Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Automated Segmentation of Lesions and Organs at Risk on [68Ga]Ga-Psma-11 Pet/Ct Images Using Self-Supervised Learning With Swin Unetr Publisher Pubmed



Yazdani E1, 2 ; Karamzadehziarati N3 ; Cheshmi SS4 ; Sadeghi M1, 2 ; Geramifar P3 ; Vosoughi H3, 5 ; Jahromi MK1, 2 ; Kheradpisheh SR4
Authors
Show Affiliations
Authors Affiliations
  1. 1. Medical Physics Department, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
  2. 2. Fintech in Medicine Research Center, Iran University of Medical Sciences, Tehran, Iran
  3. 3. Research Center for Nuclear Medicine, Tehran University of Medical Sciences, Tehran, Iran
  4. 4. Department of Computer and Data Sciences, Faculty of Mathematical Sciences, Shahid Beheshti University, Tehran, Iran
  5. 5. Nuclear Medicine and Molecular Imaging Department, Imam Reza International University, Razavi Hospital, Mashhad, Iran

Source: Cancer Imaging Published:2024


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-tuned, including its decoder, using labeled data. Methods: In this work, 752 whole-body [68Ga]Ga-PSMA-11 PET/CT images were collected from two centers. For self-supervised model pre-training, 652 unlabeled images were employed. The remaining 100 images were manually labeled for supervised training. In the supervised training phase, 5-fold cross-validation was used with 64 images for model training and 16 for validation, from one center. For testing, 20 hold-out images, evenly distributed between two centers, were used. Image segmentation and quantification metrics were evaluated on the test set compared to the ground-truth segmentation conducted by a nuclear medicine physician. Results: The model generates high-quality OARs and lesion segmentation in lesion-positive cases, including mCRPC. The results show that self-supervised pre-training significantly improved the average dice similarity coefficient (DSC) for all classes by about 3%. Compared to nnU-Net, a well-established model in medical image segmentation, our approach outperformed with a 5% higher DSC. This improvement was attributed to our model’s combined use of self-supervised pre-training and supervised fine-tuning, specifically when applied to PET/CT input. Our best model had the lowest DSC for lesions at 0.68 and the highest for liver at 0.95. Conclusions: We developed a state-of-the-art neural network using self-supervised pre-training on whole-body [68Ga]Ga-PSMA-11 PET/CT images, followed by fine-tuning on a limited set of annotated images. The model generates high-quality OARs and lesion segmentation for PSMA image analysis. The generalizable model holds potential for various clinical applications, including enhanced RLT and patient-specific internal dosimetry. © The Author(s) 2024.