Towards 3D heart mesh generation using contactless radar imaging and physics-informed neural network
2026-05-25 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method called SAR2Mesh to create detailed 3D models of the heart using millimeter-wave radar images, which are tricky because the images are noisy and incomplete. Instead of just using traditional radar data or optical methods, their approach starts with a basic heart shape and gradually adjusts it to fit the radar data better. They also created a special way to compare the radar signals with their 3D model to make sure it matches the physical measurements. Their results show that this method works better than previous ways at accurately capturing heart shapes in 3D.
millimeter-wave radarSynthetic Aperture Radar (SAR)3D cardiac geometrymesh deformationspeckle noisefeature projectionphysics-informed losstopological templatepoint cloudsCardiac Mesh-SAR dataset
Authors
Jinye Li, Chenxi Fu, Minghang Zheng, Yang Liu, Xiahai Zhuang, Qingchao Chen
Abstract
Cardiac function evaluation necessitates continuous, non-invasive monitoring, a capability limited in MRI. Millimeter-wave (mmWave) radar and its Synthetic Aperture Radar (SAR) mode offer a privacy-preserving and portable point-of-care clinical applications. However, reconstructing high-fidelity 3D cardiac geometry from SAR remains an open challenge. Traditional radar methods generate sparse point clouds that lack continuous surface topology. Meanwhile, direct application of optical reconstruction networks performs poorly due to the severe speckle noise and ambiguous boundaries inherent in SAR images. To bridge this gap, we propose SAR2Mesh, a novel framework that reformulates the task as a coarse-to-fine mesh deformation process. By initializing with a topological template, our approach explicitly preserves anatomical connectivity through progressive mesh deformation.We introduce a geometry-aware feature projection module to extract multi-view features via 3D-to-2D sampling, and a physics-informed radar loss to enforce consistency between the predicted geometry and raw radar echoes. Furthermore, we present Cardiac Mesh-SAR, the first large-scale paired SAR-mesh dataset. Extensive experiments demonstrate that SAR2Mesh significantly outperforms existing image-based baselines, achieving accurate and physically consistent cardiac reconstructions.