{"title":"基于深度学习的全景 X 光片牙齿撞击检测。","authors":"He Zhicheng, Wang Yipeng, Li Xiao","doi":"10.1177/11795972241288319","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>The aim is to detect impacted teeth in panoramic radiology by refining the pretrained MedSAM model.</p><p><strong>Study design: </strong>Impacted teeth are dental issues that can cause complications and are diagnosed via radiographs. We modified SAM model for individual tooth segmentation using 1016 X-ray images. The dataset was split into training, validation, and testing sets, with a ratio of 16:3:1. We enhanced the SAM model to automatically detect impacted teeth by focusing on the tooth's center for more accurate results.</p><p><strong>Results: </strong>With 200 epochs, batch size equals to 1, and a learning rate of 0.001, random images trained the model. Results on the test set showcased performance up to an accuracy of 86.73%, F1-score of 0.5350, and IoU of 0.3652 on SAM-related models.</p><p><strong>Conclusion: </strong>This study fine-tunes MedSAM for impacted tooth segmentation in X-ray images, aiding dental diagnoses. Further improvements on model accuracy and selection are essential for enhancing dental practitioners' diagnostic capabilities.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":null,"pages":null},"PeriodicalIF":2.3000,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11456186/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep Learning-Based Detection of Impacted Teeth on Panoramic Radiographs.\",\"authors\":\"He Zhicheng, Wang Yipeng, Li Xiao\",\"doi\":\"10.1177/11795972241288319\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>The aim is to detect impacted teeth in panoramic radiology by refining the pretrained MedSAM model.</p><p><strong>Study design: </strong>Impacted teeth are dental issues that can cause complications and are diagnosed via radiographs. We modified SAM model for individual tooth segmentation using 1016 X-ray images. The dataset was split into training, validation, and testing sets, with a ratio of 16:3:1. We enhanced the SAM model to automatically detect impacted teeth by focusing on the tooth's center for more accurate results.</p><p><strong>Results: </strong>With 200 epochs, batch size equals to 1, and a learning rate of 0.001, random images trained the model. Results on the test set showcased performance up to an accuracy of 86.73%, F1-score of 0.5350, and IoU of 0.3652 on SAM-related models.</p><p><strong>Conclusion: </strong>This study fine-tunes MedSAM for impacted tooth segmentation in X-ray images, aiding dental diagnoses. Further improvements on model accuracy and selection are essential for enhancing dental practitioners' diagnostic capabilities.</p>\",\"PeriodicalId\":42484,\"journal\":{\"name\":\"Biomedical Engineering and Computational Biology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2024-10-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11456186/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biomedical Engineering and Computational Biology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1177/11795972241288319\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomedical Engineering and Computational Biology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/11795972241288319","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0
摘要
研究目的研究设计:研究设计:撞击牙是一种可引起并发症的牙科问题,可通过 X 光片进行诊断。我们利用 1016 张 X 光图像修改了用于单个牙齿分割的 SAM 模型。数据集分为训练集、验证集和测试集,比例为 16:3:1。我们对 SAM 模型进行了改进,通过聚焦牙齿中心来自动检测撞击牙齿,从而获得更准确的结果:在 200 个历元、批量大小等于 1 和学习率为 0.001 的条件下,随机图像对模型进行了训练。测试集的结果显示,SAM 相关模型的准确率高达 86.73%,F1 分数为 0.5350,IoU 为 0.3652:本研究对 MedSAM 进行了微调,用于 X 射线图像中的撞击牙分割,为牙科诊断提供了帮助。要提高牙科医生的诊断能力,进一步提高模型的准确性和选择至关重要。
Deep Learning-Based Detection of Impacted Teeth on Panoramic Radiographs.
Objective: The aim is to detect impacted teeth in panoramic radiology by refining the pretrained MedSAM model.
Study design: Impacted teeth are dental issues that can cause complications and are diagnosed via radiographs. We modified SAM model for individual tooth segmentation using 1016 X-ray images. The dataset was split into training, validation, and testing sets, with a ratio of 16:3:1. We enhanced the SAM model to automatically detect impacted teeth by focusing on the tooth's center for more accurate results.
Results: With 200 epochs, batch size equals to 1, and a learning rate of 0.001, random images trained the model. Results on the test set showcased performance up to an accuracy of 86.73%, F1-score of 0.5350, and IoU of 0.3652 on SAM-related models.
Conclusion: This study fine-tunes MedSAM for impacted tooth segmentation in X-ray images, aiding dental diagnoses. Further improvements on model accuracy and selection are essential for enhancing dental practitioners' diagnostic capabilities.