The Texture-Shape Dilemma: Boundary-Safe Synthetic Generation for 3D Medical Transformers

• URL: http://arxiv.org/abs/2603.00985v1
• Date: Sun, 01 Mar 2026 08:27:45 GMT
• Title: The Texture-Shape Dilemma: Boundary-Safe Synthetic Generation for 3D Medical Transformers
• Authors: Jiaqi Tang, Weixuan Xu, Shu Zhang, Fandong Zhang, Qingchao Chen,
• Abstract summary: ViTs have revolutionized medical image analysis, yet their data-hungry nature clashes with the scarcity and privacy constraints of clinical archives.<n>Formula-Driven Supervised Learning has emerged as a promising solution to this bottleneck, synthesizing infinite annotated samples from mathematical formulas without utilizing real patient data.<n>Existing F paradigms rely on simple geometric with homogeneous intensities, creating a substantial gap by neglecting tissue textures and noise patterns inherent in modalities like CT and MRI.<n>In this paper, we identify a critical conflict boundary aliasing: when high-frequency synthetic textures are naively added, they corrupt the image gradient signals necessary for learning structural boundaries, causing
• Score: 22.195374577712133
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformers (ViTs) have revolutionized medical image analysis, yet their data-hungry nature clashes with the scarcity and privacy constraints of clinical archives. Formula-Driven Supervised Learning (FDSL) has emerged as a promising solution to this bottleneck, synthesizing infinite annotated samples from mathematical formulas without utilizing real patient data. However, existing FDSL paradigms rely on simple geometric shapes with homogeneous intensities, creating a substantial gap by neglecting tissue textures and noise patterns inherent in modalities like CT and MRI. In this paper, we identify a critical optimization conflict termed boundary aliasing: when high-frequency synthetic textures are naively added, they corrupt the image gradient signals necessary for learning structural boundaries, causing the model to fail in delineating real anatomical margins. To bridge this gap, we propose a novel Physics-inspired Spatially-Decoupled Synthesis framework. Our approach orthogonalizes the synthesis process: it first constructs a gradient-shielded buffer zone based on boundary distance to ensure stable shape learning, and subsequently injects physics-driven spectral textures into the object core. This design effectively reconciles robust shape representation learning with invariance to acquisition noise. Extensive experiments on the BTCV and MSD datasets demonstrate that our method significantly outperforms previous FDSL, as well as SSL methods trained on real-world medical datasets, by 1.43% on BTCV and up to 1.51% on MSD task, offering a scalable, annotation-free foundation for medical ViTs. The code will be made publicly available upon acceptance.

Related papers

• Fake It Right: Injecting Anatomical Logic into Synthetic Supervised Pre-training for Medical Segmentation [21.75204301463342]
  Vision Transformers (ViTs) excel in 3D medical segmentation but require massive datasets.<n>Formula-Driven Supervised Learning (F) offers a privacy-preserving alternative by pre-training on synthetic mathematical primitives.<n>We propose an annotated-Informed Synthetic Anatomy Supervised Pre-training framework unifying F's infinite scalability with anatomical realism.
  arXiv  Detail & Related papers  (2026-03-01T08:15:18Z)
• Physics Informed Generative AI Enabling Labour Free Segmentation For Microscopy Analysis [3.3176565054468714]
  This paper introduces a novel framework for labour-free segmentation that successfully bridges the simulation-to-reality gap.<n>We employ a Cycle-Consistent Generative Adversarial Network (CycleGAN) for unpaired image-to-image translation.<n>A U-Net model, trained exclusively on this synthetic data, demonstrated remarkable generalisation when deployed on unseen experimental images.
  arXiv  Detail & Related papers  (2026-02-02T06:36:06Z)
• Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing [63.141976759536625]
  We propose Interp3D, a training-free framework for textured 3D morphing.<n>It harnesses generative priors and adopts a progressive alignment principle to ensure both geometric fidelity and texture coherence.<n>For comprehensive evaluations, we construct a dedicated dataset, Interp3DData, with graded difficulty levels and assess generation results from fidelity, transition smoothness, and plausibility.
  arXiv  Detail & Related papers  (2026-01-20T16:03:22Z)
• Physically-Grounded Manifold Projection Model for Generalizable Metal Artifact Reduction in Dental CBCT [20.637726557566793]
  Metal artifacts in Dental CBCT severely obscure anatomical structures.<n>Current deep learning for Metal Artifact Reduction (MAR) faces limitations.<n>Denoising Diffusion Models (DDPMs) offer realism but rely on slow, iterative sampling.
  arXiv  Detail & Related papers  (2025-12-30T14:36:26Z)
• Denoising via Repainting: an image denoising method using layer wise medical image repainting [6.195127726026568]
  We propose a multi-scale approach that integrates anisotropic Gaussian filtering and progressive Bezier-path redrawing.<n>Our method constructs a scale-space pyramid to mitigate noise while preserving structural details.<n> Empirical results on multiple MRI datasets demonstrate consistent improvements in PSNR and SSIM over competing methods.
  arXiv  Detail & Related papers  (2025-03-11T06:54:37Z)
• PhyRecon: Physically Plausible Neural Scene Reconstruction [81.73129450090684]
  We introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets.
  arXiv  Detail & Related papers  (2024-04-25T15:06:58Z)
• Boundary Constraint-free Biomechanical Model-Based Surface Matching for Intraoperative Liver Deformation Correction [0.6249768559720122]
  In image-guided liver surgery, 3D-3D non-rigid registration methods play a crucial role in estimating the mapping between the preoperative model and the intraoperative surface represented as point clouds.<n>We propose a 3D-3D non-rigid registration method that incorporates a modified FEM into the surface matching term.
  arXiv  Detail & Related papers  (2024-03-15T02:05:20Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• Diffusion-based Holistic Texture Rectification and Synthesis [26.144666226217062]
  Traditional texture synthesis approaches focus on generating textures from pristine samples. We propose a framework that synthesizes holistic textures from degraded samples in natural images.
  arXiv  Detail & Related papers  (2023-09-26T08:44:46Z)
• InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation [29.78647170035808]
  We propose a realistic data augmentation method for nuclei segmentation, named InsMix, that follows a Copy-Paste-Smooth principle. Specifically, we propose morphology constraints that enable the augmented images to acquire luxuriant information about nuclei. To fully exploit the pixel redundancy of the background, we propose a background perturbation method, which randomly shuffles the background patches.
  arXiv  Detail & Related papers  (2022-06-30T08:58:05Z)
• Scene Synthesis via Uncertainty-Driven Attribute Synchronization [52.31834816911887]
  This paper introduces a novel neural scene synthesis approach that can capture diverse feature patterns of 3D scenes. Our method combines the strength of both neural network-based and conventional scene synthesis approaches.
  arXiv  Detail & Related papers  (2021-08-30T19:45:07Z)
• NeRF in detail: Learning to sample for view synthesis [104.75126790300735]
  Neural radiance fields (NeRF) methods have demonstrated impressive novel view synthesis. In this work we address a clear limitation of the vanilla coarse-to-fine approach -- that it is based on a performance and not trained end-to-end for the task at hand. We introduce a differentiable module that learns to propose samples and their importance for the fine network, and consider and compare multiple alternatives for its neural architecture.
  arXiv  Detail & Related papers  (2021-06-09T17:59:10Z)
• Data-driven generation of plausible tissue geometries for realistic photoacoustic image synthesis [53.65837038435433]
  Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties. We propose a novel approach to PAT data simulation, which we refer to as "learning to simulate" We leverage the concept of Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data to generate plausible tissue geometries.
  arXiv  Detail & Related papers  (2021-03-29T11:30:18Z)
• Fed-Sim: Federated Simulation for Medical Imaging [131.56325440976207]
  We introduce a physics-driven generative approach that consists of two learnable neural modules. We show that our data synthesis framework improves the downstream segmentation performance on several datasets.
  arXiv  Detail & Related papers  (2020-09-01T19:17:46Z)

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.