Automated segmentation of lesions and organs at risk on [⁶⁸Ga]Ga-PSMA-11 PET/CT images using self-supervised learning with Swin UNETR.

ABSTRACT:

Background

Prostate-specific membrane antigen (PSMA) PET/CT imaging is widely used for quantitative image analysis, especially in radioligand therapy (RLT) for metastatic castration-resistant prostate cancer (mCRPC). Unknown features influencing PSMA biodistribution can be explored by analyzing segmented organs at risk (OAR) and lesions. Manual segmentation is time-consuming and labor-intensive, so automated segmentation methods are desirable. Training deep-learning segmentation models is challenging due to the scarcity of high-quality annotated images. Addressing this, we developed shifted windows UNEt TRansformers (Swin UNETR) for fully automated segmentation. Within a self-supervised framework, the model's encoder was pre-trained on unlabeled data. The entire model was fine-tune

SUBMITTER: Yazdani E 

PROVIDER: S-EPMC10903052 | biostudies-literature | 2024 Feb

REPOSITORIES: biostudies-literature