ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography

by   Hooman Vaseli, et al.

Aortic stenosis (AS) is a common heart valve disease that requires accurate and timely diagnosis for appropriate treatment. Most current automatic AS severity detection methods rely on black-box models with a low level of trustworthiness, which hinders clinical adoption. To address this issue, we propose ProtoASNet, a prototypical network that directly detects AS from B-mode echocardiography videos, while making interpretable predictions based on the similarity between the input and learned spatio-temporal prototypes. This approach provides supporting evidence that is clinically relevant, as the prototypes typically highlight markers such as calcification and restricted movement of aortic valve leaflets. Moreover, ProtoASNet utilizes abstention loss to estimate aleatoric uncertainty by defining a set of prototypes that capture ambiguity and insufficient information in the observed data. This provides a reliable system that can detect and explain when it may fail. We evaluate ProtoASNet on a private dataset and the publicly available TMED-2 dataset, where it outperforms existing state-of-the-art methods with an accuracy of 80.0 interpretability and an uncertainty measure for each prediction, which can improve transparency and facilitate the interactive usage of deep networks to aid clinical decision-making. Our source code is available at:


page 8

page 12

page 13


Probabilistic Concept Bottleneck Models

Interpretable models are designed to make decisions in a human-interpret...

Uncertainty-Aware Multi-Modal Ensembling for Severity Prediction of Alzheimer's Dementia

Reliability in Neural Networks (NNs) is crucial in safety-critical appli...

Don't PANIC: Prototypical Additive Neural Network for Interpretable Classification of Alzheimer's Disease

Alzheimer's disease (AD) has a complex and multifactorial etiology, whic...

A Dataset To Evaluate The Representations Learned By Video Prediction Models

We present a parameterized synthetic dataset called Moving Symbols to su...

EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentation

Active learning algorithms have become increasingly popular for training...

A Lightweight Causal Model for Interpretable Subject-level Prediction

Recent years have seen a growing interest in methods for predicting a va...

Two New Stenoses Detection Methods of Coronary Angiograms

Coronary angiography is the "gold standard" for the diagnosis of coronar...

Please sign up or login with your details

Forgot password? Click here to reset