使用深度学习在全景射线图上检测状腺斑块
Shankeeth Vinayahalingam1, Niels van Nistelrooij1, Tong Xi2
1Charité - Universitätsmedizin Berlin, Department of Oral and Maxillofacial Surgery, Corporate Member of Freie Universität Berlin and Humboldt Universität zu Berlin, Augustenburger Platz 1, Berlin 13353, Germany; Department of Oral and Maxillofacial Surgery, Radboud University Medical Center, P.O. Box 9101, Nijmegen 6500 HB, the Netherlands.
Journal of dentistry
|October 26, 2024
概括
使用视觉变压器的人工智能 (AI) 模型在全景放射图 (PRs) 上有效检测出动脉化 (CAC). 这种人工智能方法与现有方法相比,表现出更高的性能,有助于早期诊断动脉样硬化.
科学领域:
- 医疗成像中的人工智能
- 口腔和面放射学 口腔和面放射学
- 进行心血管疾病查.
背景情况:
- 全景射线图 (PRs) 偶尔会在3-15%的患者中检测出动脉化 (CAC).
- 牙科专业人员由于有限的培训,经常错过CAC诊断.
- 早期发现CAC对于管理动脉动脉样硬化至关重要.
研究的目的:
- 开发和验证人工智能 (AI) 模型,用于检测PRs上的CAC.
- 利用基于视觉变压器的AI方法来提高诊断准确度.
- 将AI模型的性能与现有的卷积神经网络 (CNN) 模型进行比较.
主要方法:
- 在6404个PR上使用Faster R-CNN和Swin Transformer训练了一个AI模型.
- 在 185 个带有 CAC 的 PR 和 185 个没有 CAC 的 PR 上手动注释 CAC.
- 使用精度,F1分数,回忆,AUC和AP评估模型性能,与基于CNN的AI进行比较.
主要成果:
- 更快的R-CNN和Swin变压器模型实现了高性能:精度为0.895,回调为0.881,F1得分为0.888,AUC为0.950,AP为0.942.
- 开发的AI模型显著超过了之前报道的基于CNN的AI方法.
- 该模型证明了PRs上的CAC的检测性能得到了改进.
结论:
- 这种新型的人工智能模型显示了对CAC在PRs上的增强检测能力.
- 将这种AI工具集成到牙科成像中可以帮助专业人员识别CAC.
- 这项技术有可能改善早期检测和临床管理动脉动脉样硬化.
相关概念视频
Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
3
Calcium-Scoring CT ScanA calcium-scoring CT scan, also known as coronary artery calcium (CAC) scan, detects calcium deposits in the coronary arteries. This test assesses the risk of coronary artery disease (CAD), which can lead to cardiovascular events such as angina, heart failure, and sudden cardiac arrest.A calcium-scoring CT scan is generally recommended for individuals at intermediate risk of CAD without symptoms. It includes:Men aged 40-75 and women aged 50-75: Especially those with a...
3
Imaging Studies for Cardiovascular System V: CT
3
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
3


