Dual channel CW nnU-Net for 3D PET-CT Lesion Segmentation in 2024 autoPET III Challenge

TL;DR

This paper introduces a dual channel CW nnU-Net with a novel sample attention boosting technique for improved 3D PET-CT lesion segmentation, demonstrating superior performance in the autoPET III Challenge with a high Dice score.

Contribution

The study presents a novel dual channel CW nnU-Net architecture combined with a sample attention boosting method to enhance segmentation accuracy and generalization across different tracers in PET-CT imaging.

Findings

Outperformed baseline model in challenge test set

Achieved a Dice score of 0.8700

Ranked 2nd among 497 participants worldwide

Abstract

PET/CT is extensively used in imaging malignant tumors because it highlights areas of increased glucose metabolism, indicative of cancerous activity. Accurate 3D lesion segmentation in PET/CT imaging is essential for effective oncological diagnostics and treatment planning. In this study, we developed an advanced 3D residual U-Net model for the Automated Lesion Segmentation in Whole-Body PET/CT - Multitracer Multicenter Generalization (autoPET III) Challenge, which will be held jointly with 2024 Medical Image Computing and Computer Assisted Intervention (MICCAI) conference at Marrakesh, Morocco. Proposed model incorporates a novel sample attention boosting technique to enhance segmentation performance by adjusting the contribution of challenging cases during training, improving generalization across FDG and PSMA tracers. The proposed model outperformed the challenge baseline model in the preliminary test set on the Grand Challenge platform, and our team is currently ranking in the 2nd place among 497 participants worldwide from 53 countries (accessed date: 2024/9/4), with Dice score of 0.8700, False Negative Volume of 19.3969 and False Positive Volume of 1.0857.