High-Fidelity Medical Shape Generation via Skeletal Latent Diffusion

• URL: http://arxiv.org/abs/2603.07504v3
• Date: Thu, 12 Mar 2026 13:57:32 GMT
• Title: High-Fidelity Medical Shape Generation via Skeletal Latent Diffusion
• Abstract summary: We propose a skeletal latent diffusion framework for efficient and high-fidelity medical shape generation.<n>New shapes are generated via a latent-space diffusion model, followed by neural implicit decoding and mesh extraction.<n>Experiments on MedSDF and vessel datasets demonstrate that the proposed method achieves superior reconstruction and generation quality.
• Score: 10.218375997417917
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Anatomy shape modeling is a fundamental problem in medical data analysis. However, the geometric complexity and topological variability of anatomical structures pose significant challenges to accurate anatomical shape generation. In this work, we propose a skeletal latent diffusion framework that explicitly incorporates structural priors for efficient and high-fidelity medical shape generation. We introduce a shape auto-encoder in which the encoder captures global geometric information through a differentiable skeletonization module and aggregates local surface features into shape latents, while the decoder predicts the corresponding implicit fields over sparsely sampled coordinates. New shapes are generated via a latent-space diffusion model, followed by neural implicit decoding and mesh extraction. To address the limited availability of medical shape data, we construct a large-scale dataset, \textit{MedSDF}, comprising surface point clouds and corresponding signed distance fields across multiple anatomical categories. Extensive experiments on MedSDF and vessel datasets demonstrate that the proposed method achieves superior reconstruction and generation quality while maintaining a higher computational efficiency compared with existing approaches. Code is available at: https://github.com/wlsdzyzl/meshage.

Related papers

• Shape-informed cardiac mechanics surrogates in data-scarce regimes via geometric encoding and generative augmentation [3.03918153717041]
  Surrogate models can accelerate simulations, but generalization across diverse anatomies is challenging.<n>We propose a two-step framework that decouples geometric representation from learning the physics response.<n>We show that the proposed approaches allow for accurate predictions and generalization to unseen geometries.
  arXiv  Detail & Related papers  (2026-02-23T19:40:55Z)
• Data-Efficient Meningioma Segmentation via Implicit Spatiotemporal Mixing and Sim2Real Semantic Injection [6.992254817538211]
  We propose a novel dual-augmentation framework that integrates spatial manifold expansion and semantic object injection.<n>We show that our framework significantly enhances the data efficiency and robustness of state-of-the-art models, including nnU-Net and U-Mamba.
  arXiv  Detail & Related papers  (2026-01-19T09:11:28Z)
• An End-to-End Deep Learning Generative Framework for Refinable Shape Matching and Generation [45.820901263103806]
  Generative modelling for shapes is a prerequisite for In-Silico Clinical Trials (ISCTs) We develop a novel unsupervised geometric deep-learning model to establish refinable shape correspondences in a latent space. We extend our proposed base model to a joint shape generative-clustering multi-atlas framework to incorporate further variability.
  arXiv  Detail & Related papers  (2024-03-10T21:33:53Z)
• ReshapeIT: Reliable Shape Interaction with Implicit Template for Anatomical Structure Reconstruction [59.971808117043366]
  ReShapeIT represents an anatomical structure with an implicit template field shared within the same category. It ensures the implicit template field generates valid templates by strengthening the constraint of the correspondence between the instance shape and the template shape. A template Interaction Module is introduced to reconstruct unseen shapes by interacting the valid template shapes with the instance-wise latent codes.
  arXiv  Detail & Related papers  (2023-12-11T07:09:32Z)
• Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models [83.35835521670955]
  Surf-D is a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies. We use the Unsigned Distance Field (UDF) as our surface representation to accommodate arbitrary topologies. We also propose a new pipeline that employs a point-based AutoEncoder to learn a compact and continuous latent space for accurately encoding UDF.
  arXiv  Detail & Related papers  (2023-11-28T18:56:01Z)
• Abdominal organ segmentation via deep diffeomorphic mesh deformations [5.4173776411667935]
  Abdominal organ segmentation from CT and MRI is an essential prerequisite for surgical planning and computer-aided navigation systems. We employ template-based mesh reconstruction methods for joint liver, kidney, pancreas, and spleen segmentation. The resulting method, UNetFlow, generalizes well to all four organs and can be easily fine-tuned on new data.
  arXiv  Detail & Related papers  (2023-06-27T14:41:18Z)
• T1: Scaling Diffusion Probabilistic Fields to High-Resolution on Unified Visual Modalities [69.16656086708291]
  Diffusion Probabilistic Field (DPF) models the distribution of continuous functions defined over metric spaces. We propose a new model comprising of a view-wise sampling algorithm to focus on local structure learning. The model can be scaled to generate high-resolution data while unifying multiple modalities.
  arXiv  Detail & Related papers  (2023-05-24T03:32:03Z)
• S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences [91.48841778012782]
  We propose an unsupervised method to simultaneously learn local and global shape structures across population anatomies. Our pipeline significantly improves unsupervised correspondence estimation for SSMs compared to baseline methods. Our method is robust enough to learn from noisy neural network predictions, potentially enabling scaling SSMs to larger patient populations.
  arXiv  Detail & Related papers  (2023-04-15T09:39:52Z)
• A Generative Shape Compositional Framework to Synthesise Populations of Virtual Chimaeras [52.33206865588584]
  We introduce a generative shape model for complex anatomical structures, learnable from datasets of unpaired datasets. We build virtual chimaeras from databases of whole-heart shape assemblies that each contribute samples for heart substructures. Our approach significantly outperforms a PCA-based shape model (trained with complete data) in terms of generalisability and specificity.
  arXiv  Detail & Related papers  (2022-10-04T13:36:52Z)
• SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection [76.01333073259677]
  We propose the use of Space-aware Memory Queues for In-painting and Detecting anomalies from radiography images (abbreviated as SQUID) We show that SQUID can taxonomize the ingrained anatomical structures into recurrent patterns; and in the inference, it can identify anomalies (unseen/modified patterns) in the image.
  arXiv  Detail & Related papers  (2021-11-26T13:47:34Z)
• Discriminative and Generative Models for Anatomical Shape Analysison Point Clouds with Deep Neural Networks [3.7814216736076434]
  We introduce deep neural networks for the analysis of anatomical shapes that learn a low-dimensional shape representation from the given task. Our framework is modular and consists of several computing blocks that perform fundamental shape processing tasks. We propose a discriminative model for disease classification and age regression, as well as a generative model for the accruate reconstruction of shapes.
  arXiv  Detail & Related papers  (2020-10-02T07:37:40Z)

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.