Synergic Adversarial Label Learning for Grading Retinal Diseases via Knowledge Distillation and Multi-task Learning

Abstract

The need for comprehensive and automated screening methods for retinal image classification has long been recognized. Well-qualified doctors annotated images are very expensive and only a limited amount of data is available for various retinal diseases such as age-related macular degeneration (AMD) and diabetic retinopathy (DR). Some studies show that AMD and DR share some common features like hemorrhagic points and exudation but most classification algorithms only train those disease models independently. Inspired by knowledge distillation where additional monitoring signals from various sources is beneficial to train a robust model with much fewer data. We propose a method called synergic adversarial label learning (SALL) which leverages relevant retinal disease labels in both semantic and feature space as additional signals and train the model in a collaborative manner. Our experiments on DR and AMD fundus image classification task demonstrate that the proposed method can significantly improve the accuracy of the model for grading diseases. In addition, we conduct additional experiments to show the effectiveness of SALL from the aspects of reliability and interpretability in the context of medical imaging application.

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• An Overview of Multi-Task Learning in Deep Neural Networks
• On Calibration of Modern Neural Networks
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• A Model of Inductive Bias Learning
• Born Again Neural Networks
• Unifying distillation and privileged information
• Label Refinery: Improving ImageNet Classification through Label Progression
• Moonshine: Distilling with Cheap Convolutions

Cited by in corpus (7)

• Weakly-supervised detection of AMD-related lesions in color fundus images using explainable deep learning
• Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognition
• Structure Preserving Stain Normalization of Histopathology Images Using Self-Supervised Semantic Guidance
• CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis
• Semi-Supervised Multi-Task Learning for Interpretable Quality As- sessment of Fundus Images
• Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentation
• Multimodal Generalized Zero Shot Learning for Gleason Grading using Self-Supervised Learning