Citation

Ismail, Amelia Ritahani and Azlan, Faris Farhan and Noormaizan, Khairul Akmal and Afiqa, Nurul and Nisa, Syed Qamrun and Ghazali, Ahmad Badaruddin and Pranolo, Andri and Saifullah, Shoffan (2025) Privacy-Preserving U-Net Variants with pseudo-labeling for radiolucent lesion segmentation in dental CBCT. International Journal of Advances in Intelligent Informatics, 11 (2). p. 275. ISSN 2442-6571

Text Privacy-Preserving U-Net Variants with pseudo-labeling for radiolucent lesion segmentation in dental CBCT _ Ismail _ International Journal of Advances in Intelligent Informatics.pdf - Published Version Restricted to Repository staff only Download (11MB)

Abstract

Accurate segmentation of radiolucent lesions in dental ConeBeam Computed Tomography (CBCT) is vital for enhancing diagnostic reliability and reducing the burden on clinicians. This study proposes a privacypreserving segmentation framework leveraging multiple U-Net variantsU-Net, DoubleU-Net, U2-Net, and Spatial Attention U-Net (SA-UNet)to address challenges posed by limited labeled data and patient confidentiality concerns. To safeguard sensitive information, Differential Privacy Stochastic Gradient Descent (DP-SGD) is integrated using TensorFlow-Privacy, achieving a privacy budget of ε≈1.5 with minimal performance degradation. Among the evaluated architectures, U2-Net demonstrates superior segmentation performance with a Dice coefficient of 0.833 and an Intersection over Union (IoU) of 0.881, showing less than 2% reduction under privacyconstraints. To mitigate data annotation scarcity, a pseudo-labeling approach is implemented within an MLOps pipeline, enabling semi-supervised learning from unlabeled CBCT images. Over three iterative refinements, the pseudolabeling strategy reduces validation loss by 14.4% and improves Dice score by 2.6%, demonstrating its effectiveness. Additionally, comparative evaluations reveal that SA-UNet offers competitive accuracy with faster inference time (22 ms per slice), making itsuitable for low-resource deployments. The proposed approach presents a scalable and privacy-compliant framework for radiolucent lesion segmentation, supporting clinical decision-making in real-world dental imaging scenarios.

Item Type:	Article
Uncontrolled Keywords:	Dental imaging
Subjects:	R Medicine > RC Internal medicine > RC71-78.7 Examination. Diagnosis
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	29 Jul 2025 05:17
Last Modified:	29 Jul 2025 05:17
URII:	http://shdl.mmu.edu.my/id/eprint/14380

Downloads

Edit (login required)