Development and evaluation of AI model with deep learning for segmentation of extraocular muscles in thyroid eye disease.
Authors
Affiliations (4)
Affiliations (4)
- Department of Ophthalmology and Visual Sciences, Graduate School of Medicine, Osaka Metropolitan University, Abeno-ku, Osaka-shi, Osaka-fu, Japan.
- Department of Medical Device Engineering, Graduate School of Medicine, Kobe University, Chuo-ku, Kobe-shi, Hyogo Prefecture, Japan.
- Departments of Radiology, Graduate School of Medicine, Kobe University, Chuo-ku, Kobe-shi, Hyogo Prefecture, Japan.
- Department of Ophthalmology & Visual Sciences, Washington University School of Medicine, St. Louis, Missouri, United States of America.
Abstract
To develop and evaluate an AI model for the segmentation of extraocular muscles (EOMs) using Magnetic Resonance Imaging (MRI). Single-center study with retrospective study. The study included 52 patients with thyroid eye disease (TED) who underwent MRI examination of the orbital region at the Department of Ophthalmology, Osaka Metropolitan University, between October 2020 and June 2023. Manual labelling of all EOMs was performed on all slices. An AI model was created and compared with the manually labelled data using 5-fold cross validation on data sets of 12, 32, and 52 cases. The average signal intensity ratio (SIR) within the EOMs was measured. The primary outcome was the comparison of DICE similarity coefficients (DSC) as the agreement rate between AI's result and manual labelling amongst the three data sets (52 cases vs 32 cases vs 12 cases). The secondary outcome was the correlation of SIR between the AI and manual labelling. A significant difference in DSC was observed between the 12-, 32-, and 52-case data sets for the inferior rectus muscle and medial rectus muscle. A significant correlation was observed between the AI and manual labelling for SIR in all EOMs. An AI model was successfully developed for the automatic segmentation of EOMs. There was little measurement error between AI and manual labelling, and the AI model using 52 cases had improved measurement accuracy compared to the AI models using 32 and 12 cases.