Zhu Yunyang, Wang Jing, Xue Chen, Zhai Xiaoyang, Xiao Chaoyong, Lu Ting
Department of Neurosurgery, The First Affiliated Hospital of Soochow University, Suzhou, China (Y.Z., J.W., T.L.).
Department of Radiology, the Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China (C.X., C.X.).
Acad Radiol. 2025 Feb;32(2):963-975. doi: 10.1016/j.acra.2024.09.021. Epub 2024 Sep 24.
Recent radiomics studies on predicting pathological outcomes of glioma have shown immense potential. However, the predictive ability remains suboptimal due to the tumor intrinsic heterogeneity. We aimed to achieve better pathological prediction outcomes by combining habitat analysis with deep learning.
387 cases of primary glioma from three hospitals were collected, along with their T1 contrast-enhanced and T2-weighted MR sequences, pathological reports and clinical histories. The training set consisted of 264 patients, 82 patients composed the test set, and 41 patients were used as the validation set for hyperparameter tuning and optimal model selection. All groups were sourced from different centers. Through radiomics, deep learning, habitat analysis and combined analysis, we extracted imaging features separately and jointly modeled them with clinical features. We identified the optimal models for predicting glioma grades, Ki67 expression levels, P53 mutation and IDH1 mutation.
Using a LightGBM model with DenseNet161 features based on habitat subregions, the best tumor grade prediction model was achieved. A LightGBM model with ResNet50 features based on habitat subregions yielded the best Ki67 expression level prediction model. An SVM model with Radiomics and Inception_v3 features provided the best prediction of P53 mutation. The best model for predicting IDH1 mutation was achieved by an MLP model with Radiomics features based on habitat subregions. Clinical features might be potentially helpful for the prediction with relatively weak evidence.
Habitat+Deep Learning feature extraction methods were optimal for predicting grades and Ki67 levels. Deep Learning is optimal for predicting P53 mutation, while the combination of Habitat+ Radiomics models yielded the best prediction for IDH1 mutation.
近期关于预测胶质瘤病理结果的放射组学研究显示出巨大潜力。然而，由于肿瘤内在的异质性，其预测能力仍不尽人意。我们旨在通过将栖息地分析与深度学习相结合来获得更好的病理预测结果。
收集了来自三家医院的387例原发性胶质瘤病例，以及它们的T1增强和T2加权磁共振序列、病理报告和临床病史。训练集由264例患者组成，82例患者构成测试集，41例患者用作验证集以进行超参数调整和最佳模型选择。所有组均来自不同中心。通过放射组学、深度学习、栖息地分析和联合分析，我们分别提取影像特征，并将其与临床特征联合建模。我们确定了预测胶质瘤分级、Ki67表达水平、P53突变和IDH1突变的最佳模型。
基于栖息地子区域使用具有DenseNet161特征的LightGBM模型，获得了最佳的肿瘤分级预测模型。基于栖息地子区域使用具有ResNet50特征的LightGBM模型产生了最佳的Ki67表达水平预测模型。具有放射组学和Inception_v3特征的支持向量机模型对P53突变提供了最佳预测。基于栖息地子区域使用具有放射组学特征的多层感知器模型获得了预测IDH1突变的最佳模型。临床特征可能对预测有潜在帮助，但证据相对较弱。
栖息地+深度学习特征提取方法在预测分级和Ki67水平方面最为理想。深度学习在预测P53突变方面最为理想，而栖息地+放射组学模型的组合对IDH1突变产生了最佳预测。
