Autopet III challenge: Incorporating anatomical knowledge into nnUNet for lesion segmentation in PET/CT
This work addresses the clinical need for robust and generalizable tumor segmentation in PET/CT, but it is incremental as it builds on existing nnUNet frameworks with multi-label tasks.
The paper tackled automated lesion segmentation in PET/CT imaging for oncology by developing a method that incorporates anatomical knowledge into nnUNet, achieving cross-validation Dice scores of 76.90% for FDG and 61.33% for PSMA datasets.
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/ .