Collaborative deep learning model for tooth segmentation and identification using panoramic radiographs
Collaborative deep learning model for tooth segmentation and identification using panoramic radiographs
复制标题
基于全景X线片的牙齿分割与识别协同深度学习模型
DOI：
10.1016/j.compbiomed.2022.105829
复制
发表时间：
2022-07-19
影响因子：
7.7
通讯作者：
Lee, Yugyung
中科院分区：
文献类型：
--
作者：
Chandrashekar, Geetha;AlQarni, Saeed;Lee, Yugyung
全景X光片是有效的牙科治疗计划的组成部分，支持牙科医生识别阻生牙、感染、恶性肿瘤和其他牙科问题。然而，仅仅根据牙医的评估进行异常筛查可能会导致诊断不一致，给制定成功的治疗计划带来困难。基于深度学习的分割和目标检测算法的最新进展使得能够提供可预测的和实用的识别来帮助评估患者的矿化口腔健康，使牙医能够构建更成功的治疗计划。然而，缺乏开发通过利用个别模型来提高学习绩效的协作模型的努力。文章描述了一种新的技术，通过结合牙齿分割和识别模型来实现协作学习，这些模型独立于全景X光片创建。这种协作技术允许聚合牙齿分割和识别，通过识别和编号现有牙齿(最多32颗牙齿)来产生增强的结果。实验结果表明，对于牙齿分割和识别，所提出的协作模型明显比单独学习模型更有效(例如，对于牙齿分割和识别，分别为98.77%比96%和98.44%比91%)。此外，我们的模型优于最先进的分割和识别研究。我们展示了协作学习在各种复杂情况下检测和分割牙齿的有效性，包括健康的牙列、缺失的牙齿、正在进行的正畸治疗以及种植牙齿的牙齿。
Panoramic radiographs are an integral part of effective dental treatment planning, supporting dentists in iden-tifying impacted teeth, infections, malignancies, and other dental issues. However, screening for anomalies solely based on a dentist's assessment may result in diagnostic inconsistency, posing difficulties in developing a suc-cessful treatment plan. Recent advancements in deep learning-based segmentation and object detection algo-rithms have enabled the provision of predictable and practical identification to assist in the evaluation of a patient's mineralized oral health, enabling dentists to construct a more successful treatment plan. However, there has been a lack of efforts to develop collaborative models that enhance learning performance by leveraging individual models. The article describes a novel technique for enabling collaborative learning by incorporating tooth segmentation and identification models created independently from panoramic radiographs. This collab-orative technique permits the aggregation of tooth segmentation and identification to produce enhanced results by recognizing and numbering existing teeth (up to 32 teeth). The experimental findings indicate that the proposed collaborative model is significantly more effective than individual learning models (e.g., 98.77% vs. 96% and 98.44% vs.91% for tooth segmentation and recognition, respectively). Additionally, our models outperform the state-of-the-art segmentation and identification research. We demonstrated the effectiveness of collaborative learning in detecting and segmenting teeth in a variety of complex situations, including healthy dentition, missing teeth, orthodontic treatment in progress, and dentition with dental implants.