Deep PET/CT fusion with Dempster-Shafer theory for lymphoma segmentation

TL;DR

This paper introduces a novel lymphoma segmentation method combining PET and CT data using Dempster-Shafer theory within a UNet framework, achieving high accuracy without user interaction.

Contribution

It proposes an evidential fusion layer based on Dempster-Shafer theory and a multi-task loss function for improved PET/CT lymphoma segmentation.

Findings

Achieved a Dice score of 0.726 on a lymphoma PET/CT dataset.

Outperformed state-of-the-art segmentation methods.

Demonstrated effective fusion of PET and CT evidence.

Abstract

Lymphoma detection and segmentation from whole-body Positron Emission Tomography/Computed Tomography (PET/CT) volumes are crucial for surgical indication and radiotherapy. Designing automatic segmentation methods capable of effectively exploiting the information from PET and CT as well as resolving their uncertainty remain a challenge. In this paper, we propose an lymphoma segmentation model using an UNet with an evidential PET/CT fusion layer. Single-modality volumes are trained separately to get initial segmentation maps and an evidential fusion layer is proposed to fuse the two pieces of evidence using Dempster-Shafer theory (DST). Moreover, a multi-task loss function is proposed: in addition to the use of the Dice loss for PET and CT segmentation, a loss function based on the concordance between the two segmentation is added to constrain the final segmentation. We evaluate our proposal on a database of polycentric PET/CT volumes of patients treated for lymphoma, delineated by the experts. Our method get accurate segmentation results with Dice score of 0.726, without any user interaction. Quantitative results show that our method is superior to the state-of-the-art methods.