UniSpine-GS: An Efficient Physics-Aware Gaussian Framework for Cross-Modality Multi-view Spine Image Synthesis

• URL: http://arxiv.org/abs/2607.04923v1
• Date: Mon, 06 Jul 2026 10:52:41 GMT
• Title: UniSpine-GS: An Efficient Physics-Aware Gaussian Framework for Cross-Modality Multi-view Spine Image Synthesis
• Abstract summary: UniSpine-GS is an efficient framework for novel-view projection rendering in multi-view spine imaging.<n>We introduce SPWM, a structure-guided loss reweighting strategy to improve boundary fidelity and local details.<n>Our results demonstrate that UniSpine-GS significantly outperforms existing methods across all metrics.
• Score: 28.871303611629315
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The diagnosis of spinal diseases is often assisted by 3D imaging techniques in clinical practice. However, precise 3D spinal assessment is limited by the high costs of 3D imaging hardware and the challenges posed by the physical differences between imaging modalities, which hinder the generalizability of models. To address these issues, we propose UniSpine-GS, an efficient, physics-aware Gaussian framework designed for novel-view projection rendering in multi-view spine imaging via a 3D-aware representation. Instead of performing explicit 3D reconstruction, our approach learns a geometry-aware Gaussian representation that ensures anatomical consistency across different views. We introduce SPWM, a structure-guided loss reweighting strategy to improve boundary fidelity and local details. We evaluate our method on the CTSpine3D dataset and a newly constructed 3D fetal ultrasound dataset, FeSpine3D. Our results demonstrate that UniSpine-GS significantly outperforms existing methods across all metrics, offering a practical and cost-effective solution for unified multi-view medical imaging. Our code is publicly available at https://github.com/orangeisland66/UniSpine-GS.

Related papers

• Mr3D-VL: A generalist vision language foundation model for Multiparametric 3D Magnetic Resonance Imaging [3.8658612593287525]
  Mr3D-VL is a visual-language foundation model for multi-parametric 3D MRI.<n>It employs an unsupervised pre-trained shared 3D encoder and 4D rotational positional embedding for dual modality-spatial integration.
  arXiv  Detail & Related papers  (2026-08-13T01:12:34Z)
• MedGS: Gaussian Splatting for Multi-Modal 3D Medical Imaging [3.003629981599447]
  We present MedGS, a semi-supervised neural implicit surface reconstruction framework that employs a Gaussian Splatting (GS)-based mechanism.<n>In this framework, medical imaging data are represented as consecutive two-dimensional (2D) frames embedded in 3D space.<n>As a result, MedGS offers more efficient training than traditional neural implicit methods.
  arXiv  Detail & Related papers  (2025-09-20T20:52:26Z)
• Accelerating 3D Photoacoustic Computed Tomography with End-to-End Physics-Aware Neural Operators [74.65171736966131]
  Photoacoustic computed tomography (PACT) combines optical contrast with ultrasonic resolution, achieving deep-tissue imaging beyond the optical diffusion limit.<n>Current implementations require dense transducer arrays and prolonged acquisition times, limiting clinical translation.<n>We introduce Pano, an end-to-end physics-aware model that directly learns the inverse acoustic mapping from sensor measurements to volumetric reconstructions.
  arXiv  Detail & Related papers  (2025-09-11T23:12:55Z)
• From Slices to Structures: Unsupervised 3D Reconstruction of Female Pelvic Anatomy from Freehand Transvaginal Ultrasound [8.740779457368255]
  We present a novel framework for reconstructing 3D anatomical structures from 2D transvaginal ultrasound (TVS) sweeps.<n>Our method adapts the principles of Gaussian Splatting to the domain of ultrasound, introducing a slice-aware, differentiable spatializer.<n>The result is a compact, flexible, and memory-efficient representation that captures anatomical detail with high fidelity.
  arXiv  Detail & Related papers  (2025-08-20T09:09:06Z)
• Enhancing Free-hand 3D Photoacoustic and Ultrasound Reconstruction using Deep Learning [3.8426872518410997]
  This study introduces a motion-based learning network with a global-local self-attention module (MoGLo-Net) to enhance 3D reconstruction in handheld photoacoustic and ultrasound (PAUS) imaging.<n>MoGLo-Net exploits the critical regions, such as fully-developed speckle area or high-echogenic tissue area within successive ultrasound images to accurately estimate motion parameters.
  arXiv  Detail & Related papers  (2025-02-05T11:59:23Z)
• Multi-resolution Guided 3D GANs for Medical Image Translation [6.299981733052469]
  We introduce a multi-resolution guided Generative Adrial Network (GAN)-based framework for 3D medical image translation.<n>Our framework uses a 3D multi-resolution Dense-Attention UNet (3D-mDAUNet) as the generator and a 3D multi-resolution UNet as the discriminator.<n>Our approach yields promising results in volumetric image quality assessment (IQA) across a variety of imaging modalities, body regions, and age groups, demonstrating its robustness.
  arXiv  Detail & Related papers  (2024-11-30T20:11:55Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.<n>Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)
• Generative Enhancement for 3D Medical Images [74.17066529847546]
  We propose GEM-3D, a novel generative approach to the synthesis of 3D medical images. Our method begins with a 2D slice, noted as the informed slice to serve the patient prior, and propagates the generation process using a 3D segmentation mask. By decomposing the 3D medical images into masks and patient prior information, GEM-3D offers a flexible yet effective solution for generating versatile 3D images.
  arXiv  Detail & Related papers  (2024-03-19T15:57:04Z)
• SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imaging [59.78761085714715]
  This study proposes a novel Siamese Dual-Resolution Transformer (SDR-Former) framework for liver lesion classification. The proposed framework has been validated through comprehensive experiments on two clinical datasets. To support the scientific community, we are releasing our extensive multi-phase MR dataset for liver lesion analysis to the public.
  arXiv  Detail & Related papers  (2024-02-27T06:32:56Z)
• MinD-3D: Reconstruct High-quality 3D objects in Human Brain [50.534007259536715]
  Recon3DMind is an innovative task aimed at reconstructing 3D visuals from Functional Magnetic Resonance Imaging (fMRI) signals. We present the fMRI-Shape dataset, which includes data from 14 participants and features 360-degree videos of 3D objects. We propose MinD-3D, a novel and effective three-stage framework specifically designed to decode the brain's 3D visual information from fMRI signals.
  arXiv  Detail & Related papers  (2023-12-12T18:21:36Z)
• On the Localization of Ultrasound Image Slices within Point Distribution Models [84.27083443424408]
  Thyroid disorders are most commonly diagnosed using high-resolution Ultrasound (US) Longitudinal tracking is a pivotal diagnostic protocol for monitoring changes in pathological thyroid morphology. We present a framework for automated US image slice localization within a 3D shape representation.
  arXiv  Detail & Related papers  (2023-09-01T10:10:46Z)
• A Geometry-Informed Deep Learning Framework for Ultra-Sparse 3D Tomographic Image Reconstruction [13.44786774177579]
  We establish a geometry-informed deep learning framework for ultra-sparse 3D tomographic image reconstruction. We demonstrate that the seamless inclusion of known priors is essential to enhance the performance of 3D volumetric computed tomography imaging.
  arXiv  Detail & Related papers  (2021-05-25T06:20:03Z)

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.