Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance · 2025
A radiomic model based on 7T intracranial vessel wall imaging for identification of culprit middle cerebral artery plaque associated with subcortical infarctions.
СтатьяПоддержка 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.
Chen Tong, Zhu Wenhui, Bai Xiaoyan, Mossa-Basha Mahmud, Zhao Yuanbin, Pei Xun, Zhang Xue, Liu Gaifen, Zhao Xingquan, Li Zixiao, Xu Jie, Sun Shengjun, Chen Duanduan, Zhang Shuaitong, Sui Binbin
Аннотация
BACKGROUND: Radiomics has been proven to be an important method for the quantitative assessment of atherosclerotic plaques. Therefore, we aimed to evaluate a radiomics approach based on 7.0T high-resolution vessel wall imaging (HR-VWI) to identify culprit middle cerebral artery (MCA) plaques associated with subcortical infarctions.
METHODS: One hundred patients with MCA plaques were prospectively enrolled. Among these patients, 145 plaques (74 culprit plaques and 71 non-culprit plaques) were included. A traditional model was constructed by recording the conventional radiological plaque characteristics of HR-VWI. Radiomics features from HR-VWI images were utilized to construct a radiomics model. A combined model was built using both conventional radiological and radiomics features. Receiver operating characteristic (ROC) curves and area under curve (AUC) were used to compare the performance of these models.
RESULTS: Plaque surface irregularity and superior wall location of MCA plaques were independently associated with subcortical infarctions. The traditional model had AUCs of 0.744 and 0.700 in the training and test sets, respectively. The radiomics and the combined model showed improved AUCs: 0.860 and 0.896 in the training sets and 0.795 and 0.833 in the test sets, respectively. The radiomics model was superior to the traditional model (p = 0.042) in the training set. The combined model outperformed the traditional model (training p < 0.001, test p = 0.048).
CONCLUSION: The radiomics approach based on 7.0T HR-VWI can accurately identify culprit plaques associated with subcortical infarctions, potentially better than conventional HR-VWI features.
METHODS: One hundred patients with MCA plaques were prospectively enrolled. Among these patients, 145 plaques (74 culprit plaques and 71 non-culprit plaques) were included. A traditional model was constructed by recording the conventional radiological plaque characteristics of HR-VWI. Radiomics features from HR-VWI images were utilized to construct a radiomics model. A combined model was built using both conventional radiological and radiomics features. Receiver operating characteristic (ROC) curves and area under curve (AUC) were used to compare the performance of these models.
RESULTS: Plaque surface irregularity and superior wall location of MCA plaques were independently associated with subcortical infarctions. The traditional model had AUCs of 0.744 and 0.700 in the training and test sets, respectively. The radiomics and the combined model showed improved AUCs: 0.860 and 0.896 in the training sets and 0.795 and 0.833 in the test sets, respectively. The radiomics model was superior to the traditional model (p = 0.042) in the training set. The combined model outperformed the traditional model (training p < 0.001, test p = 0.048).
CONCLUSION: The radiomics approach based on 7.0T HR-VWI can accurately identify culprit plaques associated with subcortical infarctions, potentially better than conventional HR-VWI features.