Int J Comput Dent. 2024 Oct 15;27(3):225-233. doi: 10.3290/j.ijcd.b4200863.
Artificial intelligence (AI)-based systems are used in dentistry to ensure a more accurate and efficient diagnostic process. The objective of the present study was to evaluate the performance of a deep learning (DL) program for the detection and classification of dental structures and treatments on panoramic radiographs of pediatric patients.
In total, 4821 anonymized digital panoramic radiographs of children between 5 and 13 years of age were analyzed by YOLOv4, a CNN (Convolutional Neural Networks)-based object detection model. The ability to make a correct diagnosis was tested on samples from pediatric patients examined within the scope of the study. All statistical analyses were performed using SPSS version 26.0 software.
The YOLOv4 model diagnosed the primary teeth, permanent tooth germs, and brackets successfully, with high F1 scores of 0.95, 0.90, and 0.76, respectively. Although this model achieved promising results, there were certain limitations for some dental structures and treatments, including fillings, root canal treatments, and supernumerary teeth. The architecture of the present study achieved reliable results, with some specific limitations for detecting dental structures and treatments.
The detection of certain dental structures and previous dental treatments on pediatric panoramic radiographs by using a DL-based approach may provide early diagnosis of some dental anomalies and help dental practitioners to find more accurate treatment options by saving time and effort.
人工智能（AI）系统被用于牙科领域，以确保更准确和高效的诊断过程。本研究的目的是评估一种深度学习（DL）程序在检测和分类儿科患者全景放射片中的牙科结构和治疗方面的性能。
共分析了 4821 名 5 至 13 岁儿童的匿名数字化全景放射图像，使用基于卷积神经网络（CNN）的目标检测模型 YOLOv4。使用研究范围内检查的儿科患者样本测试正确诊断的能力。所有统计分析均使用 SPSS 版本 26.0 软件进行。
YOLOv4 模型成功诊断了乳牙、恒牙胚和托槽，其 F1 分数分别为 0.95、0.90 和 0.76，非常高。尽管该模型取得了有希望的结果，但对于某些牙科结构和治疗方法，包括填充物、根管治疗和多生牙，仍存在一定的局限性。本研究的体系结构取得了可靠的结果，但在检测某些牙科结构和治疗方法方面存在一些特定的局限性。
使用基于深度学习的方法在儿科全景放射片中检测某些牙科结构和先前的牙科治疗方法可能有助于早期诊断某些牙科异常，并通过节省时间和精力，帮助牙科医生找到更准确的治疗方案。
