Explainable Diabetic Retinopathy Detection and Retinal Image Generation
arXiv:2107.00296 · doi:10.1109/JBHI.2021.3110593
Abstract
Though deep learning has shown successful performance in classifying the label and severity stage of certain diseases, most of them give few explanations on how to make predictions. Inspired by Koch's Postulates, the foundation in evidence-based medicine (EBM) to identify the pathogen, we propose to exploit the interpretability of deep learning application in medical diagnosis. By determining and isolating the neuron activation patterns on which diabetic retinopathy (DR) detector relies to make decisions, we demonstrate the direct relation between the isolated neuron activation and lesions for a pathological explanation. To be specific, we first define novel pathological descriptors using activated neurons of the DR detector to encode both spatial and appearance information of lesions. Then, to visualize the symptom encoded in the descriptor, we propose Patho-GAN, a new network to synthesize medically plausible retinal images. By manipulating these descriptors, we could even arbitrarily control the position, quantity, and categories of generated lesions. We also show that our synthesized images carry the symptoms directly related to diabetic retinopathy diagnosis. Our generated images are both qualitatively and quantitatively superior to the ones by previous methods. Besides, compared to existing methods that take hours to generate an image, our second level speed endows the potential to be an effective solution for data augmentation.
arXiv commentCode is available at https://github.com/zzdyyy/Patho-GAN
References in corpus (15)
- Conditional Generative Adversarial Nets
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- Learning Important Features Through Propagating Activation Differences
- MedGAN: Medical Image Translation using GANs
- This Looks Like That: Deep Learning for Interpretable Image Recognition
- Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability
- RISE: Randomized Input Sampling for Explanation of Black-box Models
- Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
- DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images
- Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation
- Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
- Pathological Evidence Exploration in Deep Retinal Image Diagnosis