首页|Peking University School and Hospital of Stomatology Reports Findings in Artific ial Intelligence (Digital pathology-based artificial intelligence models for dif ferential diagnosis and prognosis of sporadic odontogenic keratocysts)
Peking University School and Hospital of Stomatology Reports Findings in Artific ial Intelligence (Digital pathology-based artificial intelligence models for dif ferential diagnosis and prognosis of sporadic odontogenic keratocysts)
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 Beiji ng, People's Republic of China, by NewsRx correspondents, research stated, "Odon togenic keratocyst (OKC) is a common jaw cyst with a high recurrence rate. OKC c ombined with basal cell carcinoma as well as skeletal and other developmental ab normalities is thought to be associated with Gorlin syndrome." Our news editors obtained a quote from the research from the Peking University S chool and Hospital of Stomatology, "Moreover, OKC needs to be differentiated fro m orthokeratinized odontogenic cyst and other jaw cysts. Because of the differen t prognosis, differential diagnosis of several cysts can contribute to clinical management. We collected 519 cases, comprising a total of 2 157 hematoxylin and eosin-stained images, to develop digital pathology-based artificial intelligence (AI) models for the diagnosis and prognosis of OKC. The Inception_ v3 neural network was utilized to train and test models developed from patch-lev el images. Finally, whole slide image-level AI models were developed by integrat ing deep learning-generated pathology features with several machine learning alg orithms. The AI models showed great performance in the diagnosis (AUC = 0.935, 9 5% CI: 0.898-0.973) and prognosis (AUC = 0.840, 95%CI : 0.751-0.930) of OKC. The advantages of multiple slides model for integrating o f histopathological information are demonstrated through a comparison with the s ingle slide model. Furthermore, the study investigates the correlation between A I features generated by deep learning and pathological findings, highlighting th e interpretative potential of AI models in the pathology. Here, we have develope d the robust diagnostic and prognostic models for OKC."
BeijingPeople's Republic of ChinaAsi aArtificial IntelligenceDiagnostics and ScreeningEmerging TechnologiesHe alth and MedicineMachine LearningPathology
NETL
NSTL
