Reliable Multi-View Learning with Conformal Prediction for Aortic Stenosis Classification in Echocardiography

TL;DR

This paper introduces RT4U, a data-centric method to incorporate uncertainty into training for aortic stenosis classification in echocardiography, enhancing accuracy and providing reliable prediction sets through conformal prediction.

Contribution

The paper proposes RT4U, a novel approach that improves existing classification methods by adding uncertainty modeling, combined with conformal prediction for reliable, adaptively sized prediction sets.

Findings

RT4U improves accuracy across multiple datasets.

Conformal prediction guarantees high-accuracy prediction sets.

Method is effective on diverse datasets including public and private.

Abstract

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.