PRECISE-AS: Personalized Reinforcement Learning for Efficient Point-of-Care Echocardiography in Aortic Stenosis Diagnosis

• URL: http://arxiv.org/abs/2509.02898v1
• Date: Tue, 02 Sep 2025 23:47:43 GMT
• Title: PRECISE-AS: Personalized Reinforcement Learning for Efficient Point-of-Care Echocardiography in Aortic Stenosis Diagnosis
• Authors: Armin Saadat, Nima Hashemi, Hooman Vaseli, Michael Y. Tsang, Christina Luong, Michiel Van de Panne, Teresa S. M. Tsang, Purang Abolmaesumi,
• Abstract summary: Aortic stenosis (AS) is a life-threatening condition caused by a narrowing of the aortic valve, leading to impaired blood flow.<n>Access to echocardiography (echo) is often limited due to resource constraints, particularly in rural and underserved areas.<n>We propose a reinforcement learning (RL)-driven active video acquisition framework that dynamically selects each patient's most informative echo videos.
• Score: 6.276251898178271
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Aortic stenosis (AS) is a life-threatening condition caused by a narrowing of the aortic valve, leading to impaired blood flow. Despite its high prevalence, access to echocardiography (echo), the gold-standard diagnostic tool, is often limited due to resource constraints, particularly in rural and underserved areas. Point-of-care ultrasound (POCUS) offers a more accessible alternative but is restricted by operator expertise and the challenge of selecting the most relevant imaging views. To address this, we propose a reinforcement learning (RL)-driven active video acquisition framework that dynamically selects each patient's most informative echo videos. Unlike traditional methods that rely on a fixed set of videos, our approach continuously evaluates whether additional imaging is needed, optimizing both accuracy and efficiency. Tested on data from 2,572 patients, our method achieves 80.6% classification accuracy while using only 47% of the echo videos compared to a full acquisition. These results demonstrate the potential of active feature acquisition to enhance AS diagnosis, making echocardiographic assessments more efficient, scalable, and personalized. Our source code is available at: https://github.com/Armin-Saadat/PRECISE-AS.

Related papers

• VA-Adapter: Adapting Ultrasound Foundation Model to Echocardiography Probe Guidance [57.43511837589102]
  We adapt medical knowledge learned by foundation models from vast datasets to the probe guidance task.<n>We meticulously design a parameter-efficient Vision-Action Adapter (VA-Adapter) to enable foundation model's image encoder to encode vision-action sequences.<n>With built-in sequential reasoning capabilities in a compact design, the VA-Adapter enables a pre-trained ultrasound foundation model to learn precise probe adjustment strategies.
  arXiv  Detail & Related papers  (2025-10-08T09:38:30Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Patient-specific radiomic feature selection with reconstructed healthy persona of knee MR images [39.11295870085984]
  Classical radiomic features have been designed to describe image appearance and intensity patterns.<n>Lower dimensional parametric models that use such radiomic features offer enhanced interpretability but lower comparative performance in clinical tasks.<n>We propose an approach where a standard logistic regression model performance is substantially improved by learning to select radiomic features for individual patients.
  arXiv  Detail & Related papers  (2025-03-17T12:55:43Z)
• Class-Aware Cartilage Segmentation for Autonomous US-CT Registration in Robotic Intercostal Ultrasound Imaging [39.597735935731386]
  A class-aware cartilage bone segmentation network with geometry-constraint post-processing is presented to capture patient-specific rib skeletons. A dense skeleton graph-based non-rigid registration is presented to map the intercostal scanning path from a generic template to individual patients. Results demonstrate that the proposed graph-based registration method can robustly and precisely map the path from CT template to individual patients.
  arXiv  Detail & Related papers  (2024-06-06T14:15:15Z)
• Goal-conditioned reinforcement learning for ultrasound navigation guidance [4.648318344224063]
  We propose a novel ultrasound navigation assistance method based on contrastive learning as goal-conditioned reinforcement learning (G) We augment the previous framework using a novel contrastive patient method (CPB) and a data-augmented contrastive loss. Our method was developed with a large dataset of 789 patients and obtained an average error of 6.56 mm in position and 9.36 degrees in angle.
  arXiv  Detail & Related papers  (2024-05-02T16:01:58Z)
• Echocardiogram Foundation Model -- Application 1: Estimating Ejection Fraction [2.4164193358532438]
  We introduce EchoAI, an echocardiogram foundation model, that is trained using self-supervised learning (SSL) on 1.5 million echocardiograms. We evaluate our approach by fine-tuning EchoAI to estimate the ejection fraction achieving a mean absolute percentage error of 9.40%.
  arXiv  Detail & Related papers  (2023-11-21T13:00:03Z)
• Deep denoising autoencoder-based non-invasive blood flow detection for arteriovenous fistula [10.030431512848239]
  We propose an approach based on deep denoising autoencoders (DAEs) that perform dimensionality reduction and reconstruction tasks. Our results demonstrate that the latent representation generated by the DAE surpasses expectations with an accuracy of 0.93. The incorporation of noise-mixing and the utilization of a noise-to-clean scheme effectively enhance the discriminative capabilities of the latent representation.
  arXiv  Detail & Related papers  (2023-06-12T04:46:01Z)
• Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis [48.64462717254158]
  We developed a self-supervised contrastive learning approach, EchoCLR, to catered to echocardiogram videos. When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improved classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) EchoCLR is unique in its ability to learn representations of medical videos and demonstrates that SSL can enable label-efficient disease classification from small, labeled datasets.
  arXiv  Detail & Related papers  (2022-07-23T19:17:26Z)
• Know your sensORs $\unicode{x2013}$ A Modality Study For Surgical Action Classification [39.546197658791]
  The medical community seeks to leverage this wealth of data to develop automated methods to advance interventional care, lower costs, and improve patient outcomes. Existing datasets from OR room cameras are thus far limited in size or modalities acquired, leaving it unclear which sensor modalities are best suited for tasks such as recognizing surgical action from videos. This study demonstrates that surgical action recognition performance can vary depending on the image modalities used.
  arXiv  Detail & Related papers  (2022-03-16T15:01:17Z)
• A Deep Learning Approach to Predicting Collateral Flow in Stroke Patients Using Radiomic Features from Perfusion Images [58.17507437526425]
  Collateral circulation results from specialized anastomotic channels which provide oxygenated blood to regions with compromised blood flow. The actual grading is mostly done through manual inspection of the acquired images. We present a deep learning approach to predicting collateral flow grading in stroke patients based on radiomic features extracted from MR perfusion data.
  arXiv  Detail & Related papers  (2021-10-24T18:58:40Z)
• Segmentation-free Heart Pathology Detection Using Deep Learning [12.065014651638943]
  We propose a novel segmentation-free heart sound classification method. Specifically, we apply discrete wavelet transform to denoise the signal, followed by feature extraction and feature reduction. Support Vector Machines and Deep Neural Networks are utilised for classification.
  arXiv  Detail & Related papers  (2021-08-09T16:09:30Z)
• Predicting post-operative right ventricular failure using video-based deep learning [9.884447146588542]
  We develop a video AI system trained to predict post-operative right ventricular failure (RV failure) using the full density of information from pre-operative echocardiography scans. We achieve an temporal acuity of 0.729, specificity of 52% at 80% sensitivity and sensitivity at 80% specificity. Furthermore, we show that our ML system significantly outperforms a team of human experts tasked with predicting RV failure on independent clinical evaluation.
  arXiv  Detail & Related papers  (2021-02-28T00:58:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.