Webly Supervised Learning for Skin Lesion Classification

Within medical imaging, manual curation of sufficient well-labeled samples is cost, time and scale-prohibitive. To improve the representativeness of the training dataset, for the first time, we present an approach to utilize large amounts of freely available web data through web-crawling. To handle noise and weak nature of web annotations, we propose a two-step transfer learning based training process with a robust loss function, termed as Webly Supervised Learning (WSL) to train deep models for the task. We also leverage search by image to improve the search specificity of our web-crawling and reduce cross-domain noise. Within WSL, we explicitly model the noise structure between classes and incorporate it to selectively distill knowledge from the web data during model training. To demonstrate improved performance due to WSL, we benchmarked on a publicly available 10-class fine-grained skin lesion classification dataset and report a significant improvement of top-1 classification accuracy from 71.25 % to 80.53 % due to the incorporation of web-supervision.

[1]  Ivan Laptev,et al.  Is object localization for free? - Weakly-supervised learning with convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Noel C. F. Codella,et al.  Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[3]  Richard Nock,et al.  Making Neural Networks Robust to Label Noise: a Loss Correction Approach , 2016, ArXiv.

[4]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[5]  Barbara Caputo,et al.  Learning deep visual object models from noisy web data: How to make it work , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[6]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Xiaogang Wang,et al.  Learning from massive noisy labeled data for image classification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Fatma Sherif,et al.  Skin Lesion Analysis Toward Melanoma Detection Using Deep Learning Techniques , 2019, International Journal of Electronics and Telecommunications.

[9]  Richard Nock,et al.  Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Hiroshi Koga,et al.  Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble , 2017, ArXiv.

[11]  R Saranya,et al.  Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks , 2019 .

[12]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[13]  Rob Fergus,et al.  Learning from Noisy Labels with Deep Neural Networks , 2014, ICLR.

[14]  Joan Bruna,et al.  Training Convolutional Networks with Noisy Labels , 2014, ICLR 2014.

[15]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[16]  Xinlei Chen,et al.  Webly Supervised Learning of Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[17]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Robert B. Fisher,et al.  A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions , 2013 .

[19]  Jonathan Krause,et al.  The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition , 2015, ECCV.

[20]  Arash Vahdat,et al.  Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks , 2017, NIPS.

[21]  Hao Chen,et al.  Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks , 2017, IEEE Transactions on Medical Imaging.