Department of Neuroimaging and Interventional Radiology, National Institute of Mental Health and Neuro Sciences (NIMHANS), Bengaluru, Karnataka, 560029, India.
Department of Neurosurgery, National Institute of Mental Health and Neuro Sciences (NIMHANS), Bengaluru, Karnataka, India.
Neuroradiology. 2024 Nov;66(11):1979-1992. doi: 10.1007/s00234-024-03435-7. Epub 2024 Aug 5.
Tuberculomas are prevalent in developing countries and demonstrate variable signals on MRI resulting in the overlap of the conventional imaging phenotype with other entities including glioma and brain metastasis. An accurate MRI diagnosis is important for the early institution of anti-tubercular therapy, decreased patient morbidity, mortality, and prevents unnecessary neurosurgical excision. This study aims to assess the potential of radiomics features of regular contrast images including T1W, T2W, T2W FLAIR, T1W post contrast images, and ADC maps, to differentiate between tuberculomas, high-grade-gliomas and metastasis, the commonest intra parenchymal mass lesions encountered in the clinical practice.
This retrospective study includes 185 subjects. Images were resampled, co-registered, skull-stripped, and zscore-normalized. Automated lesion segmentation was performed followed by radiomics feature extraction, train-test split, and features reduction. All machine learning algorithms that natively support multiclass classification were trained and assessed on features extracted from individual modalities as well as combined modalities. Model explainability of the best performing model was calculated using the summary plot obtained by SHAP values.
Extra tree classifier trained on the features from ADC maps was the best classifier for the discrimination of tuberculoma from high-grade-glioma and metastasis with AUC-score of 0.96, accuracy-score of 0.923, Brier-score of 0.23.
This study demonstrates that radiomics features are effective in discriminating between tuberculoma, metastasis, and high-grade-glioma with notable accuracy and AUC scores. Features extracted from the ADC maps surfaced as the most robust predictors of the target variable.
结核瘤在发展中国家较为常见，其在 MRI 上的信号表现多样，与其他实体瘤（包括胶质瘤和脑转移瘤）的常规影像学表现重叠。准确的 MRI 诊断对于早期开始抗结核治疗、降低患者发病率和死亡率以及避免不必要的神经外科切除非常重要。本研究旨在评估常规对比成像（包括 T1W、T2W、T2W FLAIR、T1W 对比后图像和 ADC 图）的放射组学特征在鉴别结核瘤、高级别胶质瘤和转移瘤方面的潜力，这是临床实践中最常见的脑实质内肿块病变。
这是一项回顾性研究，共纳入 185 例患者。对图像进行重采样、配准、颅骨剥离和 z 分数归一化。进行自动病变分割后，提取放射组学特征，进行训练-测试分割和特征降维。所有支持多类分类的原生机器学习算法都在从单个模态和组合模态提取的特征上进行训练和评估。使用 SHAP 值获得的汇总图计算最佳模型的可解释性。
在 ADC 图上提取特征后，使用 Extra tree 分类器进行训练，对结核瘤与高级别胶质瘤和转移瘤的鉴别效果最佳，AUC 评分为 0.96，准确率评分为 0.923，Brier 评分为 0.23。
本研究表明，放射组学特征可有效鉴别结核瘤、转移瘤和高级别胶质瘤，具有较高的准确性和 AUC 评分。从 ADC 图提取的特征是目标变量的最稳健预测因子。
