Effective encoder-decoder neural network for segmentation of orbital tissue in computed tomography images of Graves' orbitopathy patients

Neural network-based automated proptosis measurement using computed tomography images for patients with thyroid-associated orbitopathy

The purpose of this study was to evaluate the clinical feasibility and reliability of a neural network (NN)-based automated proptosis measurement system using computed tomography (CT) images. An automated proptosis measurement system was developed using the CT images of 200 eyes from 100 patients diagnosed with thyroid-associated orbitopathy. We compared the proptosis value obtained from the proposed automated system with the values obtained from the Hertel exophthalmometer and manual measurements of CT slices. The average measurement values were 17.77 ± 2.47 mm with the Hertel exophthalmometer, 18.87 ± 2.68 mm with the manual measurement of CT slices, and 19.30 ± 2.76 mm with the proposed automated system. There was no significant difference in the proptosis values measured using the manual and automated NN-based methods (p = 0.241). The values obtained from manual measurement and automated measurement using CT images showed excellent agreement with an intraclass correlation coefficient of 0.95. Based on the Bland-Altman plots, the 95% limits of agreement between manual CT and NN-based measurements were much smaller than those between Hertel exophthalmometer measurement and manual and NN-based measurements. In conclusion, automated NN-based measurements could provide a straightforward and efficient method for measuring proptosis using CT images.

Application of quantitative orbital analysis to assess the activity of Graves' ophthalmopathy

This study aimed to evaluate the diagnostic value of uptake ratios in the extraocular muscles (EOMs), lacrimal glands, and optic nerves to detect the inflammation activity of Graves' ophthalmopathy (GO) using quantitative analysis of 99m technetium (99mTc)-labeled diethylene triamine pentaacetic acid (DTPA) orbital single-photon emission computed tomography/computed tomography (SPECT/CT) images. The patients were categorized into an active stage (clinical activity score ≥ 3/7, n=23) or an inactive stage (clinical activity score < 3/7, n=38), based on their clinical activity score. The uptake ratio was manually determined by placing a region of interest within the area of highest uptake, as agreed upon by consensus, in the EOMs, lacrimal gland, and optic nerve on SPECT images corrected for CT attenuation. Patients with active GO exhibited significantly higher uptake ratios in the EOMs, lacrimal glands, and optic nerves compared to patients with inactive GO (all P < 0.01). These parameters have been proven effective in differentiating between active and inactive disease.