Evidential segmentation of 3D PET/CT images

TL;DR

This paper introduces an evidential segmentation approach for 3D PET/CT images that improves lymphoma detection accuracy by providing both segmentation and uncertainty quantification, validated on a large patient dataset.

Contribution

The novel method combines belief functions with a dual-output architecture to enhance segmentation accuracy and uncertainty estimation in 3D medical images.

Findings

Outperforms state-of-the-art segmentation methods

Provides reliable uncertainty maps alongside segmentation

Validated on 173 patient cases

Abstract

PET and CT are two modalities widely used in medical image analysis. Accurately detecting and segmenting lymphomas from these two imaging modalities are critical tasks for cancer staging and radiotherapy planning. However, this task is still challenging due to the complexity of PET/CT images, and the computation cost to process 3D data. In this paper, a segmentation method based on belief functions is proposed to segment lymphomas in 3D PET/CT images. The architecture is composed of a feature extraction module and an evidential segmentation (ES) module. The ES module outputs not only segmentation results (binary maps indicating the presence or absence of lymphoma in each voxel) but also uncertainty maps quantifying the classification uncertainty. The whole model is optimized by minimizing Dice and uncertainty loss functions to increase segmentation accuracy. The method was evaluated on a database of 173 patients with diffuse large b-cell lymphoma. Quantitative and qualitative results show that our method outperforms the state-of-the-art methods.