aiqbench analysis
The paper benchmarks four established CNN segmentation architectures (PSPNet, DeepLabV3, UNet, UNet++) on 1,269 dental radiographs under controlled settings. Its main contribution is a fairer side-by-side comparison, which the authors say prior work lacked. Readers should note that UNet++ scored best (IoU 0.6719, Dice 0.7869) at 300x300 input and batch size 16, but these are single-dataset results from a v1 preprint, so they say little about generalization or clinical readiness.
Deep Learning-based Semantic Segmentation of Dental Radiographs: Comparative Evaluation of PSPNet, DeepLabv3, UNet, and UNet++
arXiv:2610.15061v1 Announce Type: cross Abstract: Accurate and efficient analysis of dental radiographs has become increasingly important for disease diagnosis and clinical decision making. In particular, dental radiographs segmentation plays a critical role as it is challenging due to several reasons, such as low contrast, noise in the images, variations in the image quality, etc. Previous studies have primarily addressed these challenges using convolutional neural networks (CNN)-based models. However, direct comparison of these segmentation models is still challenging due to the variations among the experimental settings. Therefore, we mainly compared four segmentation models, including Pyramid Scene Parsing Network (PSPNet), DeepLabV3, UNet, and UNet++, through a fair, controlled experimentation setting under varying conditions such as image sizes and batch sizes. For this, we used 1269 dental radiography images, and prior to training, we implemented a series of preprocessing techniques. To assess the models, we used several metrics, including Dice coefficient (DICE), Intersection over Union (IoU), accuracy, precision, training and validation losses. According to our results, UNet++ demonstrated the highest IoU score of 0.6719, and a DICE value of 0.7869, showing superior results in terms of segmentation, specifically when configured with an image size of 300x300 and a batch size of 16. In addition, we also explored the effect of image resolutions and batch sizes on model performance and accuracy under different architectures. Therefore, this study provides insights into the strengths of different segmentation models and the potential of deep learning-based semantic segmentation methods for improving automated dental radiograph analysis.
Abstract:Accurate and efficient analysis of dental radiographs has become increasingly important for disease diagnosis and clinical decision making. In particular, dental radiographs segmentation plays a critical role as it is challenging due to several reasons, such as low contrast, noise in the images, variations in the image quality, etc. Previous studies have primarily addressed these challenges using convolutional neural networks (CNN)-based models. However, direct comparison of these segmentation models is still challenging due to the variations among the experimental settings. Therefore, we mainly compared four segmentation models, including Pyramid Scene Parsing Network (PSPNet), DeepLabV3, UNet, and UNet++, through a fair, controlled experimentation setting under varying conditions such as image sizes and batch sizes. For this, we used 1269 dental radiography images, and prior to training, we implemented a series of preprocessing techniques. To assess the models, we used several metrics, including Dice coefficient (DICE), Intersection over Union (IoU), accuracy, precision, training and validation losses. According to our results, UNet++ demonstrated the highest IoU score of 0.6719, and a DICE value of 0.7869, showing superior results in terms of segmentation, specifically when configured with an image size of 300x300 and a batch size of 16. In addition, we also explored the effect of image resolutions and batch sizes on model performance and accuracy under different architectures. Therefore, this study provides insights into the strengths of different segmentation models and the potential of deep learning-based semantic segmentation methods for improving automated dental radiograph analysis.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2610.15061 [cs.CV]
(or arXiv:2610.15061v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.15061 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 342 words
Related coverage
Segmentation of Bovid Dentition Under Imperfect Annotations: A Comparative Study of Convolutional and Attention Models
arXiv · Sep 1, 2026
Automated Dental Caries Segmentation in Panoramic Radiographs Using Dual-Stage Deep Learning
arXiv · Sep 17, 2026
SafeLand: Safe Autonomous Landing in Unknown Environments with Bayesian Semantic Mapping
arXiv · Aug 6, 2026
[AINews] not much happened today
Latent Space · Sep 10, 2026