Fusion of Diffusion Weighted MRI and Clinical Data for Predicting Functional Outcome after Acute Ischemic Stroke with Deep Contrastive Learning

📄 arXiv: 2402.10894v1 📥 PDF

作者: Chia-Ling Tsai, Hui-Yun Su, Shen-Feng Sung, Wei-Yang Lin, Ying-Ying Su, Tzu-Hsien Yang, Man-Lin Mai

分类: cs.CV, cs.LG

发布日期: 2024-02-16

备注: 12 pages, 5 figures, 5 tables

💡 一句话要点

提出深度对比学习融合扩散加权MRI与临床数据以预测急性缺血性中风功能结果

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture) 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 急性缺血性中风 深度学习 多模态融合 扩散加权MRI 功能结果预测 对比学习 临床数据

📋 核心要点

  1. 现有方法在急性中风患者功能结果预测中面临准确性不足的挑战，尤其是在结合影像与临床数据时。
  2. 本文提出了一种深度融合学习网络，通过两阶段训练实现跨模态表示学习与分类，利用对比学习提取区分特征。
  3. 在3297名患者的数据集上，模型取得了0.87的AUC和80.45%的准确率，显著优于现有的医学领域模型。

📝 摘要（中文）

中风是常见的致残性神经疾病，影响约四分之一的25岁以上成年人。超过一半的患者在急性中风发作后仍有不良结果。本文研究了扩散加权MRI与结构化健康档案结合在预测功能结果中的有效性，提出了一种深度融合学习网络，采用两阶段训练，第一阶段专注于跨模态表示学习，第二阶段进行分类。通过监督对比学习，学习区分患者的特征。实验结果表明，该模型在3297名患者的测试中取得了0.87的AUC、0.80的F1-score和80.45%的准确率，优于现有模型。

🔬 方法详解

问题定义：本文旨在解决急性缺血性中风患者功能结果预测的准确性不足问题，现有方法在结合影像与临床数据时效果有限。

核心思路：提出的深度融合学习网络通过两阶段训练，首先进行跨模态表示学习，然后进行分类，以提高预测准确性。

技术框架：整体架构包括输入扩散加权MRI（DWI）和表观扩散系数（ADC）图像，以及结构化健康档案数据。第一阶段为特征学习，第二阶段为分类。

关键创新：采用监督对比学习提取区分特征，能够有效分离不同患者类别的嵌入，显著提升预测性能。

关键设计：模型设计中使用了特定的损失函数以优化对比学习过程，并结合了多模态数据以增强模型的泛化能力。具体参数设置和网络结构细节在论文中详细描述。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，提出的融合模型在3297名患者的测试中取得了0.87的AUC、0.80的F1-score和80.45%的准确率，显著优于现有医学领域的模型，尤其是在使用扩散加权MRI替代NIHSS时，仍能保持较高的预测准确性。

🎯 应用场景

该研究具有广泛的应用潜力，能够为急性缺血性中风患者提供早期干预的依据，帮助医疗工作者制定个性化治疗方案。未来，模型可扩展至其他神经疾病的预测与干预领域，提升临床决策的科学性与准确性。

📄 摘要（原文）

Stroke is a common disabling neurological condition that affects about one-quarter of the adult population over age 25; more than half of patients still have poor outcomes, such as permanent functional dependence or even death, after the onset of acute stroke. The aim of this study is to investigate the efficacy of diffusion-weighted MRI modalities combining with structured health profile on predicting the functional outcome to facilitate early intervention. A deep fusion learning network is proposed with two-stage training: the first stage focuses on cross-modality representation learning and the second stage on classification. Supervised contrastive learning is exploited to learn discriminative features that separate the two classes of patients from embeddings of individual modalities and from the fused multimodal embedding. The network takes as the input DWI and ADC images, and structured health profile data. The outcome is the prediction of the patient needing long-term care at 3 months after the onset of stroke. Trained and evaluated with a dataset of 3297 patients, our proposed fusion model achieves 0.87, 0.80 and 80.45% for AUC, F1-score and accuracy, respectively, outperforming existing models that consolidate both imaging and structured data in the medical domain. If trained with comprehensive clinical variables, including NIHSS and comorbidities, the gain from images on making accurate prediction is not considered substantial, but significant. However, diffusion-weighted MRI can replace NIHSS to achieve comparable level of accuracy combining with other readily available clinical variables for better generalization.