Lesion Segmentation in FDG-PET/CT Using Swin Transformer U-Net 3D: A Robust Deep Learning Framework

TL;DR

This paper introduces SwinUNet3D, a transformer-based deep learning model that significantly improves lesion segmentation accuracy and speed in FDG-PET/CT scans, outperforming traditional U-Net architectures.

Contribution

The paper presents a novel Swin Transformer U-Net 3D framework that effectively combines global attention with local detail for improved lesion segmentation in PET/CT imaging.

Findings

SwinUNet3D achieves a Dice score of 0.88, surpassing baseline models.

The model demonstrates faster inference times compared to traditional U-Net.

Qualitative results show better detection of small and irregular lesions.

Abstract

Accurate and automated lesion segmentation in Positron Emission Tomography / Computed Tomography (PET/CT) imaging is essential for cancer diagnosis and therapy planning. This paper presents a Swin Transformer UNet 3D (SwinUNet3D) framework for lesion segmentation in Fluorodeoxyglucose Positron Emission Tomography / Computed Tomography (FDG-PET/CT) scans. By combining shifted window self-attention with U-Net style skip connections, the model captures both global context and fine anatomical detail. We evaluate SwinUNet3D on the AutoPET III FDG dataset and compare it against a baseline 3D U-Net. Results show that SwinUNet3D achieves a Dice score of 0.88 and IoU of 0.78, surpassing 3D U-Net (Dice 0.48, IoU 0.32) while also delivering faster inference times. Qualitative analysis demonstrates improved detection of small and irregular lesions, reduced false positives, and more accurate PET/CT fusion. While the framework is currently limited to FDG scans and trained under modest GPU resources, it establishes a strong foundation for future multi-tracer, multi-center evaluations and benchmarking against other transformer-based architectures. Overall, SwinUNet3D represents an efficient and robust approach to PET/CT lesion segmentation, advancing the integration of transformer-based models into oncology imaging workflows.