Repository for UFBA-425 and OralBBNet

This repository contains the implementation related to the pipelines of UFBA-425 dataset and the paper OralBBNet: Spatially Guided Dental Segmentation of Panoramic X-Rays with Bounding Box Priors.

• UFBA-425 Dataset used in this study are avaiable at FigShare

• 🔥 UFBA-425 Dataset featured in Roboflow100-VL Benchmark for the year of 2025 and referred UFBA-425 as one of the hardest datasets for vision tasks. Find the paper here.

Dataset

• We introduce a set of 425 panoramic X-rays with Human annotated Bounding Boxes and Polygons, the 425 images are a subset of UFBA-UESC Dental Dataset. This dataset can be extensively used for detection and segmentation tasks for Dental Panoramic X-rays. Refer to Description for understanding the organisation of training and evaluation data. The Distribution of Categories in the dataset are metnioned in the table below.

Category	32 Teeth	Restoration	Dental Appliance	Images	Used Images
1	✓	✓	✓	73	24
2	✓	✓		220	72
3	✓			45	15
4	✓			140	32
5	Images containing dental implant			120	37
6	Images containing more than 32 teeth			170	30
7		✓	✓	115	33
8		✓		457	140
9			✓	45	7
10				115	35
Total				1500	425

Results

• Teeth Numbering Results

Model Architecture	mAP	AP50
Mask R-CNN	70.5	97.2
PANet	74.0	99.7
HTC	71.1	97.3
ResNeSt	72.1	96.8
YOLOv8	74.9	94.6

• Instance Segmentation Results

Model Architecture	Incisors	Canines	Premolars	Molars
U-Net	73.29	69.92	67.62	64.98
YOLOv8-seg	82.78	81.91	81.89	81.42
SAM-2	87.12	86.21	86.19	85.69
OralBBNet	89.34	88.40	88.38	87.87

• Refer to the paper for further information on model architectures and datasets used for evaluation.

Teeth Numbering Heatmaps

Segmentation Masks

Code Structure

2ddaatagen.ipynb                   => Notebook for generating labels
yolov8_train.ipynb                 => Notebook for training YOLOv8
yolo_test.ipynb                    => Notebook for testing YOLOv8
unet_training.ipynb                => Notebook for training U-Net
unet+cv.ipynb                      => Notebook for training U-Net with cross validation
yolov8+unet_training.ipynb         => Notebook for training OralBBNet
yolov8+unet+cv.ipynb               => Notebook for training OralBBNet with cross validation

Cite Us

If you want to cite the dataset, cite this:

@article{Budagam2025,
author = "Devichand Budagam and Azamat Zhanatuly Imanbayev and Iskander Rafailovich Akhmetov and Aleksandr Sinitca and Sergey Antonov and Dmitrii Kaplun",
title = "{UFBA-425}",
year = "2025",
month = "8",
url = "https://figshare.com/articles/dataset/UFBA-425/29827475",
doi = "10.6084/m9.figshare.29827475.v1"
}

if you want to cite the method OralBBNet, cite this:

@misc{budagam2025oralbbnetspatiallyguideddental,
      title={OralBBNet: Spatially Guided Dental Segmentation of Panoramic X-Rays with Bounding Box Priors}, 
      author={Devichand Budagam and Azamat Zhanatuly Imanbayev and Iskander Rafailovich Akhmetov and Aleksandr Sinitca and Sergey Antonov and Dmitrii Kaplun},
      year={2025},
      eprint={2406.03747},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2406.03747}, 
}