Abdominal radiology (New York) · 2025
Construction of a predictive model for radiation proctitis after radical radiotherapy for cervical cancer based on MRI radiomics.
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.
Deng Sufang, Liu Linying, Lin Jie, Xiong Zhuang, Cai Zhihua, Yu Haijuan, Xie Ning, Fu Yixin, Sun Yang
Аннотация
PURPOSE: Radiation proctitis (RP) is a frequent and clinically relevant complication of radiotherapy (RT) in cervical cancer (CC). However, effective tools for individualized RP risk prediction remain limited. This study aimed to develop and validate an MRI-based radiomic risk score for early RP prediction in CC patients.
METHODS: This retrospective study included 375 CC patients who underwent radical RT. Patients were randomly assigned to training (80%) and validation (20%) cohorts. Radiomics features were extracted from pre-treatment MRI and screened using Mann-Whitney U test, intraclass correlation coefficient, and least absolute shrinkage and selection operator regression. Logistic regression analyses identified independent predictors of RP, and a clinical-radiomics nomogram was constructed. Model performance was assessed by the area under the curve (AUC), calibration, and decision curve analysis (DCA).
RESULTS: Of 1,906 extracted features, 9 were selected to construct the radiomics risk score. Independent predictors of RP included lymphocyte counts ≥ 2.6 × 10⁹/L, platelet-lymphocyte ratio ≥ 196, rectal mean dose ≥ 47.22 Gy, and radiomics risk score≥-0.4. The nomogram incorporating these factors achieved AUCs of 0.810 (training) and 0.730 (validation), with good calibration and clinical utility demonstrated by DCA.
CONCLUSION: The proposed MRI-based radiomic risk score enables accurate, noninvasive prediction of RP in CC patients and provides a practical tool to optimize individualized RT planning and toxicity management.
METHODS: This retrospective study included 375 CC patients who underwent radical RT. Patients were randomly assigned to training (80%) and validation (20%) cohorts. Radiomics features were extracted from pre-treatment MRI and screened using Mann-Whitney U test, intraclass correlation coefficient, and least absolute shrinkage and selection operator regression. Logistic regression analyses identified independent predictors of RP, and a clinical-radiomics nomogram was constructed. Model performance was assessed by the area under the curve (AUC), calibration, and decision curve analysis (DCA).
RESULTS: Of 1,906 extracted features, 9 were selected to construct the radiomics risk score. Independent predictors of RP included lymphocyte counts ≥ 2.6 × 10⁹/L, platelet-lymphocyte ratio ≥ 196, rectal mean dose ≥ 47.22 Gy, and radiomics risk score≥-0.4. The nomogram incorporating these factors achieved AUCs of 0.810 (training) and 0.730 (validation), with good calibration and clinical utility demonstrated by DCA.
CONCLUSION: The proposed MRI-based radiomic risk score enables accurate, noninvasive prediction of RP in CC patients and provides a practical tool to optimize individualized RT planning and toxicity management.