为超声心动图诊断引入不确定性建模，提升主动脉瓣狭窄分类可靠性
Reliable Multi-View Learning with Conformal Prediction for Aortic Stenosis Classification in Echocardiography
- 通过重训练机制为信息弱的输入样本注入不确定性
- 在三个数据集上均提升分类准确率，且与置信区间方法兼容
- 适合临床辅助诊断系统，尤其关注模型可信度的医疗AI场景
超声心动图常获取心脏三维结构的二维切片，易遗漏关键解剖细节，导致心瓣膜可视化不良或心室短缩。这种固有不确定性在机器学习中常被忽略，仅用单标签标注。本文提出一种数据驱动方法RT4U（Re-Training for Uncertainty），通过重训练为弱信息输入注入不确定性，可无缝集成至现有主动脉瓣狭窄分类模型中以进一步提升性能。结合分位数预测技术后，可生成自适应大小的预测集合，保证高概率包含真实类别。在三个不同数据集上验证：一个公开数据集TMED-2、一个私有主动脉瓣狭窄数据集及一个基于CIFAR-10的模拟数据集，结果表明该方法在所有数据集上均取得性能提升。
原文摘要 · Abstract (English)
The fundamental problem with ultrasound-guided diagnosis is that the acquired images are often 2-D cross-sections of a 3-D anatomy, potentially missing important anatomical details. This limitation leads to challenges in ultrasound echocardiography, such as poor visualization of heart valves or foreshortening of ventricles. Clinicians must interpret these images with inherent uncertainty, a nuance absent in machine learning's one-hot labels. We propose Re-Training for Uncertainty (RT4U), a data-centric method to introduce uncertainty to weakly informative inputs in the training set. This simple approach can be incorporated to existing state-of-the-art aortic stenosis classification methods to further improve their accuracy. When combined with conformal prediction techniques, RT4U can yield adaptively sized prediction sets which are guaranteed to contain the ground truth class to a high accuracy. We validate the effectiveness of RT4U on three diverse datasets: a public (TMED-2) and a private AS dataset, along with a CIFAR-10-derived toy dataset. Results show improvement on all the 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。