Benchmarking Deep Learning for NSCLC PET/CT Segmentation on a Histologically Confirmed Vietnamese Dataset: Validation and Generalization
TL;DR
The fine-tuned nnU-Net model demonstrated a high correlation between the MTV and the ground truth, indicating its potential as a reliable automated approach for quantitative MTV extraction and NSCLC prognostic-related analysis.
Abstract
Accurate segmentation of non-small cell lung cancer (NSCLC) on positron emission tomography/computed tomography (PET/CT) is an essential prerequisite for automated metabolic tumor volume (MTV) quantification and staging. Although deep learning models achieve high performance on large-scale datasets, their generalization across different clinical domains is limited by variations in imaging protocols and patient demographics. This study aims to evaluate several deep learning architectures and investigate a transfer learning strategy to mitigate domain shift. Three architectures, including ResNet-backbone 3D U-Net, nnU-Net v2, and Swin UNETR, were benchmarked from scratch and compared with a fine-tuned nnU-Net initialized with AutoPET II weights. Results on the internal dataset showed that the fine-tuned nnU-Net achieved a Dice similarity coefficient (DSC) of 83.4 ± 6.5%, a 95% Hausdorff distance (HD95) of 5.1 ± 3.6 mm, and a precision of 89.6 ± 8.2%. Compared to the nnU-Net v2, the fine-tuned nnU-Net improved the absolute DSC by 6.8% while reducing local training time by 37.5% by bypassing the initial feature-learning phase. The fine-tuned nnU-Net model also demonstrated a high correlation between the MTV and the ground truth (Pearson r = 0.96, p < 0.001), indicating its potential as a reliable automated approach for quantitative MTV extraction and NSCLC prognostic-related analysis.