Learning Cephalometric Landmarks for Diagnostic Features Using Regression Trees

Suhail, Sameera; Harris, Kayla; Sinha, Gaurav; Schmidt, Maayan; Durgekar, Sujala; Mehta, Shivam; Upadhyay, Madhur

doi:10.3390/bioengineering9110617

Open AccessArticle

Learning Cephalometric Landmarks for Diagnostic Features Using Regression Trees

by

Sameera Suhail

¹,

Kayla Harris

²,

Gaurav Sinha

³,

Maayan Schmidt

⁴,

Sujala Durgekar

⁵,

Shivam Mehta

⁶

and

Madhur Upadhyay

^7,*

¹

Department of Engineering Technologies, Swinburne University of Technology, Hawthorn, VIC 3122, Australia

²

Private Practice, Lakewood, CO 80226, USA

³

Departments of Computer Science & Statistics, University of British Columbia (Alumni), Vancouver, BC V6T1Z4, Canada

⁴

School of Dental Medicine, University of Connecticut Health, Farmington, CT 06030, USA

⁵

Department of Orthodontics, KLES’ Institute of Dental Sciences, Bangalore 560022, India

⁶

Department of Developmental Sciences/Orthodontics, Marquette University, Milwaukee, WI 53202, USA

⁷

Division of Orthodontics, University of Connecticut Health, Farmington, CT 06030, USA

^*

Author to whom correspondence should be addressed.

Bioengineering 2022, 9(11), 617; https://doi.org/10.3390/bioengineering9110617

Submission received: 27 September 2022 / Revised: 14 October 2022 / Accepted: 22 October 2022 / Published: 27 October 2022

(This article belongs to the Special Issue Advances in Appliance Design and Techniques in Orthodontics)

Download

Browse Figures

Review Reports Versions Notes

Abstract

Lateral cephalograms provide important information regarding dental, skeletal, and soft-tissue parameters that are critical for orthodontic diagnosis and treatment planning. Several machine learning methods have previously been used for the automated localization of diagnostically relevant landmarks on lateral cephalograms. In this study, we applied an ensemble of regression trees to solve this problem. We found that despite the limited size of manually labeled images, we can improve the performance of landmark detection by augmenting the training set using a battery of simple image transforms. We further demonstrated the calculation of second-order features encoding the relative locations of landmarks, which are diagnostically more important than individual landmarks.

Keywords: cephalograms; anatomical landmarks; machine learning; regression trees; orthodontics

Share and Cite

MDPI and ACS Style

Suhail, S.; Harris, K.; Sinha, G.; Schmidt, M.; Durgekar, S.; Mehta, S.; Upadhyay, M. Learning Cephalometric Landmarks for Diagnostic Features Using Regression Trees. Bioengineering 2022, 9, 617. https://doi.org/10.3390/bioengineering9110617

AMA Style

Suhail S, Harris K, Sinha G, Schmidt M, Durgekar S, Mehta S, Upadhyay M. Learning Cephalometric Landmarks for Diagnostic Features Using Regression Trees. Bioengineering. 2022; 9(11):617. https://doi.org/10.3390/bioengineering9110617

Chicago/Turabian Style

Suhail, Sameera, Kayla Harris, Gaurav Sinha, Maayan Schmidt, Sujala Durgekar, Shivam Mehta, and Madhur Upadhyay. 2022. "Learning Cephalometric Landmarks for Diagnostic Features Using Regression Trees" Bioengineering 9, no. 11: 617. https://doi.org/10.3390/bioengineering9110617

APA Style

Suhail, S., Harris, K., Sinha, G., Schmidt, M., Durgekar, S., Mehta, S., & Upadhyay, M. (2022). Learning Cephalometric Landmarks for Diagnostic Features Using Regression Trees. Bioengineering, 9(11), 617. https://doi.org/10.3390/bioengineering9110617

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Learning Cephalometric Landmarks for Diagnostic Features Using Regression Trees

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI