Reliable Multi-View Learning with Conformal Prediction for Aortic Stenosis Classification in Echocardiography
This work addresses the challenge of unreliable ultrasound-based diagnosis for clinicians by enhancing existing classification methods, though it is incremental as it builds on prior techniques.
The paper tackles the problem of uncertainty in ultrasound echocardiography for aortic stenosis classification by proposing RT4U, a data-centric method that introduces uncertainty to weakly informative inputs, which improves accuracy across three datasets when combined with conformal prediction.
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.