In this study, we implemented a two-stage deep learning-based approach to segment lesions in PET/CT images for the AutoPET III challenge. The first stage utilized a DynUNet model for coarse segmentation, identifying broad regions of interest. The second stage refined this segmentation using an ensemble of SwinUNETR, SegResNet, and UNet models. Preprocessing involved resampling images to a common resolution and normalization, while data augmentation techniques such as affine transformations and intensity adjustments were applied to enhance model generalization. The dataset was split into 80% training and 20% validation, excluding healthy cases. This method leverages multi-stage segmentation and model ensembling to achieve precise lesion segmentation, aiming to improve robustness and overall performance.
@article{arxiv.2409.13006,
title = {AutoPET III Challenge: PET/CT Semantic Segmentation},
author = {Reza Safdari and Mohammad Koohi-Moghaddam and Kyongtae Tyler Bae},
journal= {arXiv preprint arXiv:2409.13006},
year = {2024}
}