Transformation-driven generation of comparable projection images from multimodal anatomical scenes

• URL: http://arxiv.org/abs/2606.16573v1
• Date: Mon, 15 Jun 2026 11:19:10 GMT
• Title: Transformation-driven generation of comparable projection images from multimodal anatomical scenes
• Abstract summary: We propose a transformation-driven framework for synthetic projection imaging from multimodal anatomical data.<n>Independently transformable volumetric and surface-based anatomical objects are embedded within a shared scene representation.<n>Projection geometry, acquisition modelling, material interpretation, and image presentation remain explicitly separated.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work addresses the computational problem of generating reproducible projection-space observations from heterogeneous anatomical scenes whose components may undergo independent spatial transformations. We propose a transformation-driven framework for synthetic projection imaging from multimodal anatomical data and demonstrate it on mandibular-motion scenarios. In contrast to conventional Digitally Reconstructed Radiograph (DRR) approaches primarily designed for registration, projection realism, or rendering efficiency, the proposed formulation treats projection imaging as an observation process operating on an explicitly represented anatomical scene. Independently transformable volumetric and surface-based anatomical objects are embedded within a shared scene representation and propagated directly into projection space through explicit transformations. Projection geometry, acquisition modelling, material interpretation, and image presentation remain explicitly separated, enabling controlled exploration of methodological assumptions while preserving reproducibility and direct comparability between generated projections. Particular emphasis is placed on transformation-driven anatomical scenarios relevant to craniofacial analysis, including mandibular motion and therapeutic repositioning. Using a shared anatomical reference scene composed of CT/CBCT volumes, segmented structures, surface models, and auxiliary anatomical or therapeutic objects, the framework enables generation of directly comparable VirtualRTG projections from multiple anatomical configurations while preserving identical imaging assumptions. Rather than aiming at fully physically faithful radiographic simulation, the proposed approach provides a controllable and reproducible methodological environment for studying anatomy--projection relationships, motion observability, and transformation-aware imaging workflows.

Related papers

• Metadata Supervised MRI Representations for Modelling and Controlling Acquisition Variability [0.6940876618878119]
  learned representations entangle biological structure with acquisition-dependent appearance, limiting interpretability, generalisation, and clinical deployment.<n>We show that these sources of variation can be separated by jointly modelling MRI images and DICOM metadata.<n>Resulting contrast representations organise heterogeneous acquisitions, support sequence understanding, and detect image--metadata inconsistencies.<n>We introduce a unified anatomy-preserving harmonisation model for cross-modality and cross-site adaptation, conditioned on image or acquisition metadata.
  arXiv  Detail & Related papers  (2026-07-13T09:12:23Z)
• Towards Voxel Spacing Consistency for Medical Image Segmentation [56.992050146446495]
  We study the correlation between image resampling and segmentation, and propose Consispace, a semantic-aware resampling framework.<n> Consispace achieves consistent voxel spacing in the axial direction while preserving anatomical and semantic consistency.
  arXiv  Detail & Related papers  (2026-06-30T15:42:23Z)
• CheXanatomy: Anatomy-Aware Vision-Language Modeling for Chest Radiographs [3.369056928100267]
  CheXanatomy is a framework that integrates explicit anatomical knowledge into a pretrained vision-language model.<n>To enable scalable supervision, we synthesize realistic chest radiographs from CT volumes and forward-project CT segmentation labels.<n>We evaluate the approach on synthetic and real chest radiographs against a U-Net baseline, including ablations on model scale, input resolution, and vision encoder fine-tuning.
  arXiv  Detail & Related papers  (2026-06-07T02:41:05Z)
• Assessment of the quantitative impact of occlusal positioning splints on temporomandibular joint conditions [0.0]
  A computational method for quantitative analysis of temporomandibular joint (TMJ) configuration is proposed and demonstrated.<n>The method models a positioning splint as a physical realization of a predefined rigid transformation of the mandible.<n>Splints corresponding to selected mandibular positions are designed and fabricated, and their positioning accuracy is evaluated.
  arXiv  Detail & Related papers  (2026-04-28T07:37:16Z)
• PartNerFace: Part-based Neural Radiance Fields for Animatable Facial Avatar Reconstruction [74.52310899576547]
  We present PartNerFace, a part-based neural radiance fields approach for reconstructing animatable facial avatar from monocular RGB videos.<n>Our method generalizes well to unseen expressions and is capable of modeling fine-scale facial motions.
  arXiv  Detail & Related papers  (2026-04-15T14:28:44Z)
• Dynamic Avatar-Scene Rendering from Human-centric Context [75.95641456716373]
  We propose bf Separate-then-Map (StM) strategy to bridge separately defined and optimized models.<n>StM significantly outperforms existing state-of-the-art methods in both visual quality and rendering accuracy.
  arXiv  Detail & Related papers  (2025-11-13T17:39:06Z)
• 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)
• Novel-view X-ray Projection Synthesis through Geometry-Integrated Deep Learning [3.4916237834391874]
  The DL-GIPS model synthesizes X-ray projections from new viewpoints by leveraging a single existing projection.<n>The model strategically manipulates geometry and texture features extracted from an initial projection to match new viewing angles.<n>It then synthesizes the final projection by merging these modified geometry features with consistent texture information through an advanced image generation process.
  arXiv  Detail & Related papers  (2025-04-16T10:30:08Z)
• Intraoperative Registration by Cross-Modal Inverse Neural Rendering [61.687068931599846]
  We present a novel approach for 3D/2D intraoperative registration during neurosurgery via cross-modal inverse neural rendering. Our approach separates implicit neural representation into two components, handling anatomical structure preoperatively and appearance intraoperatively. We tested our method on retrospective patients' data from clinical cases, showing that our method outperforms state-of-the-art while meeting current clinical standards for registration.
  arXiv  Detail & Related papers  (2024-09-18T13:40:59Z)
• Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration [59.062085785106234]
  This article presents a general Bayesian learning framework for multi-modal groupwise image registration.<n>We propose a novel hierarchical variational auto-encoding architecture to realise the inference procedure of the latent variables.<n>Experiments were conducted to validate the proposed framework, including four different datasets from cardiac, brain, and abdominal medical images.
  arXiv  Detail & Related papers  (2024-01-04T08:46:39Z)
• Double-Flow GAN model for the reconstruction of perceived faces from brain activities [13.707575848841405]
  We proposed a novel reconstruction framework, which we called Double-Flow GAN.<n>We also designed a pretraining process that uses features extracted from images as conditions for making it possible to pretrain the conditional reconstruction model from fMRI.<n>Results showed that the proposed method is significant at accurately reconstructing multiple face attributes, outperforms the previous reconstruction models, and exhibited state-of-the-art reconstruction abilities.
  arXiv  Detail & Related papers  (2023-12-12T18:07:57Z)
• Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation [84.7571086566595]
  We propose improvements over previous GAN-based medical image synthesis methods by jointly encoding the intrinsic relationship of geometry and shape. The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.
  arXiv  Detail & Related papers  (2020-03-31T11:50:43Z)

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.