Dataset Information

Radiomics analysis of the optic nerve for detecting dysthyroid optic neuropathy, based on water-fat imaging.

ABSTRACT:

Objective

Detecting dysthyroid optic neuropathy (DON) in the early stages is vital for clinical decision-making. The aim of this study was to determine the feasibility of using an optic-nerve-based radiomics nomogram on water-fat imaging for detecting DON.

Methods

This study included 104 orbits (83 in the training cohort) from 59 DON patients and 131 orbits (80 in the training cohort) from 69 thyroid-associated ophthalmopathy (TAO) without DON patients. Radiomic features were extracted from the optic-nerve T2-weighted water-fat images for each patient. Selected radiomics features were retrained to construct the radiomic signature model and calculate the radiomic score (Rad-score). The conventional MRI evaluation model was constructed based on apical crowding sign, optic-nerve stretching sign and muscle index. The radiomics nomogram model combining the Rad-score and conventional MRI evaluation factors was then developed. Predictive performance of the three models was assessed using ROC curves.

Results

Eight radiomics features from water-fat imaging were selected to build the radiomics signature. The radiomics nomogram (based on Rad-score, apical crowding sign and optic-nerve stretching sign) had superior diagnostic performance than did the conventional MRI evaluation model (AUC in the training set: 0.92 vs 0.80, the validation set:0.88 vs 0.75). Decision curve analysis confirmed the clinical usefulness of the radiomics nomogram.

Conclusions

This optic-nerve-based radiomics nomogram showed better diagnostic performance than conventional MRI evaluation for differentiating DON from TAO without DON. The changes of the optic-nerve itself may deserve more consideration in the clinical decision-making process.

SUBMITTER: Wu H

PROVIDER: S-EPMC9509517 | biostudies-literature | 2022 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Radiomics analysis of the optic nerve for detecting dysthyroid optic neuropathy, based on water-fat imaging.

Wu Hongyu H Luo Ban B Zhao Yali Y Yuan Gang G Wang Qiuxia Q Liu Ping P Zhai Linhan L Lv Wenzhi W Zhang Jing J

Insights into imaging 20220924 1

<h4>Objective</h4>Detecting dysthyroid optic neuropathy (DON) in the early stages is vital for clinical decision-making. The aim of this study was to determine the feasibility of using an optic-nerve-based radiomics nomogram on water-fat imaging for detecting DON.<h4>Methods</h4>This study included 104 orbits (83 in the training cohort) from 59 DON patients and 131 orbits (80 in the training cohort) from 69 thyroid-associated ophthalmopathy (TAO) without DON patients. Radiomic features were extr ...[more]

PMID: 36153469

Similar Datasets

Project description:BackgroundDysthyroid optic neuropathy (DON) is a serious threatening vision loss in Graves' ophthalmopathy (GO). Although the European Group on Graves' Ophthalmopathy (EUGOGO) recommend intravenous methylprednisolone therapy for first line treatment, some characteristics predicting the response are still inconclusive.AimTo study the efficacy of intravenous pulse methylprednisolone (IVMP) in treating dysthyroid optic neuropathy (DON) and to identify factors predicting poor response to the treatment.MethodsAll patients diagnosed with DON between January 2010 and December 2021 at Rajavithi Hospital, Thailand, receiving IVMP 1 g/ day for 3 consecutive days were analyzed. The efficacy at 1 week and 3, 6, 12-months in terms of improvement of best corrected visual acuity (BCVA) and proptosis were compiled.ResultsOf the entire 57 DON cases that received IVMP, 50.9% gained at least 0.2 Logarithm of the Minimum Angle of Resolution (logMAR) at 1 week, and the improvement from initial to 1-week BCVA was 0.63 ± 0.63 logMAR (p < 0.001) and the decrease in proptosis was 1.8 ± 1.36 mm (p < 0.001). The remaining 23 orbits underwent orbital decompression and were excluded from the long-term efficacy analysis. In the last 12-months' follow-up time, there was an improvement of BCVA (0.53 ± 0.47 logMAR) and proptosis (0.59 ± 0.66 mm) (both p < 0.001). At last visit, there was an improvement of BCVA (0.2 logMAR) and proptosis (2 mm) in 76.5, and 5.9% respectively. Significant predictive factors of poor treatment response were age ≥ 55 years (odds ratio [OR]: 8.28, 95% confidence interval [CI]: 1.368-50.121, p = 0.021); longer onset duration before treatment (OR: 5.10, 95%CI: 1.061-24.501, p = 0.042); and proptosis at baseline (OR: 9.31, 95%CI: 1.872-46.280, p = 0.006). The strongest risk factor for predicting poor response to IVMP was poor initial visual acuity (OR: 10.26, 95%CI: 1.363-77.234, p = 0.024).ConclusionsIVMP is effective for both short- and long-term treatment to improve visual acuity greater than proptosis. Older age, longer disease duration, poor initial visual acuity, and proptotic orbits were identified as risk factors for predicting poor response to IVMP treatment in Thai population. DON patients having those risk factors should be suspected, and treated early with IVMP to preserve their future vision.

Dataset Information

Radiomics analysis of the optic nerve for detecting dysthyroid optic neuropathy, based on water-fat imaging.

Objective

Methods

Results

Conclusions

Publications

Radiomics analysis of the optic nerve for detecting dysthyroid optic neuropathy, based on water-fat imaging.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets