Deep-Learning Based Automated Segmentation and Quantitative Volumetric Analysis of Orbital Muscle and Fat for Diagnosis of Thyroid Eye Disease and Associated Optic Neuropathy

Abstract

Purpose : Thyroid eye disease (TED) is characterized by proliferation of orbital tissues and can be complicated by compressive optic neuropathy (CON). This study aims to utilize deep-learning (DL)-based automated segmentation model to segment orbital muscle and fat volumes on computed tomography (CT) images and provide quantitative volumetric data. Additionally, this study aims to develop a machine learning (ML)- based classification model to distinguish patients with TED and TED with CON.

Methods : Subjects with TED who underwent clinical evaluation and orbital CT imaging were included. Patients with clinical features of CON were classified as severe TED, and those without were mild TED. Normal patients were used for controls. A U-Net DL- model was used for automatic segmentation of orbital muscle and fat volumes from orbital CTs. Quantitative volumetric analysis of orbital muscle and fat were performed. ML-based classification models utilizing volumetric data and patient metadata were performed to distinguish normal, mild TED, and severe TED.

Results : Two-hundred and eight one subjects were included. Automatic segmentation of orbital tissues was performed and muscle volumes between normal, mild, and severe TED were found to be statistically different. A classification model utilizing volume data and limited patient data had an accuracy of 0.838 and an AUC of 0.929 in predicting normal, mild TED, and severe TED.

Conclusions : DL-based automated segmentation of orbital images for TED patients was found to be accurate and efficient. A ML-based classification model using volumetrics and metadata led to high diagnostic accuracy in distinguishing TED and TED with CON. By enabling rapid and precise volumetric assessment, this may be a useful tool in future clinical studies.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.