Automated segmentation of lesions and organs at risk on [68Ga]Ga-PSMA-11 PET/CT images using self-supervised learning with Swin UNETR
Elmira Yazdani, Najme Karamzadeh-Ziarati, Seyyed Saeid Cheshmi, Mahdi Sadeghi, Parham Geramifar, Habibeh Vosoughi, Mahmood Kazemi Jahromi, Saeed Reza Kheradpisheh
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/elmirayazdani/lesions-oars-segmentation-psma-petct-ssl-swinunetrOfficialIn paperpytorch★ 14
- github.com/scheshmi/SSL-OARs-Tumor-Segmentation-in-PETCTpytorch★ 9
Abstract
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-tuned, including its decoder, using labeled data.