Comparison of Faster R-CNN, YOLO, and SSD for Third Molar Angle Detection in Dental Panoramic X-rays
Sensors · 19.09.2024 · 24 (18) · 6053
DOI: 10.3390/s24186053 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Sensors, online erschienen am 19.09.2024. Verfasst von Piero Vilcapoma und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Engineering, Universidad Andres Bello, Santiago 7500735, Chile. Hauptthemen laut MEDLINE: Radiography, Panoramic, Molar, Third, Neural Networks, Computer, Deep Learning. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Nacional de Investigación y Desarrollo, National Research and Development Agency of Chile (ANID), Energy Transformation Center, Faculty of Engineering, Universidad Andres Bello.
Abstract (Originalsprache)
The use of artificial intelligence algorithms (AI) has gained importance for dental applications in recent years. Analyzing AI information from different sensor data such as images or panoramic radiographs (panoramic X-rays) can help to improve medical decisions and achieve early diagnosis of different dental pathologies. In particular, the use of deep learning (DL) techniques based on convolutional neural networks (CNNs) has obtained promising results in dental applications based on images, in which approaches based on classification, detection, and segmentation are being studied with growing interest. However, there are still several challenges to be tackled, such as the data quality and quantity, the variability among categories, and the analysis of the possible bias and variance associated with each dataset distribution. This study aims to compare the performance of three deep learning object detection models—Faster R-CNN, YOLO V2, and SSD—using different ResNet architectures (ResNet-18, ResNet-50, and ResNet-101) as feature extractors for detecting and classifying third molar angles in panoramic X-rays according to Winter’s classification criterion. Each object detection architecture was trained, calibrated, validated, and tested with three different feature extraction CNNs which are ResNet-18, ResNet-50, and ResNet-101, which were the networks that best fit our dataset distribution. Based on such detection networks, we detect four different categories of angles in third molars using panoramic X-rays by using Winter’s classification criterion. This criterion characterizes the third molar’s position relative to the second molar’s longitudinal axis. The detected categories for the third molars are distoangular, vertical, mesioangular, and horizontal. For training, we used a total of 644 panoramic X-rays. The results obtained in the testing dataset reached up to 99% mean average accuracy performance, demonstrating the YOLOV2 obtained higher effectiveness in solving the third molar angle detection problem. These results demonstrate that the use of CNNs for object detection in panoramic radiographs represents a promising solution in dental applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Engineering, Universidad Andres Bello, Santiago 7500735, Chile.
- Faculty of Dentistry, Universidad de las Américas, Quito 170513, Ecuador.
- Laboratorio de Odontología Traslacional, Facultad de Odontología, UNAB, Santiago 7591538, Chile.
- Centro de Biotecnología Daniel Alkalay Lowitt, Universidad Técnica Federico Santa María, Valparaiso 2390136, Chile.
- Energy Transformation Center, Faculty of Engineering, Universidad Andres Bello, Santiago 7500971, Chile.
ORCID-Profile: Piero Vilcapoma, Diana Parra Meléndez, Alejandra Fernández, Ingrid Nicole Vásconez, Nicolás Corona Hillmann, Gustavo Gatica, Juan Pablo Vásconez
Förderung
- Agencia Nacional de Investigación y Desarrollo
- National Research and Development Agency of Chile (ANID)
- Energy Transformation Center, Faculty of Engineering, Universidad Andres Bello
Zitieren
APA
Vilcapoma, P., Parra Meléndez, D., Fernández, A., Vásconez, I. N., Hillmann, N. C., Gatica, G., & Vásconez, J. P. (2024). Comparison of Faster R-CNN, YOLO, and SSD for Third Molar Angle Detection in Dental Panoramic X-rays. Sensors, 24(18), 6053. https://doi.org/10.3390/s24186053
Vancouver
Vilcapoma P, Parra Meléndez D, Fernández A, Vásconez IN, Hillmann NC, Gatica G, et al. Comparison of Faster R-CNN, YOLO, and SSD for Third Molar Angle Detection in Dental Panoramic X-rays. Sensors. 2024;24(18):6053. doi:10.3390/s24186053
BibTeX
@article{Vilcapoma2024,
author = {Vilcapoma, Piero and Parra Meléndez, Diana and Fernández, Alejandra and Vásconez, Ingrid Nicole and Hillmann, Nicolás Corona and Gatica, Gustavo and Vásconez, Juan Pablo},
title = {Comparison of Faster R-CNN, YOLO, and SSD for Third Molar Angle Detection in Dental Panoramic X-rays},
journal = {Sensors},
year = {2024},
volume = {24},
number = {18},
pages = {6053},
doi = {10.3390/s24186053}
}
EUVIMED