
Research Article
Assessment of Segmentation Models on Panoramic Radiographic Dental Images
@INPROCEEDINGS{10.1007/978-3-031-84312-9_12, author={Apporv Upadhye and Peixi Liao and Reem Alasleh and Vissuta Khampatee and Farshid Alizadeh-Shabdiz}, title={Assessment of Segmentation Models on Panoramic Radiographic Dental Images}, proceedings={Computer Science and Education in Computer Science. 20th EAI International Conference, CSECS 2024, Sofia, Bulgaria, June 28--30, 2024, Proceedings}, proceedings_a={CSECS}, year={2025}, month={3}, keywords={Segmentation Dental images deep learning model UNET}, doi={10.1007/978-3-031-84312-9_12} }
- Apporv Upadhye
Peixi Liao
Reem Alasleh
Vissuta Khampatee
Farshid Alizadeh-Shabdiz
Year: 2025
Assessment of Segmentation Models on Panoramic Radiographic Dental Images
CSECS
Springer
DOI: 10.1007/978-3-031-84312-9_12
Abstract
Computer-aided diagnostics and treatment is one of the fastest-growing areas in the dental field . In this effort, dental X-ray image segmentation plays a crucial role in enabling many dental analyses and interpretations and also enables accurate analysis. Recent advancements in image segmentation have been instrumental in this effort. This paper assesses different segmentation models accuracy on dental X-ray panoramic images. Among these models, Residual UNET with binary cross-entropy achieved the best results. Despite obtaining favorable accuracy, other UNET models exhibited lower Intersection of Union (IOU) values in segmentation masks.
Copyright © 2024–2025 ICST