Evaluation of Deep Learning for Caries Detection With Fine-Grained Classification and Postprocessing Improvements

TL;DR

This paper improves deep learning methods for detecting dental caries by using advanced models and postprocessing techniques to classify caries more precisely.

Contribution

The study introduces two correction methods for deep learning models to enhance caries detection accuracy and robustness using fine-grained classification.

Findings

The proposed correction methods improved mAP scores by up to 4.7% across three deep learning models.

Precision and recall increased by 3.8% and 5.6%, respectively, with moderate caries detection showing the most improvement.

The highest mAP score of 72.9% was achieved using the YOLO-v8 model.

Abstract

Deep learning methods have been proven to be effective in detecting dental caries in visible light images. However, existing research involves inadequate categories and mainly focuses on local lesion areas. This study aims to use advanced deep learning models to achieve caries detection based on tooth instances (where all teeth in images are detected) and fine-grained classification according to the International Caries Detection and Assessment System (ICDAS). To address the potential instability under complex scenarios, we propose 2 correction methods that incorporate background knowledge.

A total of 1200 selected high-quality intraoral images were expanded to 8,754 images using data augmentation techniques, and each tooth inside was annotated. Three advanced models, YOLO-v8, YOLO-v9, and YOLO-NAS, were trained and tested on the dataset. In the stage of postprocessing, predicted categories were corrected with a weighted average of scores, and confidence scores were adaptively adjusted based on the spatial relationships of teeth.

The proposed methods improved the mean Average Precision (mAP) scores by 4.7% (p < .01/Mann-Whitney-U-test), 2.8% (p < .01), and 4.4% (p < .01) across the 3 models, with the highest score of 72.9% on YOLO-v8. Precision and recall increased by 3.8% and 5.6%, respectively, while FPS decreased from 83.1 to 78.1. Especially improved the scores for moderate caries and demonstrated greater robustness.

The primary objectives were achieved, and the 2 proposed correction methods bring an effective improvement to the existing algorithm framework. It’s expected to promote the application of artificial intelligence and inspire further research.

This research is of clinical value due to its functional innovation: the finer classification should assist dentists formulate personalized treatment strategies. Focusing on the detailed evaluation of each tooth should help deliver better and personalised clinical care.

Figures