用传统纹理特征区分新冠与普通肺炎，准确率达75.4%。
Toward Multi-Modal Deep Learning for Pulmonary Disease Classification: A Texture-Based Machine Learning Pilot Study on Public Chest X-Ray Data
- 提取HOG和GLCM纹理特征，结合经典分类器
- 在公开数据集上达75.4%准确率，优于71.6%基线
- 为多模态深度学习提供方向，适合医疗影像研究者
基于胸部X光片的肺部疾病自动分类是医学影像机器学习中的广泛研究课题。本文提出一项试点研究，评估经典纹理与梯度特征表示方法在区分新冠肺炎与其他类型肺炎中的表现，使用公开的COVID-19图像数据集（包含408名患者共668张前后位/正位影像）。采用方向梯度直方图（HOG）与灰度共生矩阵（GLCM）纹理描述子，结合逻辑回归、随机森林及支持向量机等经典分类器，在患者级5折分层交叉验证下进行评估，获得最佳均值准确率为75.4%，AUC为0.755，略高于71.6%的多数类基线。研究透明报告结果及其局限性，并据此提出未来工作方向：构建融合卷积与Transformer编码器的多模态深度学习架构，需依赖更大规模、多机构、伦理合规的数据集。
原文摘要 · Abstract (English)
Automated classification of pulmonary disease from chest radiographs is a widely studied application of machine learning in medical imaging. This paper presents a pilot study evaluating classical texture- and gradient-based feature representations for distinguishing COVID-19 from other forms of pneumonia using the publicly available COVID-19 Image Data Collection (668 posteroanterior/anteroposterior radiographs from 408 patients). Using histogram of oriented gradients (HOG) and gray-level co-occurrence matrix (GLCM) texture descriptors with classical classifiers (logistic regression, random forest, and support vector machine), evaluated under patient-level 5-fold stratified cross-validation to prevent data leakage, we obtain a best mean accuracy of 75.4% and AUC of 0.755, modestly exceeding the 71.6% majority-class baseline. We report these results transparently, including their limitations, and use them to motivate and scope a proposed multi-modal deep learning architecture -- combining convolutional and transformer-based encoders across imaging modalities -- as a direction for future work requiring access to larger, multi-institutional, ethically sourced datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。