Frontiers in neurology · 2026
A CT radiomics nomogram predicts visual acuity improvement in patients with indirect traumatic optic neuropathy following optic canal decompression.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wang Guangyu, Yu Pengran, Li Shuo, Zhang Wenchuan
Аннотация
INTRODUCTION: Indirect traumatic optic neuropathy (ITON) is a common cause of persistent visual impairment following craniofacial trauma. While optic canal decompression (OCD) serves as a primary surgical intervention, its efficacy is variable, with approximately half of the patients failing to achieve significant visual acuity (VA) recovery. Existing models for predicting surgical outcomes lack sufficient accuracy and generalizability.
MATERIALS AND METHODS: This retrospective, single-center study included 169 patients with ITON who underwent OCD between May 2014 and October 2025. Participants were randomly assigned to training (n = 118) and test (n = 51) sets in a 7:3 ratio. Radiomics features were extracted from preoperative CT scans, and the most prognostically significant features were identified via Least Absolute Shrinkage and Selection Operator (LASSO) regression. The model's performance and clinical utility were evaluated through receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis (DCA).
RESULTS: The final nomogram incorporated nine radiomics features and three clinical predictors. It demonstrated robust discriminative ability, with area under the curve values of 0.840 in the training set and 0.832 in the test set. This tool effectively categorized patients into distinct risk groups for poor VA recovery. VA improvement rates were significantly higher in the low-risk group than in the high-risk group in both the training (87.9% vs. 30.5%) and test (87.0% vs. 28.6%) cohorts. Calibration and decision curve analyses confirmed the superior performance and clinical net benefit of the combined model over those relying solely on clinical or radiomics features.
CONCLUSION: The developed clinical-radiomics nomogram represents a valuable non-invasive tool for the preoperative prediction of VA improvement following OCD in patients with ITON, showing significant potential to inform personalized treatment strategies.
MATERIALS AND METHODS: This retrospective, single-center study included 169 patients with ITON who underwent OCD between May 2014 and October 2025. Participants were randomly assigned to training (n = 118) and test (n = 51) sets in a 7:3 ratio. Radiomics features were extracted from preoperative CT scans, and the most prognostically significant features were identified via Least Absolute Shrinkage and Selection Operator (LASSO) regression. The model's performance and clinical utility were evaluated through receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis (DCA).
RESULTS: The final nomogram incorporated nine radiomics features and three clinical predictors. It demonstrated robust discriminative ability, with area under the curve values of 0.840 in the training set and 0.832 in the test set. This tool effectively categorized patients into distinct risk groups for poor VA recovery. VA improvement rates were significantly higher in the low-risk group than in the high-risk group in both the training (87.9% vs. 30.5%) and test (87.0% vs. 28.6%) cohorts. Calibration and decision curve analyses confirmed the superior performance and clinical net benefit of the combined model over those relying solely on clinical or radiomics features.
CONCLUSION: The developed clinical-radiomics nomogram represents a valuable non-invasive tool for the preoperative prediction of VA improvement following OCD in patients with ITON, showing significant potential to inform personalized treatment strategies.