Magnetic resonance imaging · 2026
Evaluation of the diagnostic value of DCE-MRI radiomics features and K-trans parameters in differentiating endometrial cancer from submucosal uterine fibroids.
СтатьяПоддержка исследования: вне правительства СШАНазвание 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.
Su LiJian, Wang KeWu, Xiao ShengXiang, Xu LiuYan, Hu JiBo
Аннотация
OBJECTIVE: To explore the diagnostic value of Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) radiomics features and qualitative parameters for the differential diagnosis of endometrial cancer (EC) and submucosal uterine fibroidsuterine fibroids.
METHODS: This retrospective study included 70 cases of endometrial cancer patients collected from our hospital between October 2022 and October 2024, assigned to the EC group, and another 35 cases of uterine leiomyoma patients during the same period were collected as the benign group according to the 2:1 matching principle. Baseline data, DCE-MRI parameters [rate constant (Kep), volume transport constant (Ktrans), and volume fraction of extracellular space (Ve)] and radiomics characteristics were compared between the two groups. The influencing factors of DCE-MRI parameters and radiomics features on EC were analyzed, as well as their diagnostic value in differentiation, and external validation of the diagnostic value in differentiation was conducted.
RESULTS: Ktrans and Kep in EC group were higher than those in benign group, while Ve was lower (P < 0.05). The radiomic score of the EC group was higher than that of the benign group (P < 0.05). Logistic regression analysis found that Ktrans, Kep, Ve, and radiomic score were factors affecting EC (P < 0.05). The AUC values for the DCE-MRI model, radiomics model, and combined model in predicting the differential diagnosis of EC were 0.695, 0.775, and 0.867, respectively. Among them, the combined model demonstrated the highest predictive value, significantly surpassing that of the DCE-MRI and radiomics models (P < 0.05). The decision curve indicated that the clinical positive benefit achieved by the combined model in differential diagnosis of EC surpassed that of the DCE-MRI and radiomics models (P < 0.05). The calibration curve showed that the calibration curve for differential diagnosis of EC fitted well with the ideal curve. The external validation results demonstrated that the combined diagnostic model exhibited good predictive value.
CONCLUSION: The combination of DCE-MRI parameters and radiomics features can be used for the differential diagnosis of EC, demonstrating good predictive efficacy and clinical applicability, providing a reliable imaging diagnostic method for clinical diagnosis of EC.
METHODS: This retrospective study included 70 cases of endometrial cancer patients collected from our hospital between October 2022 and October 2024, assigned to the EC group, and another 35 cases of uterine leiomyoma patients during the same period were collected as the benign group according to the 2:1 matching principle. Baseline data, DCE-MRI parameters [rate constant (Kep), volume transport constant (Ktrans), and volume fraction of extracellular space (Ve)] and radiomics characteristics were compared between the two groups. The influencing factors of DCE-MRI parameters and radiomics features on EC were analyzed, as well as their diagnostic value in differentiation, and external validation of the diagnostic value in differentiation was conducted.
RESULTS: Ktrans and Kep in EC group were higher than those in benign group, while Ve was lower (P < 0.05). The radiomic score of the EC group was higher than that of the benign group (P < 0.05). Logistic regression analysis found that Ktrans, Kep, Ve, and radiomic score were factors affecting EC (P < 0.05). The AUC values for the DCE-MRI model, radiomics model, and combined model in predicting the differential diagnosis of EC were 0.695, 0.775, and 0.867, respectively. Among them, the combined model demonstrated the highest predictive value, significantly surpassing that of the DCE-MRI and radiomics models (P < 0.05). The decision curve indicated that the clinical positive benefit achieved by the combined model in differential diagnosis of EC surpassed that of the DCE-MRI and radiomics models (P < 0.05). The calibration curve showed that the calibration curve for differential diagnosis of EC fitted well with the ideal curve. The external validation results demonstrated that the combined diagnostic model exhibited good predictive value.
CONCLUSION: The combination of DCE-MRI parameters and radiomics features can be used for the differential diagnosis of EC, demonstrating good predictive efficacy and clinical applicability, providing a reliable imaging diagnostic method for clinical diagnosis of EC.