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

arXiv: https://arxiv.org/abs/2307.14433 · HTML: https://mlsanity.com/paper/2307.14433/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 26 Jul 2023.

## Builds on (most cited first, 12 of 12)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Interpretable and Accurate Fine-grained Recognition via Region Grouping](https://mlsanity.com/paper/2005.10411/) (2020)
- [XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations](https://mlsanity.com/paper/2103.10663/) (2021)
- [A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms](https://mlsanity.com/paper/2108.00080/) (2021)
- [On Modelling Label Uncertainty in Deep Neural Networks: Automatic Estimation of Intra-observer Variability in 2D Echocardiography Quality Assessment](https://mlsanity.com/paper/1911.00674/) (2019)
- [INSightR-Net: Interpretable Neural Network for Regression using Similarity-based Comparisons to Prototypical Examples](https://mlsanity.com/paper/2208.00457/) (2022)
- [Hierarchical Explanations for Video Action Recognition](https://mlsanity.com/paper/2301.00436/) (2023)

## Built on by (most cited first, 11 of 11)

- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [Semi-Supervised Multimodal Multi-Instance Learning for Aortic Stenosis Diagnosis](https://mlsanity.com/paper/2403.06024/) (2024)
- [ProtoAL: Interpretable Deep Active Learning with prototypes for medical imaging](https://mlsanity.com/paper/2404.04736/) (2024)
- [Reliable Multi-View Learning with Conformal Prediction for Aortic Stenosis Classification in Echocardiography](https://mlsanity.com/paper/2409.09680/) (2024)
- [PRECISE-AS: Personalized Reinforcement Learning for Efficient Point-of-Care Echocardiography in Aortic Stenosis Diagnosis](https://mlsanity.com/paper/2509.02898/) (2025)
- [ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiography](https://mlsanity.com/paper/2512.03339/) (2025)
- [Concerning Uncertainty -- A Systematic Survey of Uncertainty-Aware XAI](https://mlsanity.com/paper/2603.26838/) (2026)
- [Optimizing Point-of-Care Ultrasound Video Acquisition for Probabilistic Multi-Task Heart Failure Detection](https://mlsanity.com/paper/2602.13658/) (2026)
- [ProtoTTA: Prototype-Guided Test-Time Adaptation](https://mlsanity.com/paper/2604.15494/) (2026)
- [HypOProto: Hyperbolic Ordinal Prototypes for Left Ventricular Filling Pressure Classification](https://mlsanity.com/paper/2606.19804/) (2026)
- [ProtoPointNet: Prototype-Based Interpretable Classification of 3D Dental Point Clouds with Verifiable Spatial Activations](https://mlsanity.com/paper/2607.12335/) (2026)

## Abstract (arXiv)

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% and 79.7%, respectively. Furthermore, ProtoASNet provides 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: https://github.com/hooman007/ProtoASNet.