PDF(Sci-hub)
Abstract：
To evaluate an MRI radiomics-powered machine learning (ML) model\'s performance for the identification of deep myometrial invasion (DMI) in endometrial cancer (EC) patients and explore its clinical applicability.
Preoperative MRI scans of EC patients were retrospectively selected. Three radiologists performed whole-lesion segmentation on T2-weighted images for feature extraction. Feature robustness was tested before randomly splitting the population in training and test sets (80/20% proportion). A multistep feature selection was applied to the first, excluding noninformative, low variance features and redundant, highly-intercorrelated ones. A Random Forest wrapper was used to identify the most informative among the remaining. An ensemble of J48 decision trees was tuned and finalized in the training set using 10-fold cross-validation, and then assessed on the test set. A radiologist evaluated all MRI scans without and with the aid of ML to detect the presence of DMI. McNemars\'s test was employed to compare the two readings.
Of the 54 patients included, 17 had DMI. In all, 1132 features were extracted. After feature selection, the Random Forest wrapper identified the three most informative which were used for ML training. The classifier reached an accuracy of 86% and 91% and areas under the Receiver Operating Characteristic curve of 0.92 and 0.94 in the cross-validation and final testing, respectively. The radiologist performance increased from 82% to 100% when using ML (p = 0.48).
We proved the feasibility of a radiomics-powered ML model for DMI detection on MR T2-w images that might help radiologists to increase their performance.
Preoperative MRI scans of EC patients were retrospectively selected. Three radiologists performed whole-lesion segmentation on T2-weighted images for feature extraction. Feature robustness was tested before randomly splitting the population in training and test sets (80/20% proportion). A multistep feature selection was applied to the first, excluding noninformative, low variance features and redundant, highly-intercorrelated ones. A Random Forest wrapper was used to identify the most informative among the remaining. An ensemble of J48 decision trees was tuned and finalized in the training set using 10-fold cross-validation, and then assessed on the test set. A radiologist evaluated all MRI scans without and with the aid of ML to detect the presence of DMI. McNemars\'s test was employed to compare the two readings.
Of the 54 patients included, 17 had DMI. In all, 1132 features were extracted. After feature selection, the Random Forest wrapper identified the three most informative which were used for ML training. The classifier reached an accuracy of 86% and 91% and areas under the Receiver Operating Characteristic curve of 0.92 and 0.94 in the cross-validation and final testing, respectively. The radiologist performance increased from 82% to 100% when using ML (p = 0.48).
We proved the feasibility of a radiomics-powered ML model for DMI detection on MR T2-w images that might help radiologists to increase their performance.
摘要：
评价MRI影像组学驱动的机器学习(ML)模型在子宫内膜癌(EC)患者深肌层浸润(depometrialinvention,driving,drives,detainst,drivalinspection,drivalinspective,drivalinspecial,drivalinspecting,dometrialinchements,ded,
回顾性选择EC患者的术前MRI扫描。三位放射科医生对T2加权图像进行了全病变分割，以进行特征提取。在训练集和测试集(80/20%比例)中随机分裂群体之前测试特征鲁棒性。多步特征选择被应用于第一个，不包括非信息，低方差特征和冗余，高度相关的。使用随机森林包装来识别其余信息中的最大信息。使用10倍交叉验证在训练集中调整并最终确定了J48决策树的集合，然后在测试集上进行评估。放射科医生在没有ML的情况下以及在ML的帮助下评估了所有MRI扫描，以检测MI的存在。McNemars的测试用于比较两个读数。
在54名患者中，17有MDI。总之,提取了1132个特征。选择功能后，随机森林包装器确定了用于ML训练的三个最有用的信息。在交叉验证和最终测试中，分类器的准确率分别为86％和91％，接收器工作特性曲线下的面积分别为0.92和0.94。分别。使用ML时，放射科医师的表现从82％增加到100％（p=0.48）。
我们证明了影像组学驱动的ML模型在MRT2-w图像上进行MI检测的可行性，这可能有助于放射科医生提高其性能。
回顾性选择EC患者的术前MRI扫描。三位放射科医生对T2加权图像进行了全病变分割，以进行特征提取。在训练集和测试集(80/20%比例)中随机分裂群体之前测试特征鲁棒性。多步特征选择被应用于第一个，不包括非信息，低方差特征和冗余，高度相关的。使用随机森林包装来识别其余信息中的最大信息。使用10倍交叉验证在训练集中调整并最终确定了J48决策树的集合，然后在测试集上进行评估。放射科医生在没有ML的情况下以及在ML的帮助下评估了所有MRI扫描，以检测MI的存在。McNemars的测试用于比较两个读数。
在54名患者中，17有MDI。总之,提取了1132个特征。选择功能后，随机森林包装器确定了用于ML训练的三个最有用的信息。在交叉验证和最终测试中，分类器的准确率分别为86％和91％，接收器工作特性曲线下的面积分别为0.92和0.94。分别。使用ML时，放射科医师的表现从82％增加到100％（p=0.48）。
我们证明了影像组学驱动的ML模型在MRT2-w图像上进行MI检测的可行性，这可能有助于放射科医生提高其性能。
