Multisource Transfer Learning with Convolutional Neural Networks for Lung Pattern Analysis

IEEE Journal of Biomedical and Health Informatics

Volumn 21, Issue 1, 2017, Pages 76-84

  Christodoulidis, Stergios ^a   Anthimopoulos, Marios ^a,b   Ebner, Lukas ^b   Christe, Andreas ^b   Mougiakakou, Stavroula ^a,b  

^a UNIVERSITY OF BERN   (Switzerland)

^b UNIVERSITY OF BERN   (Switzerland)

Author keywords

Convolutional neural networks (CNNs); interstitial lung diseases (ILDs); knowledge distillation; model compression; model ensemble; texture classification; Transfer learning

Indexed keywords

BIOLOGICAL ORGANS; COMPUTER AIDED DIAGNOSIS; COMPUTERIZED TOMOGRAPHY; CONVOLUTION; CONVOLUTIONAL NEURAL NETWORKS; DEEP NEURAL NETWORKS; DISTILLATION; LEARNING SYSTEMS; MEDICAL IMAGING; TEXTURES; TISSUE; TISSUE ENGINEERING; TRANSFER LEARNING;

CLINICAL MANIFESTATION; COMPUTER AIDED DIAGNOSIS SYSTEMS; INTERSTITIAL LUNG DISEASE; MODEL COMPRESSION; MODEL ENSEMBLES; PROPOSED ARCHITECTURES; SPECIFIC PROBLEMS; TEXTURE CLASSIFICATION;

NETWORK ARCHITECTURE;

ARCHITECTURE; ARTICLE; COMPUTER ASSISTED TOMOGRAPHY; IMAGE ANALYSIS; LUNG; MACHINE LEARNING; MULTISOURCE TRANSFER LEARNING; MULTITASK LEARNING; NERVE CELL NETWORK; TRAINING; ARTIFICIAL NEURAL NETWORK; AUTOMATED PATTERN RECOGNITION; COMPUTER ASSISTED DIAGNOSIS; DIAGNOSTIC IMAGING; HUMAN; INTERSTITIAL LUNG DISEASE; PROCEDURES; X-RAY COMPUTED TOMOGRAPHY;

HUMANS; IMAGE INTERPRETATION, COMPUTER-ASSISTED; LUNG; LUNG DISEASES, INTERSTITIAL; MACHINE LEARNING; NEURAL NETWORKS (COMPUTER); PATTERN RECOGNITION, AUTOMATED; TOMOGRAPHY, X-RAY COMPUTED;

EID: 85014941777     PISSN: 21682194     EISSN: 21682208     Source Type: Journal    
DOI: 10.1109/JBHI.2016.2636929     Document Type: Article

References (47)

1. B. SOCIETY, "The diagnosis, assessment and treatment of diffuseparenchymal lung disease in adults, " Thorax, vol. 54, no. Suppl 1, p. S1-14, 1999.
2. I. Sluimer, A. Schilham, M. Prokop, B. Van Ginneken, "Computeranalysis of computed tomography scans of the lung: A survey, " IEEETrans. Med. Imag., vol. 25, no. 4, pp. 385-405, Apr. 2006.
3. A. Krizhevsky, I. Sutskever, G. E. Hinton, "ImageNet Classificationwith Deep Convolutional Neural Networks, " in Proc. Adv. Neural Inf. Process. Syst., 2012, pp. 1-9.
4. Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, "Gradient-based learningapplied to document recognition, " Proc. IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
5. H. Greenspan, B. Van Ginneken, R. Summers, "Guest editorial deeplearning in medical imaging: Overview and future promise of an excitingnew technique, " IEEE Trans. Med. Imag., vol. 35, no. 5, pp. 1153-1159, May 2016.
6. M. Anthimopoulos, S. Christodoulidis, L. Ebner, A. Christe, S. Mougiakakou, "Lung pattern classification for interstitial lung diseasesusing a deep convolutional neural network, " IEEE Trans. Med. Imag., vol. 35, no. 5, pp. 1207-1216, May 2016.
7. G. J. Burghouts and J.-M. Geusebroek, "Material-specific adaptationof color invariant features, " Pattern Recognit. Lett., vol. 30, no. 3, pp. 306-313, 2009.
8. M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, A. Vedaldi, "Describingtextures in the wild, " in Proc. IEEE Conf. Comput. Vis. PatternRecognit., 2014, pp. 3606-3613.
9. L. Sharan, R. Rosenholtz, E. Adelson, "Material perception: Whatcan you see in a brief glance" J. Vis., vol. 9, no. 8, pp. 784-784, 2009.
10. G. Kylberg, "The kylberg texture dataset v. 1. 0, " Centre for Image Anal., Swedish Univ. Agricultural Sci. and Uppsala Univ., Uppsala, Sweden, External Rep. (Blue series) 35, Sep. 2011.
11. B. Caputo, E. Hayman, P. Mallikarjuna, "Class-specific material categorisation, "10th IEEE Int. Conf. Comput. Vis. (ICCV'05), vol. 1, Beijing, 2005, pp. 1597-1604, vol. 2, doi: 10. 1109/ICCV. 2005. 54.
12. S. Lazebnik, C. Schmid, J. Ponce, "A sparse texture representationusing local affine regions, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 8, pp. 1265-1278, Aug. 2005.
13. R. Uppaluri, E. A. Hoffman, M. Sonka, P. G. Hartley, G. W. Hunninghake, G. McLennan, "Computer recognition of regional lungdisease patterns, " Amer. J. Respiratory Critical Care Med., vol. 160, no. 2, pp. 648-654, 1999.
14. I. C. Sluimer, P. F. van Waes, M. A. Viergever, B. van Ginneken, "Computer-aided diagnosis in high resolution ct of the lungs, " Med. Phys., vol. 30, no. 12, pp. 3081-3090, 2003.
15. M. Anthimopoulos, S. Christodoulidis, A. Christe, S. Mougiakakou, "Classification of interstitial lung disease patterns using local dct featuresand random forest, " in Proc. 2014 36th Annu. Int. Conf. IEEE, Eng. Med. Biol. Soc., 2014, pp. 6040-6043.
16. Y. Uchiyama, et al., "Quantitative computerized analysis of diffuse lungdisease in high-resolution computed tomography, " Med. Phys., vol. 30, no. 9, pp. 2440-2454, 2003.
17. K. T. Vo and A. Sowmya, "Multiple kernel learning for classification ofdiffuse lung disease using hrct lung images, " in Proc. 2010 Annu. Int. Conf. IEEE. Eng. Med. Biol. Soc., 2010, pp. 3085-3088.
18. L. Sørensen, S. B. Shaker, M. De Bruijne, "Quantitative analysis ofpulmonary emphysema using local binary patterns, " IEEE Trans. Med. Imag., vol. 29, no. 2, pp. 559-569, Feb. 2010.
19. V. A. Zavaletta, B. J. Bartholmai, R. A. Robb, "High resolution multidetectorct-aided tissue analysis and quantification of lung fibrosis, " Acad. Radiol., vol. 14, no. 7, pp. 772-787, 2007.
20. P. D. Korfiatis, A. N. Karahaliou, A. D. Kazantzi, C. Kalogeropoulou, and L. I. Costaridou, "Texture-based identification and characterization ofinterstitial pneumonia patterns in lung multidetector ct, " IEEE Trans. Inf. Technol. Biomed., vol. 14, no. 3, pp. 675-680, May 2010.
21. A. Depeursinge, et al., "Optimized steerable wavelets for texture analysisof lung tissue in 3-d ct: Classification of usual interstitial pneumonia, " in2015 IEEE 12th Int. Symp. Biomed. Imag., 2015, pp. 403-406.
22. M. J. Gangeh, L. Sørensen, S. B. Shaker, M. S. Kamel, M. De Bruijne, and M. Loog, "A texton-based approach for the classification of lungparenchyma in ct images, " in Proc. Med. Image Comput. Comput.-AssistedIntervention., 2010, pp. 595-602.
23. A. Foncubierta-Rodŕguez, A. Depeursinge, H. Müller, "Usingmultiscale visual words for lung texture classification and retrieval, "in Proc. Med. Content-Based Retrieval Clin. Decis. Support, 2011, pp. 69-79.
24. W. Zhao, R. Xu, Y. Hirano, R. Tachibana, S. Kido, "Classificationof diffuse lung diseases patterns by a sparse representation based methodon HRCT images, " in Proc. 2013 35th Annu. Int. Conf. IEEE. Eng. Med. Biol. Soc., 2013, pp. 5457-5460.
25. K. T. Vo and A. Sowmya, "Multiscale sparse representation of highresolutioncomputed tomography (HRCT) lung images for diffuse lungdisease classification, " in Proc. 2011 18th IEEE Int. Conf. Image Process., 2011, pp. 441-444.
26. Q. Li, W. Cai, D. D. Feng, "Lung image patch classification withautomatic feature learning, " in Proc. 2013 35th Annu. Int. Conf. IEEE. Eng. Med. Biol. Soc., 2013, pp. 6079-6082.
27. A. Depeursinge, D. Van de Ville, A. Platon, A. Geissbuhler, P.-A. Poletti, and H. Müller, "Near-affine-invariant texture learning for lung tissue analysisusing isotropic wavelet frames, " IEEE Trans. Inf. Technol. Biomed., vol. 16, no. 4, pp. 665-675, Jul. 2012.
28. G. van Tulder and M. de Bruijne, "Combining generative and discriminativerepresentation learning for lung ct analysis with convolutionalrestricted Boltzmann machines, " IEEE Trans. Med. Imag., vol. 35, no. 5, pp. 1262-1272, May 2016.
29. Q. Li, W. Cai, X. Wang, Y. Zhou, D. D. Feng, M. Chen, "Medicalimage classification with convolutional neural network, " in Proc. 201413th Int. Conf. Control Autom. Robot. Vis., 2014, pp. 844-848.
30. H.-c. Shin, et al., "Deep convolutional neural networks for computeraideddetection: CNN architectures, dataset characteristics and transferlearning, " IEEE Trans. Med. Imag., vol. 35, no. 5, pp. 1285-1298, Feb. 2016.
31. S. J. Pan and Q. Yang, "A survey on transfer learning, " IEEE Trans. Knowl. Data Eng., vol. 22, no. 10, pp. 1345-1359, Oct. 2010.
32. A. S. Razavian, H. Azizpour, J. Sullivan, S. Carlsson, "CNN featuresoff-the-shelf: An astounding baseline for recognition, " in Proc. 2014 IEEEConf. Comput. Vis. Pattern Recognit. Workshops, 2014, pp. 512-519.
33. J. Yosinski, J. Clune, Y. Bengio, H. Lipson, "How transferable arefeatures in deep neural networks" in Proc. Adv. Neural Inf. Process. Syst., Nov. 2014, vol. 27, pp. 1-9.
34. L. Castrejon, Y. Aytar, C. Vondrick, H. Pirsiavash, A. Torralba, "Learningaligned cross-modal representations from weakly aligned data, " inProc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 2940-2949.
35. R. Caruana, "Multitask learning, " Mach. Learn., vol. 28, no. 1, pp. 41-75, Jul. 1997.
36. L. Zheng, Y. Zhao, S. Wang, J. Wang, Q. Tian, "Good practice incnn feature transfer, " vol. abs/1604. 00133, (2016). [Online]. Available:http://arxiv. org/abs/1604. 00133
37. H. Azizpour, A. S. Razavian, J. Sullivan, A. Maki, S. Carlsson, "Fromgeneric to specific deep representations for visual recognition, " in Proc. 2015 IEEE Conf. Comput. Vis. Pattern Recognit. Workshops, Jun. 2015, pp. 36-45.
38. N. Tajbakhsh, et al., "Convolutional neural networks for medical imageanalysis: Full training or fine tuning" IEEE Trans. Med. Imag., vol. 35, no. 5, pp. 1299-1312, May 2016.
39. A. Depeursinge, A. Vargas, A. Platon, A. Geissbuhler, P.-A. Poletti, H. Müller, "Building a reference multimedia database for interstitial lungdiseases, " Comput. Med. Imag. Graph., vol. 36, no. 3, pp. 227-238, 2012.
40. D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization, "vol. abs/1412. 6980, (2014). [Online]. Available: http://arxiv. org/abs/1412. 6980
41. T. G. Dietterich, "Ensemble methods in machine learning, " in Proc. 1stInt. Workshop Multiple Classifier Syst., 2000, pp. 1-15.
42. R. Caruana, A. Niculescu-Mizil, G. Crew, A. Ksikes, "Ensembleselection from libraries of models, " in Proc. 21st Int. Conf. Mach. Learn, 2004, Art. no. 18.
43. C. Bucilua, R. Caruana, A. Niculescu-Mizil, "Model compression, "in Proc. 12th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2006, pp. 535-541.
44. G. E. Hinton, O. Vinyals, J. Dean, "Distilling the knowledge in aneural network, " CoRR, vol. abs/1503. 02531, (2015). [Online]. Available:http://arxiv. org/abs/1503. 02531
45. F. Chollet, "Keras, " 2015. [Online]. Available: https://github. com/fchollet/keras
46. R. Al-Rfou, et al., "Theano: A Python framework for fast computation ofmathematical expressions, " CoRR, vol. abs/1605. 02688, (2016). [Online]. Available:http://arxiv. org/abs/1605. 02688
47. K. Simonyan and A. Zisserman, "Very deep convolutional networksfor large-scale image recognition, " CoRR, vol. abs/1409. 1556, (2014). [Online]. Available: http://arxiv. org/abs/1409. 1556