CardioComposer: Flexible and Compositional Anatomical Structure Generation with Disentangled Geometric Guidance

• URL: http://arxiv.org/abs/2509.08015v1
• Date: Mon, 08 Sep 2025 23:08:23 GMT
• Title: CardioComposer: Flexible and Compositional Anatomical Structure Generation with Disentangled Geometric Guidance
• Authors: Karim Kadry, Shoaib Goraya, Ajay Manicka, Abdalla Abdelwahed, Farhad Nezami, Elazer Edelman,
• Abstract summary: We propose a framework for guiding unconditional diffusion models of human anatomy using interpretable ellipsoidal primitives embedded in 3D space.<n>Our method involves the selection of certain tissues within multi-tissue segmentation maps, upon which we apply geometric moment losses to guide the reverse diffusion process.
• Score: 0.6312872285702812
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative models of 3D anatomy, when integrated with biophysical simulators, enable the study of structure-function relationships for clinical research and medical device design. However, current models face a trade-off between controllability and anatomical realism. We propose a programmable and compositional framework for guiding unconditional diffusion models of human anatomy using interpretable ellipsoidal primitives embedded in 3D space. Our method involves the selection of certain tissues within multi-tissue segmentation maps, upon which we apply geometric moment losses to guide the reverse diffusion process. This framework supports the independent control over size, shape, and position, as well as the composition of multi-component constraints during inference.

Related papers

• Anatomica: Localized Control over Geometric and Topological Properties for Anatomical Diffusion Models [0.6011425044728357]
  Anatomica is an inference-time framework for generating anatomical voxel maps with localized geo-topological control.<n>We control geometric features such as size, shape, and position through voxel-wise moments, while topological features such as connected components, loops, and voids are enforced through persistent homology.<n>Anatomica applies flexibly across diverse anatomical systems, composing constraints to control complex structures over arbitrary dimensions and coordinate systems.
  arXiv  Detail & Related papers  (2025-11-25T18:18:16Z)
• PrIntMesh: Precise Intersection Surfaces for 3D Organ Mesh Reconstruction [37.06867816829073]
  PrIntMesh is a template-based, topology-preserving framework that reconstructs organs as unified systems.<n>We demonstrate its effectiveness on the heart, hippocampus, and lungs.
  arXiv  Detail & Related papers  (2025-11-20T09:50:56Z)
• GRASPing Anatomy to Improve Pathology Segmentation [67.98147643529309]
  We introduce GRASP, a modular plug-and-play framework that enhances pathology segmentation models.<n>We evaluate GRASP on two PET/CT datasets, conduct systematic ablation studies, and investigate the framework's inner workings.
  arXiv  Detail & Related papers  (2025-08-05T12:26:36Z)
• CA-Diff: Collaborative Anatomy Diffusion for Brain Tissue Segmentation [9.51662728609265]
  Collaborative Diffusion (CA-Diff) is a framework integrating spatial anatomical features to enhance segmentation accuracy.<n>We introduce distance field as an auxiliary anatomical condition to provide global spatial context.<n>We also introduce a consistency loss to refine relationships between the distance field and anatomical structures.
  arXiv  Detail & Related papers  (2025-06-28T13:39:09Z)
• JADE: Joint-aware Latent Diffusion for 3D Human Generative Modeling [62.77347895550087]
  We introduce JADE, a generative framework that learns the variations of human shapes with fined-grained control.<n>Our key insight is a joint-aware latent representation that decomposes human bodies into skeleton structures.<n>To generate coherent and plausible human shapes under our proposed decomposition, we also present a cascaded pipeline.
  arXiv  Detail & Related papers  (2024-12-29T14:18:35Z)
• A Diffusion Model for Simulation Ready Coronary Anatomy with Morpho-skeletal Control [1.053652600598537]
  We investigate how Latent Diffusion Models can custom synthesize coronary anatomy for virtual intervention studies. Our framework enables the generation and editing of coronary anatomy in a controllable manner, allowing device designers to derive mechanistic insights.
  arXiv  Detail & Related papers  (2024-07-22T13:44:06Z)
• Anatomy-guided Pathology Segmentation [56.883822515800205]
  We develop a generalist segmentation model that combines anatomical and pathological information, aiming to enhance the segmentation accuracy of pathological features. Our Anatomy-Pathology Exchange (APEx) training utilizes a query-based segmentation transformer which decodes a joint feature space into query-representations for human anatomy. In doing so, we are able to report the best results across the board on FDG-PET-CT and Chest X-Ray pathology segmentation tasks with a margin of up to 3.3% as compared to strong baseline methods.
  arXiv  Detail & Related papers  (2024-07-08T11:44:15Z)
• Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation [56.34634121544929]
  In this study, we first construct the brain-effective network via the dynamic causal model. We then introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE) This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks.
  arXiv  Detail & Related papers  (2024-05-21T20:37:07Z)
• 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)
• Shape of my heart: Cardiac models through learned signed distance functions [33.29148402516714]
  In this work, the cardiac shape is reconstructed by means of three-dimensional deep signed distance functions with Lipschitz regularity. For this purpose, the shapes of cardiac MRI reconstructions are learned to model the spatial relation of multiple chambers. We demonstrate that this approach is also capable of reconstructing anatomical models from partial data, such as point clouds from a single ventricle.
  arXiv  Detail & Related papers  (2023-08-31T09:02:53Z)
• Pairwise-Constrained Implicit Functions for 3D Human Heart Modelling [60.56741715207466]
  We introduce a pairwise-constrained SDF approach that models the heart as a set of interdependent SDFs.<n>Our method significantly improves inner structure accuracy over single-SDF, UDF-based, voxel-based, and segmentation-based reconstructions.
  arXiv  Detail & Related papers  (2023-07-16T10:07:15Z)
• Statistical Shape Modeling of Biventricular Anatomy with Shared Boundaries [16.287876512923084]
  This paper presents a general and flexible data-driven approach for building statistical shape models of multi-organ anatomies with shared boundaries. Shape changes within these shared boundaries of the heart can indicate potential pathological changes that lead to uncoordinated contraction and poor end-organ perfusion.
  arXiv  Detail & Related papers  (2022-09-06T15:54:37Z)

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.