Co-Evidential Fusion with Information Volume for Medical Image Segmentation

TL;DR

This paper presents a novel co-evidential fusion approach using generalized evidential deep learning and information volume to improve semi-supervised medical image segmentation by better utilizing voxel-level uncertainties.

Contribution

It introduces a new co-evidential fusion strategy and the concept of information volume of mass functions to enhance semi-supervised segmentation performance.

Findings

Achieves competitive results on four datasets.

Effectively utilizes multiple sources of uncertainty.

Improves learning from unlabeled data.

Abstract

Although existing semi-supervised image segmentation methods have achieved good performance, they cannot effectively utilize multiple sources of voxel-level uncertainty for targeted learning. Therefore, we propose two main improvements. First, we introduce a novel pignistic co-evidential fusion strategy using generalized evidential deep learning, extended by traditional D-S evidence theory, to obtain a more precise uncertainty measure for each voxel in medical samples. This assists the model in learning mixed labeled information and establishing semantic associations between labeled and unlabeled data. Second, we introduce the concept of information volume of mass function (IVUM) to evaluate the constructed evidence, implementing two evidential learning schemes. One optimizes evidential deep learning by combining the information volume of the mass function with original uncertainty measures. The other integrates the learning pattern based on the co-evidential fusion strategy, using IVUM to design a new optimization objective. Experiments on four datasets demonstrate the competitive performance of our method.