Towards Novel Methods for Effective Transfer Learning and Unsupervised Deep Learning for Medical Image Analysis

Mijung Kim, Jasper Zuallaert, Wesley De Neve


Increasing attention to the deep learning applications comes to the medical image analysis as well. Recently, Google published the paper on detecting the diabetic retinopathy using their deep learning approach. During our doctoral research, we will mainly focus on dealing with medical image dataset from the deep learning's perspective. In particular, due to its sensitive nature ans sparsity, medical image dataset does not show high performance as other images do such as ImageNet. By making use of transfer learning and unsupervised learning techniques we will investigate in increasing the effectiveness our models in medical image dataset. As for the first step, we challenge to the breast cancer mammography dataset using Inception V4 to diagnose the lesions. After applying data augmentation methods we will move on to unsupervised learning approach to overcome small size and unlabeled dataset. Ultimately, we will develop a unsupervised deep learning network with transferable discriminator maintaining high effectiveness.


  1. Ackley, D. H., Hinton, G. E., and Sejnowski, T. J. (1985). A Learning Algorithm for Boltzmann Machines. Cognitive Science, 9(1):147-169.
  2. Azizpour, H., Sharif Razavian, A., Sullivan, J., Maki, A., and Carlsson, S. (2015). From Generic to Specific Deep Representations for Visual Recognition. In Proceedings of CVPR.
  3. Belghazi, I. (2016). Adversarially Learned Inference.
  4. Boesen, A., Larsen, L., Sønderby, S. K., Larochelle, H., and Winther, O. (2015). Autoencoding beyond Pixels using a Learned Similarity Metric. In Proceedings of ICML, pages 1558-1566.
  5. Bowyer, K., Kopans, D., Kegelmeyer, W., Moore, R., Sallam, M., Chang, K., and Woods, K. (1996). The Digital Database for Screening Mammography. In Third International Workshop on Digital Mammography, volume 58, page 27.
  6. Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., and Abbeel, P. (2016). InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets. In Proceedings of NIPS 2016.
  7. Chen, X.-W. and Lin, X. (2014). Big Data Deep Learning: Challenges and Perspectives. IEEE Access, 2:514- 525.
  8. Ertosun, M. G. and Rubin, D. L. (2015). Probabilistic Visual Search for Masses within Mammography Images using Deep Learning. In 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 1310-1315.
  9. Frans, K. (2016). Generative Adversarial Networks Explained.
  10. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580-587.
  11. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. Book in preparation for MIT Press.
  12. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Nets. In Advances in Neural Information Processing Systems, pages 2672-2680.
  13. Guttenberg, N., Sinapayen, L., Yu, Y., Virgo, N., and Kanai, R. (2016). Recurrent Generative Auto-encoders and Novelty Search.
  14. Hajian-Tilaki, K. (2013). Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation. Caspian Journal of Internal Medicine, 4(2):627.
  15. Heath, M., Bowyer, K., Kopans, D., Kegelmeyer Jr, P., Moore, R., Chang, K., and Munishkumaran, S. (1998). Current Status of the Digital Database for Screening Mammography. In Digital Mammography, pages 457-460. Springer.
  16. Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A.- r., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T. N., et al. (2012). Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Processing Magazine, 29(6):82-97.
  17. Kingma, D. P. and Welling, M. (2013). Auto-encoding Variational Bayes. arXiv preprint arXiv:1312.6114.
  18. Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097-1105.
  19. Lalkhen, A. G. and McCluskey, A. (2008). Clinical Tests: Sensitivity and Specificity. Continuing Education in Anaesthesia, Critical Care & Pain, 8(6):221-223.
  20. LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436-444.
  21. Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., and Dean, J. (2013). Distributed Representations of Words and Phrases and Their Compositionality. In Advances in Neural Information Processing Systems, pages 3111-3119.
  22. Pan, S. J. and Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10):1345-1359.
  23. Pewsner, D., Battaglia, M., Minder, C., Marx, A., Bucher, H. C., and Egger, M. (2004). Ruling a Diagnosis In or Out with SpPIn and SnNOut: a Note of Caution. BMJ, 329(7459):209-213.
  24. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. CoRR, abs/1511.06434.
  25. Rezende, D. J., Mohamed, S., and Wierstra, D. (2014). Stochastic Backpropagation and Approximate Inference in Deep Generative Models. arXiv preprint arXiv:1401.4082.
  26. Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1985). Learning internal representations by error propagation. Technical report, DTIC Document.
  27. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved Techniques for Training GANs. In Proceedings of NIPS 2016.
  28. Salimans, T., Kingma, D. P., Welling, M., et al. (2015). Markov chain Monte Carlo and Variational Inference: Bridging the Gap. In International Conference on Machine Learning, pages 1218-1226.
  29. Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., and Lillicrap, T. (2016). One-shot Learning with Memory-Augmented Neural Networks. arXiv preprint arXiv:1605.06065.
  30. Sharma, A. (2015). DDSM Utility.
  31. Szegedy, C., Ioffe, S., and Vanhoucke, V. (2016a). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. arXiv preprint arXiv:1602.07261.
  32. Szegedy, C., Ioffe, S., and Vanhoucke, V. (2016b). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. arXiv preprint arXiv:1602.07261.
  33. BREASTCANCER.ORG (2016). U.S. Breast Cancer Statistics. understand bc/statistics.
  34. Weinstein, S., Obuchowski, N. A., and Lieber, M. L. (2005). Clinical Evaluation of Diagnostic Tests. American Journal of Roentgenology, 184(1):14-19.
  35. Wong, T. Y. and Bressler, N. M. (2016). Artificial Intelligence With Deep Learning Technology Looks Into Diabetic Retinopathy Screening. JAMA, 316(22):2366-2367.
  36. Yosinski, J., Clune, J., Bengio, Y., and Lipson, H. (2014). How Transferable are Features in Deep Neural Networks? In Proceedings of NIPS, pages 3320-3328.

Paper Citation

in Harvard Style

Kim M., Zuallaert J. and De Neve W. (2017). Towards Novel Methods for Effective Transfer Learning and Unsupervised Deep Learning for Medical Image Analysis . In Doctoral Consortium - DCBIOSTEC, (BIOSTEC 2017) ISBN , pages 32-39

in Bibtex Style

author={Mijung Kim and Jasper Zuallaert and Wesley De Neve},
title={Towards Novel Methods for Effective Transfer Learning and Unsupervised Deep Learning for Medical Image Analysis},
booktitle={Doctoral Consortium - DCBIOSTEC, (BIOSTEC 2017)},

in EndNote Style

JO - Doctoral Consortium - DCBIOSTEC, (BIOSTEC 2017)
TI - Towards Novel Methods for Effective Transfer Learning and Unsupervised Deep Learning for Medical Image Analysis
SN -
AU - Kim M.
AU - Zuallaert J.
AU - De Neve W.
PY - 2017
SP - 32
EP - 39
DO -