Transductive image segmentation: Self-training and effect of uncertainty estimation

TL;DR

This paper explores transductive semi-supervised learning for medical image segmentation, emphasizing prediction quality on specific unlabeled data and demonstrating benefits of calibrated models in self-training.

Contribution

It investigates transductive learning in medical image segmentation, highlighting the importance of prediction calibration and providing extensive experimental validation.

Findings

Transductive learning improves segmentation accuracy on specific unlabeled datasets.

Calibrated or under-confident models enhance self-training effectiveness.

Experimental results show promising gains over inductive methods.

Abstract

Semi-supervised learning (SSL) uses unlabeled data during training to learn better models. Previous studies on SSL for medical image segmentation focused mostly on improving model generalization to unseen data. In some applications, however, our primary interest is not generalization but to obtain optimal predictions on a specific unlabeled database that is fully available during model development. Examples include population studies for extracting imaging phenotypes. This work investigates an often overlooked aspect of SSL, transduction. It focuses on the quality of predictions made on the unlabeled data of interest when they are included for optimization during training, rather than improving generalization. We focus on the self-training framework and explore its potential for transduction. We analyze it through the lens of Information Gain and reveal that learning benefits from the use of calibrated or under-confident models. Our extensive experiments on a large MRI database for multi-class segmentation of traumatic brain lesions shows promising results when comparing transductive with inductive predictions. We believe this study will inspire further research on transductive learning, a well-suited paradigm for medical image analysis.