首页|University Hospital RWTH Aachen Reports Findings in Artificial Intelligence (Ins ights into Predicting Tooth Extraction from Panoramic Dental Images: Artificial Intelligence vs. Dentists)
University Hospital RWTH Aachen Reports Findings in Artificial Intelligence (Ins ights into Predicting Tooth Extraction from Panoramic Dental Images: Artificial Intelligence vs. Dentists)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Artificial Intelligenc e is the subject of a report. According to news reporting originating from Aache n, Germany, by NewsRx correspondents, research stated, “Tooth extraction is one of the most frequently performed medical procedures. The indication is based on the combination of clinical and radiological examination and individual patient parameters and should be made with great care.” Financial support for this research came from Universitatsklinikum RWTH Aachen. Our news editors obtained a quote from the research from University Hospital RWT H Aachen, “However, determining whether a tooth should be extracted is not alway s a straightforward decision. Moreover, visual and cognitive pitfalls in the ana lysis of radiographs may lead to incorrect decisions. Artificial intelligence (A I) could be used as a decision support tool to provide a score of tooth extracta bility. Using 26,956 single teeth images from 1,184 panoramic radiographs (PANs) , we trained a ResNet50 network to classify teeth as either extraction-worthy or preservable. For this purpose, teeth were cropped with different margins from P ANs and annotated. The usefulness of the AI-based classification as well that of dentists was evaluated on a test dataset. In addition, the explainability of th e best AI model was visualized via a class activation mapping using CAMERAS. The ROC-AUC for the best AI model to discriminate teeth worthy of preservation was 0.901 with 2% margin on dental images. In contrast, the average RO C-AUC for dentists was only 0.797. With a 19.1% tooth extractions prevalence, the AI model’s PR-AUC was 0.749, while the dentist evaluation only r eached 0.589. AI models outperform dentists/specialists in predicting tooth extr action based solely on X-ray images, while the AI performance improves with incr easing contextual information.”
AachenGermanyEuropeArtificial Inte lligenceDentistryEmerging TechnologiesHealth and MedicineMachine Learnin g
NETL
NSTL
