GRC-ProbNet：用于心血管疾病分类的不确定性感知特征提取
GRC-ProbNet: Uncertainty-aware Feature Extraction for Cardiovascular Disease Classification
查看机构详情
- Imperial College London（伦敦帝国学院）
- Medical University of Vienna（维也纳医科大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
研究旨在从CT图像自动检测和分类心血管疾病，提出GRC-ProbNet利用深度集成生成多个分割掩码以提取不确定性特征，实验表明该方法能提高CVD分类的AUROC，优于基线GRC-Net模型。
中文摘要 AI 辅助
从计算机断层扫描（CT）图像中自动检测和分类心血管疾病（CVD）在临床实践中起着重要作用。最近提出了一种用于CVD分类的混合管道（GRC-Net），它利用基于深度学习的分割和配准方法来提取放射组学和几何特征。然而，GRC-Net依赖于确定性分割掩码，未考虑与心脏解剖结构相关的固有模糊性。本文提出GRC-ProbNet，利用深度集成针对给定输入生成多个分割掩码，从中提取多个不确定性特征，并分析其与分割误差的相关性以及对下游CVD分类性能的传播效应。在公开可用的MM-WHS和ASOCA数据集上的实验表明，最能反映分割质量的不确定性度量不一定能为下游CVD分类提供最强信号。总体而言，利用不确定性特征的GRC-ProbNet与基线GRC-Net模型相比，显著提高了CVD分类的AUROC（从91.25%提高到92.92%）。
英文摘要
The automatic detection and classification of cardiovascular disease (CVD) from computed tomography (CT) images plays an important role in clinical practice. Recently, a hybrid pipeline (GRC-Net) for CVD classification was proposed, which leverages a deep-learning-based segmentation and registration method to extract radiomic and geometric features. However, GRC-Net relies on a deterministic segmentation mask, without considering the inherent ambiguity associated with cardiac anatomy. In this paper, we propose GRC-ProbNet, which takes advantage of a deep ensemble to produce multiple segmentation masks for a given input. From these masks, we extract multiple uncertainty features. We analyze these uncertainty features for both their correlation with segmentation error and their propagation effects on downstream CVD classification performance. Our experiments on the publicly available MM-WHS and ASOCA datasets show that the uncertainty measure that best reflects segmentation quality is not necessarily the one that provides the strongest signal for downstream CVD classification. Overall, our results demonstrate that GRC-ProbNet utilizing uncertainty features substantially improves CVD classification AUROC (92.92\) compared to the baseline GRC-Net model (91.25%). Our code is publicly available: https://github.com/biomedia-mira/GRC-ProbNet.
