02 آذر 1403
حبيب رستمي

حبیب رستمی

مرتبه علمی: دانشیار
نشانی: دانشکده مهندسی سیستم های هوشمند و علوم داده - گروه مهندسی کامپیوتر
تحصیلات: دکترای تخصصی / کامپیوتر
تلفن: 0773
دانشکده: دانشکده مهندسی سیستم های هوشمند و علوم داده

مشخصات پژوهش

عنوان A convolutional neural network-based system for fully automatic segmentation of whole-body [68Ga]Ga-PSMA PET images in prostate cancer
نوع پژوهش مقالات در نشریات
کلیدواژه‌ها
Artificial intelligence; Deep learning; PET/CT; Prostate cancer; [68Ga]Ga-PSMA.
مجله EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING
شناسه DOI 10.1007/s00259-023-06555-z
پژوهشگران اسماعیل جعفری (نفر اول) ، زارعی امین (نفر دوم) ، حبیب الله دادگر (نفر سوم) ، احمد کشاورز (نفر چهارم) ، ریحانه منافی فرد (نفر پنجم) ، حبیب رستمی (نفر ششم به بعد) ، مجید اسدی (نفر ششم به بعد)

چکیده

Purpose: The aim of this study was development and evaluation of a fully automated tool for the detection and segmentation of mPCa lesions in whole-body [68Ga]Ga-PSMA-11 PET scans by using a nnU-Net framework. Methods: In this multicenter study, a cohort of 412 patients from three different center with all indication of PCa who underwent [68Ga]Ga-PSMA-11 PET/CT were enrolled. Two hundred cases of center 1 dataset were used for training the model. A fully 3D convolutional neural network (CNN) is proposed which is based on the self-configuring nnU-Net framework. A subset of center 1 dataset and cases of center 2 and center 3 were used for testing of model. The performance of the segmentation pipeline that was developed was evaluated by comparing the fully automatic segmentation mask with the manual segmentation of the corresponding internal and external test sets in three levels including patient-level scan classification, lesion-level detection, and voxel-level segmentation. In addition, for comparison of PET-derived quantitative biomarkers between automated and manual segmentation, whole-body PSMA tumor volume (PSMA-TV) and total lesions PSMA uptake (TL-PSMA) were calculated. Results: In terms of patient-level classification, the model achieved an accuracy of 83%, sensitivity of 92%, PPV of 77%, and NPV of 91% for the internal testing set. For lesion-level detection, the model achieved an accuracy of 87-94%, sensitivity of 88-95%, PPV of 98-100%, and F1-score of 93-97% for all testing sets. For voxel-level segmentation, the automated method achieved average values of 65-70% for DSC, 72-79% for PPV, 53-58% for IoU, and 62-73% for sensitivity in all testing sets. In the evaluation of volumetric parameters, there was a strong correlation between the manual and automated measurements of PSMA-TV and TL-PSMA for all centers. Conclusions: The deep learning networks presented here offer promising solutions for automatically segmenting malignant lesions in prostate cancer pa