Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( 🔒 ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Need Help

SCH: Four-Chamber Cardiac Anatomy and Flow Field Inference from Patient Echocardiography for Improved Cardiac Disease Diagnosis

Award Number: R01HL192617
ORGANIZATION: NATIONAL HEART, LUNG, & BLOOD INSTITUTE
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)
PERIOD OF PERFORMANCE START DATE: 09/20/2026
PERIOD OF PERFORMANCE END DATE: 06/30/2030

Group Awards By:

View Award Description

SCH: Four-Chamber Cardiac Anatomy and Flow Field Inference from Patient Echocardiography for Improved Cardiac Disease Diagnosis - Echocardiography (echo) is the most widely used imaging modality for cardiac assessment, providing real time bedside evaluation of cardiac structure and blood flow. However, its diagnostic power remains limited by variable image quality, probe angle–dependent fields of view, operator dependence, and sparse, noisy velocity measurements. Conventional practice often reduces interpretation to single-chamber motion evaluation or oversimplified global indices, overlooking the integrated physiology of detailed four-chamber interactions and intracardiac flow patterns. These limitations are especially important in acute cardiac disease, where timely differentiation of conditions with overlapping clinical presentations, such as Takotsubo syndrome (TTS) and acute myocardial infarction (AMI), remains challenging. Leveraging a large-scale retrospective multi-view echo dataset, this project will develop an integrated ML framework that infers patient-specific four-chamber anatomy, motion, and intracardiac flow dynamics directly from routine echocardiograms. These features encode subtle physiological signals for early diagnosis and risk stratification that are currently inaccessible from routine echo; unlocking them may improve diagnostic power and reduce reliance on costly or less accessible imaging modalities. We will also develop interpretable ML-based diagnostic models that incorporate these uncertainty-aware anatomy and flow reconstructions. In Aim 1, we will introduce a hierarchical generative diffusion model to reconstruct dynamic 3D chamber and valve anatomies from routine multi-view 2D echocardiography while accounting for imaging uncertainty. In Aim 2, we will develop generative diffusion models that infer distributions of physiologically consistent intracardiac flow fields constrained by patient-specific anatomy, Doppler measurements, and governing fluid dynamic equations. In Aim 3, we will design interpretable spatiotemporal attention models that integrate anatomy–motion–flow interactions into diagnostic classifiers, identify when and where predictive patterns arise, and propagate reconstruction uncertainty into diagnostic confidence. These contributions move beyond black-box medical AI toward principled, physics-informed, and interpretable models, enabling accurate and uncertainty-aware differentiation of acute cardiac diseases that are often misdiagnosed using current tools. Although the primary validation will focus on TTS and AMI, the methods will be broadly applicable to other cardiac conditions in which anatomy–motion–flow interactions are clinically important. All models and code will be open-sourced to promote transparency, reproducibility, and future research.


Issue Date FY	Funding FY	Legal Entity Name	Legal Entity Address	Legal Entity City	Legal Entity State	Legal Entity Zip Code	Legal Entity COUNTY	Legal Entity COUNTRY	Assistance Listing	Award Code	Budget Year	Action Date	Action Type	Action Amount

Issue Date FY: 2026 ( Subtotal = $313,948 )
2026	2026	WASHINGTON UNIVERSITY, THE	1 BROOKINGS DR	SAINT LOUIS	MO	63130	SAINT LOUIS	USA	Cardiovascular Diseases Research	000	1	9/17/2026	NEW	$313,948
														Subtotal = $313,948

Grand Total All Awards = $313,948

Top

All Categories

About

Search

Reports

Data Submission

Award Information

SCH: Four-Chamber Cardiac Anatomy and Flow Field Inference from Patient Echocardiography for Improved Cardiac Disease Diagnosis

Award Number: R01HL192617

ORGANIZATION: NATIONAL HEART, LUNG, & BLOOD INSTITUTE

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)

PERIOD OF PERFORMANCE START DATE: 09/20/2026

PERIOD OF PERFORMANCE END DATE: 06/30/2030

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer