Autopet III challenge: Incorporating anatomical knowledge into nnUNet for lesion segmentation in PET/CT

TL;DR

This paper presents an advanced automated lesion segmentation method for PET/CT images using nnUNet with anatomical knowledge, achieving high accuracy across diverse datasets and tracers in a challenging multicenter setting.

Contribution

The study introduces a tracer classifier and multi-label nnUNet ensembles incorporating anatomical labels, improving lesion segmentation performance in a multicenter, multi-tracer PET/CT challenge.

Findings

Achieved Dice scores of 76.90% for FDG and 61.33% for PSMA datasets.

Developed a tracer classifier based on Maximum Intensity Projection.

Enhanced segmentation accuracy by including anatomical labels as multi-label tasks.

Abstract

Lesion segmentation in PET/CT imaging is essential for precise tumor characterization, which supports personalized treatment planning and enhances diagnostic precision in oncology. However, accurate manual segmentation of lesions is time-consuming and prone to inter-observer variability. Given the rising demand and clinical use of PET/CT, automated segmentation methods, particularly deep-learning-based approaches, have become increasingly more relevant. The autoPET III Challenge focuses on advancing automated segmentation of tumor lesions in PET/CT images in a multitracer multicenter setting, addressing the clinical need for quantitative, robust, and generalizable solutions. Building on previous challenges, the third iteration of the autoPET challenge introduces a more diverse dataset featuring two different tracers (FDG and PSMA) from two clinical centers. To this extent, we developed a classifier that identifies the tracer of the given PET/CT based on the Maximum Intensity Projection of the PET scan. We trained two individual nnUNet-ensembles for each tracer where anatomical labels are included as a multi-label task to enhance the model's performance. Our final submission achieves cross-validation Dice scores of 76.90% and 61.33% for the publicly available FDG and PSMA datasets, respectively. The code is available at https://github.com/hakal104/autoPETIII/ .