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

Jizong Peng1, Marco Pedersoli1, Christian Desrosiers1
1: ÉTS Montréal
Publication date: 2021/06/28
https://doi.org/10.59275/j.melba.2021-g79f
PDF · Code · Video · arXiv

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 leveraging 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.

Keywords

semantic segmentation · semi-supervised learning · deep clustering · mutual information · convolutional neural network

Bibtex @article{melba:2021:009:peng, title = "Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization", author = "Peng, Jizong and Pedersoli, Marco and Desrosiers, Christian", journal = "Machine Learning for Biomedical Imaging", volume = "1", issue = "MIDL 2020 special issue", year = "2021", pages = "1--29", issn = "2766-905X", doi = "https://doi.org/10.59275/j.melba.2021-g79f", url = "https://melba-journal.org/2021:009" }
RISTY - JOUR AU - Peng, Jizong AU - Pedersoli, Marco AU - Desrosiers, Christian PY - 2021 TI - Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization T2 - Machine Learning for Biomedical Imaging VL - 1 IS - MIDL 2020 special issue SP - 1 EP - 29 SN - 2766-905X DO - https://doi.org/10.59275/j.melba.2021-g79f UR - https://melba-journal.org/2021:009 ER -

2021:009 cover