用混合AI框架提升肺结核和症状的早期检测准确率
An Explainable Hybrid AI Framework for Enhanced Tuberculosis and Symptom Detection
- 结合监督与自监督学习，设计双监督头+自监督头架构
- 疾病分类准确率达98.85%，多标签症状检测宏F1达90.09%
- 模型决策基于关键解剖特征，适合临床筛查部署
肺结核仍是资源匮乏和偏远地区的重要健康挑战。早期检测对治疗至关重要，但缺乏专业放射科医生，亟需人工智能驱动的筛查工具。由于高质量大规模数据集获取成本高，可靠AI模型的开发面临困难。为此，我们提出一种教师-学生框架，通过集成两个监督头和一个自监督头，提升胸片上的疾病与症状检测能力。模型在区分新冠、肺结核与正常病例的分类任务中达到98.85%的准确率，在多标签症状检测上获得90.09%的宏F1分数，显著优于基线方法。可解释性评估表明，模型预测依赖于相关解剖区域，展现出在临床筛查与分诊场景中的应用潜力。
原文摘要 · Abstract (English)
Tuberculosis remains a critical global health issue, particularly in resource-limited and remote areas. Early detection is vital for treatment, yet the lack of skilled radiologists underscores the need for artificial intelligence (AI)-driven screening tools. Developing reliable AI models is challenging due to the necessity for large, high-quality datasets, which are costly to obtain. To tackle this, we propose a teacher--student framework which enhances both disease and symptom detection on chest X-rays by integrating two supervised heads and a self-supervised head. Our model achieves an accuracy of 98.85% for distinguishing between COVID-19, tuberculosis, and normal cases, and a macro-F1 score of 90.09% for multilabel symptom detection, significantly outperforming baselines. The explainability assessments also show the model bases its predictions on relevant anatomical features, demonstrating promise for deployment in clinical screening and triage settings.
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。