Salari Elahheh, Elsamaloty Haitham, Ray Aniruddha, Hadziahmetovic Mersiha, Parsai E Ishmael
Departments of Radiation Oncology.
Radiology, University of Toledo Medical Center, Sylvania.
Am J Clin Oncol. 2023 Nov 1;46(11):486-495. doi: 10.1097/COC.0000000000001036. Epub 2023 Aug 15.
Distinguishing between radiation necrosis (RN) and metastatic progression is extremely challenging due to their similarity in conventional imaging. This is crucial from a therapeutic point of view as this determines the outcome of the treatment. This study aims to establish an automated technique to differentiate RN from brain metastasis progression using radiomics with machine learning.
Eighty-six patients with brain metastasis after they underwent stereotactic radiosurgery as primary treatment were selected. Discrete wavelets transform, Laplacian-of-Gaussian, Gradient, and Square were applied to magnetic resonance post-contrast T1-weighted images to extract radiomics features. After feature selection, dataset was randomly split into train/test (80%/20%) datasets. Random forest classification, logistic regression, and support vector classification were trained and subsequently validated using test set. The classification performance was measured by area under the curve (AUC) value of receiver operating characteristic curve, accuracy, sensitivity, and specificity.
The best performance was achieved using random forest classification with a Gradient filter (AUC=0.910±0.047, accuracy 0.8±0.071, sensitivity=0.796±0.055, specificity=0.922±0.059). For, support vector classification the best result obtains using wavelet_HHH with a high AUC of 0.890±0.89, accuracy of 0.777±0.062, sensitivity=0.701±0.084, and specificity=0.85±0.112. Logistic regression using wavelet_HHH provides a poor result with AUC=0.882±0.051, accuracy of 0.753±0.08, sensitivity=0.717±0.208, and specificity=0.816±0.123.
This type of machine-learning approach can help accurately distinguish RN from recurrence in magnetic resonance imaging, without the need for biopsy. This has the potential to improve the therapeutic outcome.
由于放射性坏死（RN）和转移进展在传统影像学上具有相似性，因此区分二者极具挑战性。从治疗角度来看，这一点至关重要，因为它决定了治疗结果。本研究旨在建立一种利用放射组学和机器学习来区分RN与脑转移进展的自动化技术。
选取86例接受立体定向放射外科作为主要治疗的脑转移患者。将离散小波变换、高斯拉普拉斯算子、梯度和平方应用于对比增强磁共振T1加权图像，以提取放射组学特征。特征选择后，将数据集随机分为训练/测试（80%/20%）数据集。对随机森林分类、逻辑回归和支持向量分类进行训练，并随后使用测试集进行验证。通过受试者操作特征曲线的曲线下面积（AUC）值、准确率、敏感性和特异性来衡量分类性能。
使用带有梯度滤波器的随机森林分类获得了最佳性能（AUC = 0.910±0.047，准确率0.8±0.071，敏感性 = 0.796±0.055，特异性 = 0.922±0.059）。对于支持向量分类，使用小波_HHH获得了最佳结果，AUC高达0.890±0.89，准确率为0.777±0.062，敏感性 = 0.701±0.084，特异性 = 0.85±0.112。使用小波_HHH的逻辑回归结果较差，AUC = 0.882±0.051，准确率为0.753±0.08，敏感性 = 0.717±0.208，特异性 = 0.816±0.123。
这种机器学习方法有助于在磁共振成像中准确区分RN与复发，无需进行活检。这有可能改善治疗结果。
