From Pixels to Polygons

A survey of deep learning approaches for medical image-to-mesh reconstruction

Medical Image Analysis · Survey

From Pixels to Polygons

A visual survey of deep learning approaches that reconstruct anatomical meshes directly from medical images, bridging imaging, geometric modelling, and simulation-ready digital anatomy.

Fengming Lin, Arezoo Zakeri, Yidan Xue, Michael MacRaild, Haoran Dou, Zherui Zhou, Ziwei Zou, Ali Sarrami-Foroushani, Jinming Duan, Alejandro F. Frangi*

4
method families
12
subcategories
3
core challenge axes

Drag to compare benchmark landscapes

Brain MR reconstruction benchmark summary
Cardiac MR reconstruction benchmark summary
Brain MR
Cardiac MR

A Neuralangelo-style comparison block for this project page: move the slider between the cortical and cardiac meta-analysis figures.

Project video

A short overview of the survey. The embedded player keeps the browser's native controls enabled so visitors can drag the progress bar, adjust volume, and switch to fullscreen.

Overview video. The video is configured to attempt autoplay on page load and keeps the native controls enabled for seeking.

Autoplay with sound may be blocked by some browsers. If that happens, press play once and the video will continue normally with audio.
At a glance. The survey organizes end-to-end medical image-to-mesh reconstruction into four paradigms—template models, statistical shape models, generative models, and implicit models—then links these families to losses, evaluation metrics, public datasets, clinical use cases, and open research problems.

Why image-to-mesh reconstruction matters

In computational medicine and in-silico trials, image-to-mesh reconstruction is the bridge between medical imaging and numerical simulation. The paper emphasizes a shift from segmentation-heavy pipelines toward models that directly predict geometrically meaningful mesh representations from CT, MR, ultrasound, projections, or sparse point observations.

Patient-specific meshes are more than a visualization layer. They are the structural backbone for downstream tasks such as hemodynamic simulation, structural mechanics, virtual device testing, motion analysis, and digital twin generation. When mesh quality is poor, simulation quality suffers too.

That is why the survey treats reconstruction as a full pipeline problem: input modality, representation, topology, regularization, and evaluation all matter. The most compelling methods are not only accurate against ground truth, but also stable, anatomically plausible, and ready for computation.

Inputs: CT, MR, ultrasound, 2D projections, sparse contours, point clouds, and videos.
Outputs: Surface meshes, point clouds, implicit fields, and simulation-ready geometric models.
Applications: Heart, cortex, vessels, abdominal organs, skull repair, endoscopy, and fetal imaging.
In-silico trial pipeline for image-to-mesh reconstruction

In-silico trial pipeline. Medical images feed reconstruction, generation, and simulation stages. This figure captures why anatomical meshing matters beyond segmentation: it is the geometric substrate for downstream evidence generation.

Survey map

The paper provides a unified taxonomy that connects methodology, input modality, output representation, and evaluation strategy. It also makes the field easier to navigate by splitting it into four families and twelve subcategories.

Taxonomy of deep learning medical image to mesh reconstruction

Taxonomy of the field. Template models, statistical shape models, generative models, and implicit models are connected to input type, feature representation, output form, and evaluation design.

Template

Template models

Start from an initial mesh and learn how to deform it into the target anatomy.

  • Strong control over topology
  • Good fit for stable anatomical priors
  • Conditioned deformation and registration variants
SSM

Statistical shape models

Use low-dimensional shape priors to constrain reconstruction around plausible anatomical variation.

  • Linear and non-linear latent spaces
  • Robustness to noisy data
  • Especially useful when strong population priors exist
Generative

Generative models

Synthesize shapes directly from data distributions rather than relying on a fixed template.

  • VAE, GAN, interpolation, and diffusion families
  • Adapt well to diverse or pathological shapes
  • Useful when completion or synthesis matters
Implicit

Implicit models

Represent anatomy through continuous functions such as SDFs, occupancy fields, Neural ODEs, or NeRF-style densities.

  • High-resolution and continuous surfaces
  • Flexible topology
  • Strong overall robustness in the meta-analysis

Representative formulations

Rather than showing every method in the paper, the page highlights a compact set of schematics that capture how the main families are typically formulated.

Conditioned deformation model schematic

Conditioned deformation. CNN features are transferred to a graph network that deforms a template mesh while preserving a known topological scaffold.

Template based registration schematic

Template-based registration. A learned deformation field aligns a template representation with the target anatomy, connecting image registration and mesh generation.

Linear statistical shape model schematic

Linear SSM. A PCA/SVD block predicts coefficients in a low-dimensional statistical basis, turning image evidence into a structured shape prior.

Non-Linear statistical shape model schematic

Non-Linear SSM. A deep encoder predicts coefficients in a low-dimensional statistical basis, turning image evidence into a structured shape prior.

Generative completion based mesh reconstruction schematic

Completion-based generative model. Sparse contours or points are densified into complete point clouds before meshing, making generative completion central to reconstruction.

Neural ODE based implicit reconstruction schematic

Implicit flow / Neural ODE. Continuous deformation dynamics provide smooth trajectories and strong geometric regularity for complex anatomical surfaces.

What the survey finds

The meta-analysis compares method categories on cardiac and cortical benchmarks. The key message is not that one family always wins, but that different families dominate under different anatomical and geometric constraints.

Meta-analysis

Relative trend across the reviewed studies

Implicit models > Generative models > Statistical shape models > Template models

The paper frames this as a relative trend rather than an absolute rule. Anatomy, modality, topology, supervision, and simulation requirements can still change which model family is best for a specific task.

Trade-offs

Why the ranking is not the whole story

  • Template: controlled topology and simulation-friendly priors
  • SSM: strong regularization from population anatomy
  • Generative: flexibility for diverse and pathological shapes
  • Implicit: continuous, high-resolution, topology-flexible surfaces
Cardiac MR / CT / echo Cortical MR Thoracic and abdominal CT Vascular ultrasound and angiography Skull and musculoskeletal CT Endoscopic reconstruction

Metrics, datasets, and evidence base

One strength of the survey is that it does not stop at method taxonomy. It also systematizes the losses, evaluation metrics, and public datasets that shape experimental practice in this field.

PRISMA review process figure

PRISMA-guided review process. The survey follows a systematic review structure to define inclusion, screening, and analysis.

Evaluation

Metrics span geometry, topology, and function

  • Shape similarity: Chamfer, Hausdorff, ASSD, MSD, Dice, IoU, normal consistency
  • Regularization: smoothness, curvature, self-intersection, topology, edge quality
  • Functional utility: ejection fraction, disease prediction, CFD velocity, kinetic energy
  • Efficiency: inference time and simulation readiness
Coverage

Datasets span many organs and modalities

The paper curates datasets across cardiac imaging, brain MRI, thoracic and abdominal CT, skull reconstruction, endoscopy, microscopy, fetal ultrasound, and more. That breadth is valuable because it connects reconstruction design choices to anatomy and clinical use.

Open challenges and future directions

The field is moving toward higher-fidelity, more topology-aware, and more simulation-ready reconstruction. The paper frames the future around a few central tensions: topology, geometric fidelity, multi-modality, and computational usability.

Challenges for medical image to mesh reconstruction

Challenge map. Topological requirements, geometric accuracy, and multi-modality integration determine which reconstruction strategy is most appropriate for a given medical task.

Topology

Mesh validity still matters

Simulation-ready models require connectivity, manifoldness, and low self-intersection, especially for anatomy where downstream solvers are sensitive to geometric artifacts.

Fidelity

Fine detail is clinically meaningful

Thin walls, folds, bifurcations, and device-relevant structures push models toward higher-resolution and more continuous representations.

Fusion

Multi-modal and dynamic data are rising

CT, MR, ultrasound, sparse views, and time-varying sequences increasingly need to be integrated into a single reconstruction framework.

Looking ahead. The survey points toward higher-fidelity implicit reconstruction, stronger topology-aware training, multi-modal fusion, volume mesh generation for biomechanics, and the transfer of fast neural surface reconstruction ideas into medical imaging.

Citation

Show BibTeX
@article{lin2026pixels,
  title   = {From Pixels to Polygons: A Survey of Deep Learning Approaches for Medical Image-to-Mesh Reconstruction},
  author  = {Lin, Fengming and Zakeri, Arezoo and Xue, Yidan and MacRaild, Michael and Dou, Haoran and Zhou, Zherui and Zou, Ziwei and Sarrami-Foroushani, Ali and Duan, Jinming and Frangi, Alejandro F.},
  journal = {Medical Image Analysis},
  year    = {2026}
}

References