Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation

Abstract

Few-shot semantic segmentation (FSS) has great potential for medical imaging applications. Most of the existing FSS techniques require abundant annotated semantic classes for training. However, these methods may not be applicable for medical images due to the lack of annotations. To address this problem we make several contributions: (1) A novel self-supervised FSS framework for medical images in order to eliminate the requirement for annotations during training. Additionally, superpixel-based pseudo-labels are generated to provide supervision; (2) An adaptive local prototype pooling module plugged into prototypical networks, to solve the common challenging foreground-background imbalance problem in medical image segmentation; (3) We demonstrate the general applicability of the proposed approach for medical images using three different tasks: abdominal organ segmentation for CT and MRI, as well as cardiac segmentation for MRI. Our results show that, for medical image segmentation, the proposed method outperforms conventional FSS methods which require manual annotations for training.

arXiv commentECCV2020

References in corpus (18)

• Semi-Supervised Classification with Graph Convolutional Networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Improved Baselines with Momentum Contrastive Learning
• CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation
• Domain Generalization via Model-Agnostic Learning of Semantic Features
• Few-Shot Learning with Graph Neural Networks
• Multivariate mixture model for myocardium segmentation combining multi-source images
• nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation
• Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
• Few-Shot Segmentation Propagation with Guided Networks
• SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
• Deep Compressed Sensing
• Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
• Prototype Refinement Network for Few-Shot Segmentation
• Realistic Adversarial Data Augmentation for MR Image Segmentation
• Meta-Learning Initializations for Image Segmentation
• Differentiable Meta-learning Model for Few-shot Semantic Segmentation

Cited by in corpus (1)

• Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation