医学
视神经病变
医学诊断
放射科
人工智能
深度学习
外科
核医学
眼科
视神经
计算机科学
作者
Lisa Y. Lin,Paul Zhou,Min Shi,Jonathan E. Lu,Soomin Jeon,Doyun Kim,J. Liu,Mengyu Wang,Synho Do,Grace Lee
标识
DOI:10.1016/j.xops.2023.100412
摘要
PurposeThyroid eye disease (TED) is an autoimmune condition with an array of clinical manifestations, which can be complicated by compressive optic neuropathy. It is important to identify patients with TED early to ensure close monitoring and treatment to prevent potential permanent disability or vision loss. Deep learning artificial intelligence (AI) algorithms have been utilized in ophthalmology and in other fields of medicine to detect disease. This study aims to introduce a deep learning model to evaluate orbital computed tomography (CT) images for the presence of TED and potential compressive optic neuropathy.DesignRetrospective review and deep learning algorithm modelingSubjects: Patients with TED with dedicated orbital CT scans and with an examination by an oculoplastic surgeon over a 10- year period at a single academic institution was performed. Patients with no TED and normal CTs were used as normal controls. Those with other diagnoses, such as tumors or other inflammatory processes were excluded.MethodsOrbital CTs were preprocessed and adopted for the VGG-16 network to distinguish patients with no TED, mild TED, and severe TED with compressive optic neuropathy. The primary model included training and testing of all three conditions. Binary model performance was also evaluated. An oculoplastic surgeon was also similarly tested with single image and serial images for comparison.Main Outcome MeasuresAccuracy of deep learning model discernment of region of interest for CT scans to distinguish TED versus normal control, as well as TED with clinical signs of optic neuropathy.ResultsA total of 1,187 photos from 141 patients were used to develop the AI model. The primary model trained on patients with no TED, mild TED, and severe TED had a 89.5% accuracy (AUC ranged from 0.96 to 0.99) in distinguishing patients with these clinical categories. In comparison, testing of an oculoplastic surgeon in these three categories showed decreased accuracy (70.0% accuracy in serial image testing).ConclusionThe deep learning model developed in the study can accurately detect TED and further detect TED with clinical signs of optic neuropathy based on orbital CT. The model proved superior compared to human expert grading. With further optimization and validation, this TED deep learning model could help guide frontline healthcare providers in the detection of TED and help stratify the urgency of a referral to an oculoplastic surgeon and endocrinologist.
科研通智能强力驱动
Strongly Powered by AbleSci AI