Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization

Abstract

The scarcity of labeled data often impedes the application of deep learning to the segmentation of medical images. Semi-supervised learning seeks to overcome this limitation by exploiting unlabeled examples in the learning process. In this paper, we present a novel semi-supervised segmentation method that leverages mutual information (MI) on categorical distributions to achieve both global representation invariance and local smoothness. In this method, we maximize the MI for intermediate feature embeddings that are taken from both the encoder and decoder of a segmentation network. We first propose a global MI loss constraining the encoder to learn an image representation that is invariant to geometric transformations. Instead of resorting to computationally-expensive techniques for estimating the MI on continuous feature embeddings, we use projection heads to map them to a discrete cluster assignment where MI can be computed efficiently. Our method also includes a local MI loss to promote spatial consistency in the feature maps of the decoder and provide a smoother segmentation. Since mutual information does not require a strict ordering of clusters in two different assignments, we incorporate a final consistency regularization loss on the output which helps align the cluster labels throughout the network. We evaluate the method on four challenging publicly-available datasets for medical image segmentation. Experimental results show our method to outperform recently-proposed approaches for semi-supervised segmentation and provide an accuracy near to full supervision while training with very few annotated images.

References in corpus (15)

• A Simple Framework for Contrastive Learning of Visual Representations
• Representation Learning with Contrastive Predictive Coding
• Bootstrap your own latent: A new approach to self-supervised Learning
• The information bottleneck method
• Learning deep representations by mutual information estimation and maximization
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• MINE: Mutual Information Neural Estimation
• Contrastive learning of global and local features for medical image segmentation with limited annotations
• Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations
• Semi-Supervised Deep Learning for Fully Convolutional Networks
• Region Mutual Information Loss for Semantic Segmentation
• DEMI: Discriminative Estimator of Mutual Information
• Information based Deep Clustering: An experimental study

Cited by in corpus (3)

• Segmentation with mixed supervision: Confidence maximization helps knowledge distillation
• Weakly-Supervised 3D Medical Image Segmentation using Geometric Prior and Contrastive Similarity
• Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation