Gong Kai, Dai Qian, Wang Jiacheng, Zheng Yingbin, Shi Tao, Yu Jiaxing, Chen Jiangwang, Huang Shaohui, Wang Zhanxiang
The First Affiliated Hospital of Xiamen University, Xiamen University, Xiamen, Fujian, China.
Department of Computer Science, School of Informatics, Xiamen University, Xiamen, Fujian, China.
Front Neurosci. 2023 Mar 14;17:1118340. doi: 10.3389/fnins.2023.1118340. eCollection 2023.
With the recent development of deep learning, the regression, classification, and segmentation tasks of Computer-Aided Diagnosis (CAD) using Non-Contrast head Computed Tomography (NCCT) for spontaneous IntraCerebral Hematoma (ICH) have become popular in the field of emergency medicine. However, a few challenges such as time-consuming of ICH volume manual evaluation, excessive cost demanding patient-level predictions, and the requirement for high performance in both accuracy and interpretability remain. This paper proposes a multi-task framework consisting of upstream and downstream components to overcome these challenges. In the upstream, a weight-shared module is trained as a robust feature extractor that captures global features by performing multi-tasks (regression and classification). In the downstream, two heads are used for two different tasks (regression and classification). The final experimental results show that the multi-task framework has better performance than single-task framework. And it also reflects its good interpretability in the heatmap generated by Gradient-weighted Class Activation Mapping (Grad-CAM), which is a widely used model interpretation method, and will be presented in subsequent sections.
随着深度学习的近期发展，使用非增强头部计算机断层扫描（NCCT）对自发性脑内血肿（ICH）进行计算机辅助诊断（CAD）的回归、分类和分割任务在急诊医学领域变得流行起来。然而，仍然存在一些挑战，例如ICH体积手动评估耗时、对患者水平预测的成本过高以及对准确性和可解释性的高性能要求。本文提出了一个由上游和下游组件组成的多任务框架来克服这些挑战。在上游，一个权重共享模块被训练为一个强大的特征提取器，通过执行多任务（回归和分类）来捕获全局特征。在下游，两个头部用于两个不同的任务（回归和分类）。最终的实验结果表明，多任务框架比单任务框架具有更好的性能。并且它在梯度加权类激活映射（Grad-CAM）生成的热图中也体现了良好的可解释性，Grad-CAM是一种广泛使用的模型解释方法，将在后续章节中介绍。
