Privacy-preserving U-Net variants with pseudo-labeling for radiolucent lesion segmentation in dental CBCT

Accurate segmentation of radiolucent lesions in dental Cone-Beam Computed Tomography (CBCT) is vital for enhancing diagnostic reliability and reducing the burden on clinicians. This study proposes a privacy-preserving segmentation framework leveraging multiple U-Net variants—U-Net, DoubleU-Net, U2-N...

Full description

Bibliographic Details

Main Authors:	Ismail, Amelia Ritahani, Azlan, Faris Farhan, Noormaizan, Khairul Akmal, Afiqa, Nurul, Nisa, Syed Qamrun, Ghazali, Ahmad Badruddin, Pranolo, Andri, Saifullah, Shoffan
Format:	Article
Language:	en en
Published:	Universitas Ahmad Dahlan 2025
Subjects:	QA76 Computer software RK Dentistry RK318 Oral and Dental Medicine. Pathology. Diseases-Therapeutics-General Works
Online Access:	http://irep.iium.edu.my/122706/7/122706_Privacy%20preserving%20U-Net.pdf http://irep.iium.edu.my/122706/8/122706_Privacy%20preserving%20U-Net_SCOPUS.pdf http://irep.iium.edu.my/122706/ https://ijain.org/index.php/IJAIN/article/view/1529#:~:text=This%20study%20proposes%20a%20privacy-preserving%20segmentation%20framework%20leveraging,by%20limited%20labeled%20data%20and%20patient%20confidentiality%20concerns.
Tags:	Add Tag No Tags, Be the first to tag this record!