Fake It Right: Injecting Anatomical Logic into Synthetic Supervised Pre-training for Medical Segmentation

• URL: http://arxiv.org/abs/2603.00979v1
• Date: Sun, 01 Mar 2026 08:15:18 GMT
• Title: Fake It Right: Injecting Anatomical Logic into Synthetic Supervised Pre-training for Medical Segmentation
• Authors: Jiaqi Tang, Mengyan Zheng, Shu Zhang, Fandong Zhang, Qingchao Chen,
• Abstract summary: 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.
• Score: 21.75204301463342
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformers (ViTs) excel in 3D medical segmentation but require massive annotated datasets. While Self-Supervised Learning (SSL) mitigates this using unlabeled data, it still faces strict privacy and logistical barriers. Formula-Driven Supervised Learning (FDSL) offers a privacy-preserving alternative by pre-training on synthetic mathematical primitives. However, a critical semantic gap limits its efficacy: generic shapes lack the morphological fidelity, fixed spatial layouts, and inter-organ relationships of real anatomy, preventing models from learning essential global structural priors. To bridge this gap, we propose an Anatomy-Informed Synthetic Supervised Pre-training framework unifying FDSL's infinite scalability with anatomical realism. We replace basic primitives with a lightweight shape bank with de-identified, label-only segmentation masks from 5 subjects. Furthermore, we introduce a structure-aware sequential placement strategy to govern the patch synthesis process. Instead of random placement, we enforce physiological plausibility using spatial anchors for correct localization and a topological graph to manage inter-organ interactions (e.g., preventing impossible overlaps). Extensive experiments on BTCV and MSD datasets demonstrate that our method significantly outperforms state-of-the-art FDSL baselines and SSL methods by 1.74\% and up to 1.66\%, while exhibiting a robust scaling effect where performance improves with increased synthetic data volume. This provides a data-efficient, privacy-compliant solution for medical segmentation. The code will be made publicly available upon acceptance.

Related papers

• The Texture-Shape Dilemma: Boundary-Safe Synthetic Generation for 3D Medical Transformers [22.195374577712133]
  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
  arXiv  Detail & Related papers  (2026-03-01T08:27:45Z)
• Federated Learning Meets LLMs: Feature Extraction From Heterogeneous Clients [0.0]
  Federated learning (FL) enables collaborative model training without sharing raw data.<n>We propose FedLLM-Align, a framework that leverages pre-trained large language models (LLMs) as universal feature extractors.<n>We evaluate FedLLM-Align on coronary heart disease prediction using partitioned datasets with simulated schema divergence.
  arXiv  Detail & Related papers  (2025-09-29T14:06:52Z)
• Private Training & Data Generation by Clustering Embeddings [74.00687214400021]
  Differential privacy (DP) provides a robust framework for protecting individual data.<n>We introduce a novel principled method for DP synthetic image embedding generation.<n> Empirically, a simple two-layer neural network trained on synthetically generated embeddings achieves state-of-the-art (SOTA) classification accuracy.
  arXiv  Detail & Related papers  (2025-06-20T00:17:14Z)
• Generalizing Segmentation Foundation Model Under Sim-to-real Domain-shift for Guidewire Segmentation in X-ray Fluoroscopy [1.4353812560047192]
  Sim-to-real domain adaptation approaches utilize synthetic data from simulations, offering a cost-effective solution. We propose a strategy to adapt SAM to X-ray fluoroscopy guidewire segmentation without any annotation on the target domain. Our method surpasses both pre-trained SAM and many state-of-the-art domain adaptation techniques by a large margin.
  arXiv  Detail & Related papers  (2024-10-09T21:59:48Z)
• Optimizing against Infeasible Inclusions from Data for Semantic Segmentation through Morphology [58.17907376475596]
  State-of-the-art semantic segmentation models are typically optimized in a data-driven fashion.<n>InSeIn extracts explicit inclusion constraints that govern spatial class relations from the semantic segmentation training set at hand.<n>It then enforces a morphological yet differentiable loss that penalizes violations of these constraints during training to promote prediction feasibility.
  arXiv  Detail & Related papers  (2024-08-26T22:39:08Z)
• Synthetic Data for Robust Stroke Segmentation [0.0]
  Current deep learning-based approaches to lesion segmentation in neuroimaging often depend on high-resolution images and extensive annotated data.<n>This paper introduces a novel synthetic data framework tailored for stroke lesion segmentation.<n>Our approach trains models with label maps from healthy and stroke datasets, facilitating segmentation across both normal and pathological tissue.
  arXiv  Detail & Related papers  (2024-04-02T13:42:29Z)
• AttenScribble: Attentive Similarity Learning for Scribble-Supervised Medical Image Segmentation [5.8447004333496855]
  In this paper, we present a straightforward yet effective scribble supervised learning framework. We create a pluggable spatial self-attention module which could be attached on top of any internal feature layers of arbitrary fully convolutional network (FCN) backbone. This attentive similarity leads to a novel regularization loss that imposes consistency between segmentation prediction and visual affinity.
  arXiv  Detail & Related papers  (2023-12-11T18:42:18Z)
• Learnable Weight Initialization for Volumetric Medical Image Segmentation [66.3030435676252]
  We propose a learnable weight-based hybrid medical image segmentation approach. Our approach is easy to integrate into any hybrid model and requires no external training data. Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-06-15T17:55:05Z)
• GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning [55.79997930181418]
  Generalized Zero-Shot Learning aims to recognize images from both the seen and unseen classes by transferring semantic knowledge from seen to unseen classes. It is a promising solution to take the advantage of generative models to hallucinate realistic unseen samples based on the knowledge learned from the seen classes. We propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.
  arXiv  Detail & Related papers  (2022-07-05T04:04:37Z)
• Mitigating Generation Shifts for Generalized Zero-Shot Learning [52.98182124310114]
  Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. We propose a novel Generation Shifts Mitigating Flow framework for learning unseen data synthesis efficiently and effectively. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings.
  arXiv  Detail & Related papers  (2021-07-07T11:43:59Z)
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
  We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
  arXiv  Detail & Related papers  (2020-12-06T18:55:07Z)

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.