用声音和影像双模态深度学习提升先天性心脏病筛查准确率
Congenital Heart Disease recognition using Deep Learning/Transformer models
- 结合心音与胸部X光片的双模态深度学习模型
- 在ZCHSound数据集上达到73.9%准确率，在DICOM数据集上达80.72%
- 适合临床辅助诊断场景，尤其适用于资源有限地区
先天性心脏病（CHD）仍是婴幼儿发病率和死亡率的主要原因，而无创筛查常出现假阴性。深度学习模型可自动提取特征，帮助医生更有效地识别CHD。本文研究了结合心音与胸部X光片的双模态深度学习方法。在ZCHSound数据集上取得73.9%的准确率，在DICOM胸部X光数据集上达到80.72%的准确率。
原文摘要 · Abstract (English)
Congenital Heart Disease (CHD) remains a leading cause of infant morbidity and mortality, yet non-invasive screening methods often yield false negatives. Deep learning models, with their ability to automatically extract features, can assist doctors in detecting CHD more effectively. In this work, we investigate the use of dual-modality (sound and image) deep learning methods for CHD diagnosis. We achieve 73.9% accuracy on the ZCHSound dataset and 80.72% accuracy on the DICOM Chest X-ray dataset.
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。