Department Of Radiology, The Second Affiliated Hospital of Soochow University, Suzhou, 215004, China.
Department of Radiotherapy & Oncology, The Second Affiliated Hospital of Soochow University, Suzhou, 215004, China.
Eur J Radiol. 2024 Nov;180:111712. doi: 10.1016/j.ejrad.2024.111712. Epub 2024 Aug 28.
Brain metastases (BMs) represents a severe neurological complication stemming from cancers originating from various sources. It is a highly challenging clinical task to accurately distinguish the pathological subtypes of brain metastatic tumors from lung cancer (LC).The utility of 2.5-dimensional (2.5D) deep learning (DL) in distinguishing pathological subtypes of LC with BMs is yet to be determined.
A total of 250 patients were included in this retrospective study, divided in a 7:3 ratio into training set (N=175) and testing set (N=75). We devised a method to assemble a series of two-dimensional (2D) images by extracting adjacent slices from a central slice in both superior-inferior and anterior-posterior directions to form a 2.5D dataset. Multi-Instance learning (MIL) is a weakly supervised learning method that organizes training instances into "bags" and provides labels for entire bags, with the purpose of learning a classifier based on the labeled positive and negative bags to predict the corresponding class for an unknown bag. Therefore, we employed MIL to construct a comprehensive 2.5D feature set. Then we used the single-slice as input for constructing the 2D model. DL features were extracted from these slices using the pre-trained ResNet101. All feature sets were inputted into the support vector machine (SVM) for evaluation. The diagnostic performance of the classification models were evaluated using five-fold cross-validation, with accuracy and area under the curve (AUC) metrics calculated for analysis.
The optimal performance was obtained using the 2.5D DL model, which achieved the micro-AUC of 0.868 (95% confidence interval [CI], 0.817-0.919) and accuracy of 0.836 in the test cohort. The 2D model achieved the micro-AUC of 0.836 (95 % CI, 0.778-0.894) and accuracy of 0.827 in the test cohort.
The proposed 2.5D DL model is feasible and effective in identifying pathological subtypes of BMs from lung cancer.
脑转移瘤（BMs）是一种严重的神经系统并发症，源自各种来源的癌症。准确区分肺癌（LC）脑转移瘤的病理亚型是一项极具挑战性的临床任务。2.5 维（2.5D）深度学习（DL）在区分 LC 伴 BMs 的病理亚型中的应用尚待确定。
本回顾性研究共纳入 250 例患者，按 7：3 的比例分为训练集（N=175）和测试集（N=75）。我们设计了一种方法，通过从前向后和从上到下从中心切片提取相邻切片来组装一系列 2D 图像，形成 2.5D 数据集。多实例学习（MIL）是一种弱监督学习方法，它将训练实例组织成“袋子”，并为整个袋子提供标签，目的是基于标记的正袋和负袋学习分类器，以预测未知袋的对应类别。因此，我们采用 MIL 构建全面的 2.5D 特征集。然后我们使用单张切片作为输入来构建 2D 模型。使用预先训练的 ResNet101 从这些切片中提取 DL 特征。将所有特征集输入支持向量机（SVM）进行评估。使用五重交叉验证评估分类模型的诊断性能，计算准确率和曲线下面积（AUC）指标进行分析。
在测试队列中，2.5D DL 模型的性能最佳，获得了 0.868 的微 AUC（95%置信区间[CI]，0.817-0.919）和 0.836 的准确率。2D 模型在测试队列中获得了 0.836 的微 AUC（95% CI，0.778-0.894）和 0.827 的准确率。
所提出的 2.5D DL 模型在识别肺癌脑转移瘤的病理亚型方面是可行且有效的。
