UFBA-UESC Dental Dataset

Dataset Overview

Dataset Name

• Instance Segmentation and Teeth Classification in Panoramic X‑rays

Source

• This dataset is a subset of the UFBA‑UESC Dental Dataset, containing 425 panoramic X‑rays.

Content

• 425 panoramic X‑ray images, each with manually annotated bounding boxes and polygons.
• Designed for detection and segmentation tasks on dental panoramic radiographs.

Classification

• Images are categorized into multiple classes such as 32 teeth, restorations, dental appliances, etc.

• Detailed class distribution:

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

Usage

• Suitable for training and evaluating models such as Mask R‑CNN, U‑Net, etc.
• Detailed description and annotation organization are available in the Description document.

Results

• Used to evaluate performance on tooth numbering and instance segmentation tasks.

• Example performance metrics:

  • Tooth Numbering:

    Model Architecture	mAP	AP50
    Mask R‑CNN	70.5	97.2
    Mask R‑CNN + FCN	74.1	92.8
    Mask R‑CNN + pointRend	75.3	94.4
    PANet	74.0	99.7
    HTC	71.1	97.3
    ResNeSt	72.1	96.8
    YOLOv8	72.9	94.6

  • Instance Segmentation:

    Model Architecture	Incisors	Canines	Premolars	Molars
    U‑Net	73.29	69.92	67.62	64.98
    Mask R‑CNN	89.56	89.45	88.70	87.55
    U‑Net + Mask R‑CNN	91.55	91.00	90.00	88.58
    BB‑UNet + YOLOv8 (Test 1)	85.81	84.91	84.89	84.40
    BB‑UNet + YOLOv8 (Test 2)	85.71	86.64	86.22	86.03

Citation

• To cite this dataset, use the following BibTeX entry:

  @misc{budagam2024instance,
        title={Instance Segmentation and Teeth Classification in Panoramic X‑rays}, 
        author={Devichand Budagam and Ayush Kumar and Sayan Ghosh and Anuj Shrivastav and Azamat Zhanatuly Imanbayev and Iskander Rafailovich Akhmetov and Dmitrii Kaplun and Sergey Antonov and Artem Rychenkov and Gleb Cyganov and Aleksandr Sinitca},
        year={2024},
        eprint={2406.03747},
        archivePrefix={arXiv},
        primaryClass={cs.CV}
  }