learning invariant feature hierarchies. Computer vision - ECCV. Workshops and demonstrations, vol. 7583 of lecture notes in computer science 2012, 496-505. Springer, Berlin, Heidelberg/Florence, Italy. 10.1007/978-3-642-33863-2_51. A. Fusiello, V. Murino, R. Cucchiara (Eds.).
62. Bell A., Sejnowski T. The "independent components" of natural scenes are edge filters. Vis Res 1997, 37(23):3327.
63. Hyvärinen A., Hoyer P.O., Inki M. Topographic independent component analysis. Neural Comput 2001, 13(7):1527-1558. 10.1162/089976601750264992.
64. Cruz-Roa A., González F., Galaro J., Judkins A., Ellison D., Baccon J., et al. A visual latent semantic approach for automatic analysis and interpretation of anaplastic medulloblastoma virtual slides. Medical image computing and computer-assisted intervention - MICCAI, vol. 7510 of lecture notes in computer science 2012, 157-164. Springer, Berlin, Heidelberg/Nice, France. 10.1007/978-3-642-33415-3_20. N. Ayache, H. Delingette, P. Golland, K. Mori (Eds.).
65. Raina R., Battle A., Lee H., Packer B., Ng A. Self-taught learning: transfer learning from unlabeled data. Proceedings of the 24th international conference on machine learning, ICML '07 2007, 759-766. ACM, New York, USA. 10.1145/1273496.1273592. Z. Ghahramani (Ed.).
66. Lee H., Ekanadham C., Ng A.Y. Sparse deep belief net model for visual area v2. Advances in neural information processing systems 20 2008, 873-880. Curran Associates, Inc. J. Platt, D. Koller, Y. Singer, S. Roweis (Eds.).
67. Weinstein G., Frost P. Cell proliferation in human basal cell carcinoma. Cancer Res 1970, 30(3):724-728.
68. Jia Y., Shelhamer E., Donahue J., Karayev S., Long J., Girshick R., et al. Caffe, Convolutional architecture for fast feature embedding. Proceedings of the ACM international conference on multimedia, MM '14 2014, 675-678. ACM, New York, NY, USA. 10.1145/2647868.2654889. Y. Cai, W. Tavanapong (Eds.).
69. Goodfellow I.J., Warde-Farley D., Lamblin P., Dumoulin V., Mirza M., Pascanu R., et al. Pylearn2: a machine learning research library 2013, arXiv preprint arXiv:13084214.
70. Collobert R., Kavukcuoglu K., Farabet C. Torch7. A matlab-like environment for machine learning. BigLearn, NIPS workshop, no. EPFL-CONF-192376 2011, NIPS, Granada, Spain. J. Gonzalez, S. Singh (Eds.).
71. Wu R., Yan S., Shan Y., Dang Q., Sun G. Deep image: scaling up image recognition 2015, arXiv preprint arXiv:150102876.
72. Dean J., Corrado G., Monga R., Chen K., Devin M., Mao M., et al. Large scale distributed deep networks. Advances in neural information processing systems 25 2012, 1223-1231. Curran Associates, Inc. F. Pereira, C. Burges, L. Bottou, K. Weinberger (Eds.).