International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group · 2025
Ultrasound radiomics-based nomogram to predict the non-perfused volume ratio of breast fibroadenomas treated with ultrasound-guided high-intensity focused ultrasound: a multicenter study.
СтатьяМногоцентровое исследованиеПоддержка исследования: вне правительства СШАНазвание и аннотация: Перевод пока не подготовлен
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.
Zhou De, Mu Dewu, Lin Zhiqin, Ren Yijie, Zhou Ye, Liu Huan, Zhu Leilei, Luo Jie, Li Meifang, Li Chenghai, Li Faqi
Аннотация
OBJECT: To develop and validate an ultrasound radiomics-based nomogram for the preoperative prediction of the non-perfused volume ratio of Ultrasound-guided high-intensity focused ultrasound (HIFU) ablation for fibroadenomas.
METHODS: This multicenter retrospective study included 156 patients from two institutions, comprising a total of 200 breast fibroadenomas. Data from one center (n = 140) were used for the training cohort, and data from the other center (n = 60) served as the test cohort. Radiomics features were extracted from preoperative US images. Feature selection was performed sequentially using Student's t-test or the Mann-Whitney U-test, followed by the least absolute shrinkage and selection operator (LASSO) regression. LightGBM was applied to build the radiomics and clinical models, and a combined model was then developed using the multivariate logistic regression, that is US radiomics-based nomogram. The performance of the models was evaluated based on area under the curve (AUC), calibration, and clinical applicability.
RESULT: Model evaluation showed that the nomogram outperformed both the clinical model (training set AUC = 0.696; test set AUC = 0.689) and the radiomics model (training set AUC = 0.898; test set AUC = 0.805), with an AUC of 0.896 in the training set and 0.830 in the test set. Calibration and decision curve analysis indicated that the nomogram exhibited good calibration and clinical utility.
CONCLUSION: The nomogram model provides an effective prediction of the non-perfused volume ratio (NPVR) in breast fibroadenomas treated with HIFU.
METHODS: This multicenter retrospective study included 156 patients from two institutions, comprising a total of 200 breast fibroadenomas. Data from one center (n = 140) were used for the training cohort, and data from the other center (n = 60) served as the test cohort. Radiomics features were extracted from preoperative US images. Feature selection was performed sequentially using Student's t-test or the Mann-Whitney U-test, followed by the least absolute shrinkage and selection operator (LASSO) regression. LightGBM was applied to build the radiomics and clinical models, and a combined model was then developed using the multivariate logistic regression, that is US radiomics-based nomogram. The performance of the models was evaluated based on area under the curve (AUC), calibration, and clinical applicability.
RESULT: Model evaluation showed that the nomogram outperformed both the clinical model (training set AUC = 0.696; test set AUC = 0.689) and the radiomics model (training set AUC = 0.898; test set AUC = 0.805), with an AUC of 0.896 in the training set and 0.830 in the test set. Calibration and decision curve analysis indicated that the nomogram exhibited good calibration and clinical utility.
CONCLUSION: The nomogram model provides an effective prediction of the non-perfused volume ratio (NPVR) in breast fibroadenomas treated with HIFU.