LinkedIn

 آمار

تعداد نشریات21
تعداد شماره‌ها1,276
تعداد مقالات11,665
تعداد مشاهده مقاله82,398,453
تعداد دریافت فایل اصل مقاله121,390,324
Pishro Dabaghiyan, Taha, Mohammad- Asghari, Mona, Niknam, Ramin, Parsaei, Hossein, Movahedi, Mohammad Mehdi, Mahmoudi, Tahereh, Lankarani, Kamran Bagheri, Malek-Hosseini, Seyed Ali, Taghavi, Seyed Alireza, Ejtehadi, Fardad, Fallahzadeh Abarghooei, Ebrahim, Sivandzadeh, Gholam Reza. (1405). Deep Learning-Based Hybrid Loss U-Net for Automated Segmentation of Common Bile Duct Stones in ERCP Fluoroscopy. سامانه مدیریت نشریات علمی, (), -.
Taha Pishro Dabaghiyan; Mona Mohammad- Asghari; Ramin Niknam; Hossein Parsaei; Mohammad Mehdi Movahedi; Tahereh Mahmoudi; Kamran Bagheri Lankarani; Seyed Ali Malek-Hosseini; Seyed Alireza Taghavi; Fardad Ejtehadi; Ebrahim Fallahzadeh Abarghooei; Gholam Reza Sivandzadeh. "Deep Learning-Based Hybrid Loss U-Net for Automated Segmentation of Common Bile Duct Stones in ERCP Fluoroscopy". سامانه مدیریت نشریات علمی, , , 1405, -.
Pishro Dabaghiyan, Taha, Mohammad- Asghari, Mona, Niknam, Ramin, Parsaei, Hossein, Movahedi, Mohammad Mehdi, Mahmoudi, Tahereh, Lankarani, Kamran Bagheri, Malek-Hosseini, Seyed Ali, Taghavi, Seyed Alireza, Ejtehadi, Fardad, Fallahzadeh Abarghooei, Ebrahim, Sivandzadeh, Gholam Reza. (1405). 'Deep Learning-Based Hybrid Loss U-Net for Automated Segmentation of Common Bile Duct Stones in ERCP Fluoroscopy', سامانه مدیریت نشریات علمی, (), pp. -.
Pishro Dabaghiyan, Taha, Mohammad- Asghari, Mona, Niknam, Ramin, Parsaei, Hossein, Movahedi, Mohammad Mehdi, Mahmoudi, Tahereh, Lankarani, Kamran Bagheri, Malek-Hosseini, Seyed Ali, Taghavi, Seyed Alireza, Ejtehadi, Fardad, Fallahzadeh Abarghooei, Ebrahim, Sivandzadeh, Gholam Reza. Deep Learning-Based Hybrid Loss U-Net for Automated Segmentation of Common Bile Duct Stones in ERCP Fluoroscopy. سامانه مدیریت نشریات علمی, 1405; (): -.

Deep Learning-Based Hybrid Loss U-Net for Automated Segmentation of Common Bile Duct Stones in ERCP Fluoroscopy

Journal of Biomedical Physics and Engineering
مقالات آماده انتشار، اصلاح شده برای چاپ، انتشار آنلاین از تاریخ 26 خرداد 1405    اصل مقاله (1.08 M)
نوع مقاله: Original Research
نویسندگان
Taha Pishro Dabaghiyan1؛ Mona Mohammad- Asghari1؛ Ramin Niknam2؛ Hossein Parsaei* 3؛ Mohammad Mehdi Movahedi* 3؛ Tahereh Mahmoudi3؛ Kamran Bagheri Lankarani2؛ Seyed Ali Malek-Hosseini4؛ Seyed Alireza Taghavi5؛ Fardad Ejtehadi5؛ Ebrahim Fallahzadeh Abarghooei5؛ Gholam Reza Sivandzadeh5
1Student Research Committee, Shiraz University of Medical Sciences, Shiraz, Iran
2Health Policy Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
3Department of Medical Physics and Engineering, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran
4Shiraz Transplant Center, Abu Ali Sina Hospital, Shiraz University of Medical Sciences, Shiraz, Iran
5Gastroenterohepatology Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
چکیده
Background: Accurate segmentation of common bile duct (CBD) stones during endoscopic retrograde cholangiopancreatography (ERCP) is essential to reduce procedural complications and ensure complete stone removal. However, the high deformability of the CBD and the small size of stones make accurate identification challenging in fluoroscopic images.
Objective: To develop and validate a deep learning based model capable of segmenting CBD stones, the CBD, and the duodenoscope in ERCP fluoroscopic images.
Material and Methods: This retrospective study utilized 1,668 ERCP cholangiograms collected from a single tertiary center. A U-Net-based convolutional neural network was trained using various individual and hybrid loss functions. Model performance was evaluated using Intersection over Union (IoU), precision, and recall.
Results: The model trained with a hybrid loss function combining Dice Loss and Categorical Focal Loss achieved IoU scores of 96.93% for the duodenoscope, 89.76% for the CBD, and a mean IoU of 80.61% for CBD stones. These results reflect a 1.19% improvement in CBD segmentation and a 7.93% improvement in stone segmentation compared to existing approaches. 
Conclusion: The proposed deep learning model significantly enhances segmentation accuracy in ERCP imaging and shows strong potential for supporting real-time clinical decision-making. Its integration into ERCP workflows could improve procedural safety, efficiency, and patient outcomes.
کلیدواژه‌ها
Deep Learning؛ Image Segmentation؛ Common Bile Duct Stones؛ Endoscopic Retrograde Cholangiopancreatography؛ Computer-Assisted Diagnosis؛ Fluoroscopy؛ U-Net Architecture؛ Artificial Intelligence
آمار
تعداد مشاهده مقاله: 17
تعداد دریافت فایل اصل مقاله: 28


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب