吴莉莉, 孙陈, 何天洪, 吴树剑, 范莉芳, 陈基明. 基于MRI影像组学模型术前预测垂体神经内分泌瘤血供[J]. 中国肿瘤临床, 2024, 51(8): 406-412. DOI: 10.12354/j.issn.1000-8179.2024.20240254
引用本文: 吴莉莉, 孙陈, 何天洪, 吴树剑, 范莉芳, 陈基明. 基于MRI影像组学模型术前预测垂体神经内分泌瘤血供[J]. 中国肿瘤临床, 2024, 51(8): 406-412. DOI: 10.12354/j.issn.1000-8179.2024.20240254
Lili Wu, Chen Sun, Tianhong He, Shujian Wu, Lifang Fan, Jiming Chen. Preoperative prediction of blood supply in pituitary neuroendocrine tumors based on MRI radiomic models[J]. CHINESE JOURNAL OF CLINICAL ONCOLOGY, 2024, 51(8): 406-412. DOI: 10.12354/j.issn.1000-8179.2024.20240254
Citation: Lili Wu, Chen Sun, Tianhong He, Shujian Wu, Lifang Fan, Jiming Chen. Preoperative prediction of blood supply in pituitary neuroendocrine tumors based on MRI radiomic models[J]. CHINESE JOURNAL OF CLINICAL ONCOLOGY, 2024, 51(8): 406-412. DOI: 10.12354/j.issn.1000-8179.2024.20240254

基于MRI影像组学模型术前预测垂体神经内分泌瘤血供

Preoperative prediction of blood supply in pituitary neuroendocrine tumors based on MRI radiomic models

  • 摘要:
    目的 探讨基于MRI影像组学特征的机器学习模型在术前预测垂体神经内分泌瘤血供的价值。
    方法 回顾性分析2013年4月至2023年4月皖南医学院第一附属弋矶山医院136例经病理确诊的垂体神经内分泌瘤(直径>10 mm)患者的临床和影像资料。根据术中所见将其分为血供丰富组50例和血供一般组86例。按照完全随机的方法将所有患者以7∶3的比例分为训练组96例和验证组40例。采用多因素Logistic回归(LR)、随机森林(RF)、支持向量机(SVM)三种机器学习算法分别建立影像组学预测模型。绘制受试者工作特征曲线(ROC)评价模型的诊断效能,并绘制决策曲线分析(DCA)评估模型的临床净收益。
    结果 临床模型在训练组和验证组中的曲线下面积(AUC)为0.74、0.82;T1WI、T2WI、T1WI增强及联合序列影像组学模型在训练组中AUC分别为0.80、0.84、0.82、0.84,在验证组中分别为0.82、0.80、0.85、0.83;LR、RF、SVM模型在训练组中的AUC分别为0.85、0.87、0.84,验证组中分别为0.85、0.85、0.83。影像组学各模型均优于临床模型的诊断效能。DCA显示联合序列模型、LR及SVM模型均获得较好的临床净收益,LR模型最优。
    结论 MRI影像组学的机器学习各模型均具有较高的预测价值,优于临床医生肉眼观察MRI图像的判断,且具有较好的临床净收益,能够为临床决策提供有效指导作用。

     

    Abstract:
    Objective To explore the value of machine-learning models based on magnetic resonance imaging (MRI) radiomics features for the preoperative prediction of the blood supply in pituitary neuroendocrine tumors.
    Methods  A retrospective analysis was performed on the clinical and imaging data of 136 patients with pathologically confirmed pituitary neuroendocrine tumors (diameter >10 mm) from April 2013 to April 2023 at Yi Jishan Hospital of Wannan Medical College. Based on the intraoperative findings, the patients were assigned into richly vascularized (n=50) and normally vascularized (n=86) groups. All patients were allocated randomly in a 7:3 ratio into a training (n=96) or a validation group (n=40). Three machine-learning algorithms, multivariate Logistic regression (LR), random forest (RF), and support vector machine (SVM), were used to establish radiomics prediction models. Receiver operating characteristic (ROC) curves were plotted to evaluate the diagnostic performance of the models; decision curve analysis (DCA) was used to assess the net clinical benefit of the models.
    Results  The clinical model achieved areas under the ROC curve (AUC) of 0.74 and 0.82 in the training and validation groups, respectively. The radiomics models using T1-weighted imaging (WI), T2WI, T1WI-enhanced, and combined sequences achieved AUCs of 0.80, 0.84, 0.82, and 0.84 in the training group and 0.82, 0.80, 0.85, and 0.83 in the validation group, respectively. The LR, RF, and SVM models had AUCs of 0.85, 0.87, and 0.84 in the training group and 0.85, 0.85, and 0.83 in the validation group, respectively. All radiomics models demonstrated greater diagnostic efficacy than the clinical model. DCA indicated that the LR, SVM, and combined-sequence models achieved good net clinical benefits; the LR model showed the best results.
    Conclusions  Machine-learning models based on MRI radiomics exhibit high predictive value, surpassing the clinical judgment of radiologists based on MRI images alone, and offer a favorable net clinical benefit.

     

/

返回文章
返回