Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification

Explaining decisions of black-box classifiers is paramount in sensitive domains such as medical imaging since clinicians confidence is necessary for adoption. Various explanation approaches have been proposed, among which perturbation based approaches are very promising. Within this class of methods, we leverage a learning framework to produce our visual explanations method. From a given classifier, we train two generators to produce from an input image the so called similar and adversarial images. The similar image shall be classified as the input image whereas the adversarial shall not. Visual explanation is built as the difference between these two generated images. Using metrics from the literature, our method outperforms state-of-the-art approaches. The proposed approach is model-agnostic and has a low computation burden at prediction time. Thus, it is adapted for real-time systems. Finally, we show that random geometric augmentations applied to the original image play a regularization role that improves several previously proposed explanation methods. We validate our approach on a large chest X-ray database.

[1]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[2]  David Duvenaud,et al.  Explaining Image Classifiers by Counterfactual Generation , 2018, ICLR.

[3]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[4]  Pradeep Ravikumar,et al.  Evaluations and Methods for Explanation through Robustness Analysis , 2019, ICLR.

[5]  Mingyan Liu,et al.  Generating Adversarial Examples with Adversarial Networks , 2018, IJCAI.

[6]  Yarin Gal,et al.  Real Time Image Saliency for Black Box Classifiers , 2017, NIPS.

[7]  Christof Teuscher,et al.  Adversarial explanations for understanding image classification decisions and improved neural network robustness , 2019, Nature Machine Intelligence.

[8]  Amit Dhurandhar,et al.  Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives , 2018, NeurIPS.

[9]  Christian Biemann,et al.  What do we need to build explainable AI systems for the medical domain? , 2017, ArXiv.

[10]  Meng Wang,et al.  Distribution-Guided Local Explanation for Black-Box Classifiers , 2019 .

[11]  Weijia Zhang,et al.  Generating Adversarial Examples in One Shot With Image-to-Image Translation GAN , 2019, IEEE Access.

[12]  Andrea Vedaldi,et al.  There and Back Again: Revisiting Backpropagation Saliency Methods , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

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

[15]  Chris Russell,et al.  Adversarial Perturbations on the Perceptual Ball , 2019, ArXiv.

[16]  Yotam Hechtlinger,et al.  Interpretation of Prediction Models Using the Input Gradient , 2016, ArXiv.

[17]  Nassir Navab,et al.  Explaining Neural Networks via Perturbing Important Learned Features , 2019, ArXiv.

[18]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[19]  Heinz Handels,et al.  Interpretable explanations of black box classifiers applied on medical images by meaningful perturbations using variational autoencoders , 2019, Medical Imaging: Image Processing.

[20]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[21]  Andrea Vedaldi,et al.  Understanding Deep Networks via Extremal Perturbations and Smooth Masks , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[22]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[24]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[25]  Ronald M. Summers,et al.  ChestX-ray: Hospital-Scale Chest X-ray Database and Benchmarks on Weakly Supervised Classification and Localization of Common Thorax Diseases , 2019, Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics.

[26]  Sven Behnke,et al.  Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Ankur Taly,et al.  Axiomatic Attribution for Deep Networks , 2017, ICML.

[28]  Andrew Y. Ng,et al.  CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning , 2017, ArXiv.

[29]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[30]  Been Kim,et al.  Sanity Checks for Saliency Maps , 2018, NeurIPS.

[31]  Martin Wattenberg,et al.  SmoothGrad: removing noise by adding noise , 2017, ArXiv.

[32]  Gustavo Carneiro,et al.  Model Agnostic Saliency For Weakly Supervised Lesion Detection From Breast DCE-MRI , 2018, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[33]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[34]  Andrea Vedaldi,et al.  Interpretable Explanations of Black Boxes by Meaningful Perturbation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[35]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[36]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[37]  Katja Bühler,et al.  Interpreting Medical Image Classifiers by Optimization Based Counterfactual Impact Analysis , 2020, 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).

[38]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).