Anatomica: Localized Control over Geometric and Topological Properties for Anatomical Diffusion Models

• URL: http://arxiv.org/abs/2511.20587v1
• Date: Tue, 25 Nov 2025 18:18:16 GMT
• Title: Anatomica: Localized Control over Geometric and Topological Properties for Anatomical Diffusion Models
• Authors: Karim Kadry, Abdallah Abdelwahed, Shoaib Goraya, Ajay Manicka, Naravich Chutisilp, Farhad Nezami, Elazer Edelman,
• Abstract summary: 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.
• Score: 0.6011425044728357
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Anatomica: an inference-time framework for generating multi-class anatomical voxel maps with localized geo-topological control. During generation, we use cuboidal control domains of varying dimensionality, location, and shape to slice out relevant substructures. These local substructures are used to compute differentiable penalty functions that steer the sample towards target constraints. 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. Lastly, we implement Anatomica for latent diffusion models, where neural field decoders partially extract substructures, enabling the efficient control of anatomical properties. Anatomica applies flexibly across diverse anatomical systems, composing constraints to control complex structures over arbitrary dimensions and coordinate systems, thereby enabling the rational design of synthetic datasets for virtual trials or machine learning workflows.

Related papers

• 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)
• CardioComposer: Flexible and Compositional Anatomical Structure Generation with Disentangled Geometric Guidance [0.6312872285702812]
  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.
  arXiv  Detail & Related papers  (2025-09-08T23:08:23Z)
• Deformable registration and generative modelling of aortic anatomies by auto-decoders and neural ODEs [4.299467172990462]
  This work introduces AD-SVFD, a deep learning model for the registration of shapes to a pre-defined reference and for the generation of synthetic anatomies.<n>A distinctive feature of AD-SVFD is its auto-decoder structure, that enables generalization across shape cohorts and favors efficient weight sharing.<n>The use of implicit shape representations enables generative applications: new anatomies can be synthesized by suitably sampling from the latent space and applying the corresponding inverse transformations to the reference geometry.
  arXiv  Detail & Related papers  (2025-06-01T10:30:58Z)
• 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)
• 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)
• 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)
• 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)
• NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go [109.88509362837475]
  We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes. NeuroMorph produces smooth and point-to-point correspondences between them. It works well for a large variety of input shapes, including non-isometric pairs from different object categories.
  arXiv  Detail & Related papers  (2021-06-17T12:25:44Z)
• The role of feature space in atomistic learning [62.997667081978825]
  Physically-inspired descriptors play a key role in the application of machine-learning techniques to atomistic simulations. We introduce a framework to compare different sets of descriptors, and different ways of transforming them by means of metrics and kernels. We compare representations built in terms of n-body correlations of the atom density, quantitatively assessing the information loss associated with the use of low-order features.
  arXiv  Detail & Related papers  (2020-09-06T14:12:09Z)
• LORCK: Learnable Object-Resembling Convolution Kernels [1.853658628381862]
  We propose a new class of hollow kernels that learn'mimic the contours of the segmented organ. We train a series of U-Net-like neural networks using the proposed kernels and demonstrate the superiority of the idea in various-temporal convolution scenarios. Our results pave the way towards other domain-specific deep learning applications.
  arXiv  Detail & Related papers  (2020-07-09T23:17:40Z)

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.