An enhanced tooth segmentation and numbering according to FDI notation in bitewing radiographs.

Buse Yaren Tekin, Caner Ozcan, Adem Pekince, Yasin Yasa

July 2022

Synopsis of Social media discussions

The discussions emphasize the technical strengths of the system, mentioning elements like annotated radiographs and performance metrics, with phrases like '97% mAP' and 'automated segmentation' indicating a focus on precision and efficiency. Words such as 'enhanced' and 'improving' reveal a positive tone about technological advancement, while references to practical applications suggest recognition of its potential impact.

A
Agreement
 Moderate agreement

Most discussions recognize the accuracy and significance of the deep learning method, with references to high performance metrics like 97% mAP, indicating general support for the research findings.

I
Interest
 High level of interest

Posts show high interest by highlighting technical details such as annotation processes, training data, and performance metrics, suggesting engagement with the methodology.

E
Engagement
 High engagement

Discussions include mentions of specific techniques like Mask R-CNN and implications for dental diagnostics, reflecting active engagement and consideration of the tool’s applications.

I
Impact
 Moderate level of impact

Users suggest that this system could improve diagnostic speed and accuracy, implying it could have a meaningful impact on dental practice, though some see it as an incremental improvement rather than transformative.

Social Mentions

YouTube

2 Videos

Twitter

3 Posts

Metrics

Video Views

39

Total Likes

4

Extended Reach

547

Social Features

5

Timeline: Posts about article

Top Social Media Posts

Posts referencing the article

Advanced Deep Learning for Precise Tooth Segmentation and Numbering in Dental X-rays

Advanced Deep Learning for Precise Tooth Segmentation and Numbering in Dental X-rays

This study develops a deep learning system using Mask R-CNN to automatically segment and number teeth in bitewing radiographs based on FDI notation. The system achieves high accuracy, supporting dental diagnostics by automating tooth identification and labeling.

DentalAI

October 25, 2025

32 views

Advanced Tooth Segmentation and Numbering Using Mask R-CNN in Dental Radiographs

Advanced Tooth Segmentation and Numbering Using Mask R-CNN in Dental Radiographs

This 2022 study from Turkish universities introduces a Mask R-CNN based system for automatic tooth segmentation and numbering on bitewing radiographs using FDI notation. It achieved high accuracy, supporting efficient dental analysis and diagnosis.

DentalAI

October 25, 2025

8 views

  • Nielsen Pereira
    @nielsantper (Twitter)

    RT @Dentalai_pt: A total of 1,200 bitewing X-rays were annotated by oral radiologists and divided into 1,000 for training and 200 for testi…
    view full post

    October 25, 2025

    1

  • Dental AI
    @Dentalai_pt (Twitter)

    A total of 1,200 bitewing X-rays were annotated by oral radiologists and divided into 1,000 for training and 200 for testing. 97% mAP in FDI-based tooth segmentation on bitewing X-rays using Mask R-CNN. Watch on YT: https://t.co/3X3GbBnKK4
    view full post

    October 25, 2025

    2

    1

  • Tim Leiner
    @MLandDL_papers (Twitter)

    An enhanced tooth segmentation and numbering according to FDI notation in bitewing radiographs https://t.co/U7tVEFDtJK
    view full post

    May 14, 2022

Abstract Synopsis

  • The study develops a deep learning system, specifically using Mask R-CNN, to automatically segment and number teeth in bitewing radiographs based on FDI notation, aiming to make dental analysis faster and less labor-intensive for experts.
  • The system accurately segments individual teeth, assigns correct numbers, and achieves high performance metrics, including 100% precision and a 97.49% mean Average Precision (mAP), demonstrating its effectiveness compared to other methods.
  • This approach aids dentists by automating the identification and labeling of teeth in radiographs, improving diagnostic efficiency for detecting issues like caries and restorations that are hard to see directly in the mouth.]