Kanakarajan Hemalatha, De Baene Wouter, Hanssens Patrick, Sitskoorn Margriet
Department of Cognitive Neuropsychology, Tilburg University, Tilburg, The Netherlands.
Gamma Knife Center, Elisabeth-TweeSteden Hospital, Tilburg, The Netherlands.
Radiat Oncol. 2024 Dec 30;19(1):182. doi: 10.1186/s13014-024-02573-9.
Timely identification of local failure after stereotactic radiotherapy for brain metastases allows for treatment modifications, potentially improving outcomes. While previous studies showed that adding radiomics or Deep Learning (DL) features to clinical features increased Local Control (LC) prediction accuracy, their combined potential to predict LC remains unexplored. We examined whether a model using a combination of radiomics, DL and clinical features achieves better accuracy than models using only a subset of these features.
We collected pre-treatment brain MRIs (TR/TE: 25/1.86 ms, FOV: 210 × 210 × 150, flip angle: 30°, transverse slice orientation, voxel size: 0.82 × 0.82 × 1.5 mm) and clinical data for 129 patients at the Gamma Knife Center of the Elisabeth-TweeSteden Hospital. Radiomics features were extracted using the Python radiomics feature extractor and DL features were obtained using a 3D ResNet model. A Random Forest machine learning algorithm was employed to train four models using: (1) clinical features only; (2) clinical and radiomics features; (3) clinical and DL features; and (4) clinical, radiomics, and DL features. The average accuracy and other metrics were derived using K-fold cross validation.
The prediction model utilizing only clinical variables provided an Area Under the receiver operating characteristic Curve (AUC) of 0.85 and an accuracy of 75.0%. Adding radiomics features increased the AUC to 0.86 and accuracy to 79.33%, while adding DL features resulted in an AUC of 0.82 and accuracy of 78.0%. The best performance came from combining clinical, radiomics, and DL features, achieving an AUC of 0.88 and accuracy of 81.66%. This model's prediction improvement was statistically significant compared to models trained with clinical features alone or with the combination of clinical and DL features. However, the improvement was not statistically significant when compared to the model trained with clinical and radiomics features.
Integrating radiomics and DL features with clinical characteristics improves prediction of local control after stereotactic radiotherapy for brain metastases. Models incorporating radiomics features consistently outperformed those utilizing clinical features alone or clinical and DL features. The increased prediction accuracy of our integrated model demonstrates the potential for early outcome prediction, enabling timely treatment modifications to improve patient management.
及时识别脑转移瘤立体定向放射治疗后的局部失败情况有助于调整治疗方案，可能改善治疗结果。虽然先前的研究表明，在临床特征基础上增加放射组学或深度学习（DL）特征可提高局部控制（LC）预测的准确性，但它们联合预测LC的潜力尚未得到探索。我们研究了一个结合放射组学、DL和临床特征的模型是否比仅使用这些特征子集的模型具有更高的准确性。
我们收集了伊丽莎白 - 特维斯泰登医院伽玛刀中心129例患者的治疗前脑部磁共振成像（TR/TE：25/1.86 ms，视野：210×210×150，翻转角：30°，横断面切片方向，体素大小：0.82×0.82×1.5 mm）和临床数据。使用Python放射组学特征提取器提取放射组学特征，并使用3D ResNet模型获得DL特征。采用随机森林机器学习算法训练四个模型，分别使用：（1）仅临床特征；（2）临床和放射组学特征；（3）临床和DL特征；（4）临床、放射组学和DL特征。使用K折交叉验证得出平均准确率和其他指标。
仅使用临床变量的预测模型的受试者工作特征曲线下面积（AUC）为0.85，准确率为75.0%。添加放射组学特征后，AUC提高到0.86，准确率提高到79.33%，而添加DL特征后，AUC为0.82，准确率为78.0%。最佳性能来自临床、放射组学和DL特征的组合，AUC为0.88，准确率为81.66%。与仅使用临床特征或临床与DL特征组合训练的模型相比，该模型的预测改善具有统计学意义。然而，与使用临床和放射组学特征训练的模型相比，这种改善没有统计学意义。
将放射组学和DL特征与临床特征相结合可改善脑转移瘤立体定向放射治疗后局部控制的预测。包含放射组学特征的模型始终优于仅使用临床特征或临床与DL特征的模型。我们的综合模型提高的预测准确率证明了早期结果预测的潜力，能够及时调整治疗方案以改善患者管理。
