Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Faculty & Research
  • Faculty
  • Research
  • Featured Topics
  • Academic Units
  • …→
  • Harvard Business School→
  • Faculty & Research→
Publications
Publications
  • Article
  • Diagnostics

Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs

By: Michael G. Endres, Florian Hillen, Marios Salloumis, Ahmad R. Sedaghat, Stefan M. Niehues, Olivia Quatela, Henning Hanken, Ralf Smeets, Benedicta Beck-Broichsitter, Carsten Rendenbach, Karim R. Lakhani, Max Helland and Robert A. Gaudin
  • Format:Electronic
ShareBar

Abstract

Periapical radiolucencies, which can be detected on panoramic radiographs, are one of the most common radiographic findings in dentistry and have a differential diagnosis including infections, granuloma, cysts, and tumors. In this study, we seek to investigate the ability with which 24 oral and maxillofacial (OMF) surgeons assess the presence of periapical lucencies on panoramic radiographs, and we compare these findings to the performance of a predictive deep learning algorithm that we have developed using a curated data set of 2,902 de-identified panoramic radiographs. The mean diagnostic positive predictive value (PPV) of OMF surgeons based on their assessment of panoramic radiographic images was 0.69 (±0.13), indicating that dentists on average falsely diagnose 31% of cases as radiolucencies. However, the mean diagnostic true positive rate (TPR) was 0.51 (±0.14), indicating that on average 49% of all radiolucencies were missed. We demonstrate that the deep learning algorithm achieves a better performance than 14 of 24 OMF surgeons within the cohort, exhibiting an average precision of 0.60 (±0.04), and an F1 score of 0.58 (±0.04) corresponding to a PPV of 0.67 (±0.05) and TPR of 0.51 (±0.05). The algorithm, trained on limited data and evaluated on clinically validated ground truth, has potential to assist OMF surgeons in detecting periapical lucencies on panoramic radiographs.

Keywords

Artificial Intelligence; Diagnosis; Computer-assisted; Image Interpretation; Machine Learning; Radiography; Panoramic Radiograph; AI and Machine Learning

Citation

Endres, Michael G., Florian Hillen, Marios Salloumis, Ahmad R. Sedaghat, Stefan M. Niehues, Olivia Quatela, Henning Hanken, Ralf Smeets, Benedicta Beck-Broichsitter, Carsten Rendenbach, Karim R. Lakhani, Max Helland, and Robert A. Gaudin. "Development of a Deep Learning Algorithm for Periapical Disease Detection in Dental Radiographs." Diagnostics 10, no. 6 (June 2020).

Supplemental Information

https://www.mdpi.com/2075-4418/10/6/430
  • Read Now

About The Author

Karim R. Lakhani

Technology and Operations Management
→More Publications

More from the Authors

    • December 2022
    • Faculty Research

    TSG Hoffenheim; Step by Step Analysis in Excel

    By: Feng Zhu, Karim R. Lakhani, Kerry Herman and Sascha L. Schmidt
    • December 2022
    • Faculty Research

    Freelancer, Ltd.

    By: Christopher Stanton, Karim R. Lakhani, Jin Hyun Paik and Nina Cohodes
    • December 2022
    • Faculty Research

    Freelancer, Ltd. Case Supplement

    By: Christopher Stanton, Karim R. Lakhani, Jin Hyun Paik and Nina Cohodes
More from the Authors
  • TSG Hoffenheim; Step by Step Analysis in Excel By: Feng Zhu, Karim R. Lakhani, Kerry Herman and Sascha L. Schmidt
  • Freelancer, Ltd. By: Christopher Stanton, Karim R. Lakhani, Jin Hyun Paik and Nina Cohodes
  • Freelancer, Ltd. Case Supplement By: Christopher Stanton, Karim R. Lakhani, Jin Hyun Paik and Nina Cohodes
ǁ
Campus Map
Harvard Business School
Soldiers Field
Boston, MA 02163
→Map & Directions
→More Contact Information
  • Make a Gift
  • Site Map
  • Jobs
  • Harvard University
  • Trademarks
  • Policies
  • Accessibility
  • Digital Accessibility
Copyright © President & Fellows of Harvard College