Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis

• URL: http://arxiv.org/abs/2406.18967v2
• Date: Wed, 28 Aug 2024 05:40:55 GMT
• Title: Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis
• Abstract summary: Transformer-based models excel in imaging translation tasks thanks to their ability to capture long-range dependencies. This paper empirically demonstrates that, lacking strong inductive biases, Transformer can converge to non-optimal solutions in the absence of paired data. We introduce UNet Structured Transformer (UNest), a novel architecture incorporating structural inductive biases for unpaired medical image synthesis.
• Score: 25.531060259709157
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Unpaired medical image synthesis aims to provide complementary information for an accurate clinical diagnostics, and address challenges in obtaining aligned multi-modal medical scans. Transformer-based models excel in imaging translation tasks thanks to their ability to capture long-range dependencies. Although effective in supervised training settings, their performance falters in unpaired image synthesis, particularly in synthesizing structural details. This paper empirically demonstrates that, lacking strong inductive biases, Transformer can converge to non-optimal solutions in the absence of paired data. To address this, we introduce UNet Structured Transformer (UNest), a novel architecture incorporating structural inductive biases for unpaired medical image synthesis. We leverage the foundational Segment-Anything Model to precisely extract the foreground structure and perform structural attention within the main anatomy. This guides the model to learn key anatomical regions, thus improving structural synthesis under the lack of supervision in unpaired training. Evaluated on two public datasets, spanning three modalities, i.e., MR, CT, and PET, UNest improves recent methods by up to 19.30% across six medical image synthesis tasks. Our code is released at https://github.com/HieuPhan33/MICCAI2024-UNest.

Related papers

• Visually-Guided Controllable Medical Image Generation via Fine-Grained Semantic Disentanglement [13.410085175938486]
  Medical image synthesis is crucial for alleviating data scarcity and privacy constraints.<n>Fine-tuning general text-to-image (T2I) models remains challenging.<n>We propose a Visually-Guided Text Disentanglement framework.
  arXiv  Detail & Related papers  (2026-03-11T08:20:33Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• Structure Observation Driven Image-Text Contrastive Learning for Computed Tomography Report Generation [51.509572354327986]
  This work introduces a novel two-stage (structure- and report-learning) framework tailored for Computed Tomography Report Generation (CTRG)<n>In the first stage, a set of learnable structure-specific visual queries observe corresponding structures in a CT image. The resulting observation tokens are contrasted with structure-specific textual features extracted from the accompanying radiology report with a structure-wise image-text contrastive loss.<n>In the second stage, the visual structure queries are frozen and used to select the critical image patch embeddings depicting each anatomical structure, minimizing distractions from irrelevant areas while reducing memory consumption.
  arXiv  Detail & Related papers  (2026-03-05T07:07:07Z)
• MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and Analysis [36.41448398760502]
  We propose MeDUET, a 3D Medical image Disentangled UnifiEd PreTraining framework.<n>MeDUET explicitly disentangles domain-invariant content from domain-specific style.<n>It delivers higher fidelity, faster convergence, and improved controllability for synthesis.
  arXiv  Detail & Related papers  (2026-02-19T23:45:23Z)
• Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels [54.58539616385138]
  We introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owN Anatomy (MONA) First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features. Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features.
  arXiv  Detail & Related papers  (2022-09-27T15:50:31Z)
• MISSU: 3D Medical Image Segmentation via Self-distilling TransUNet [55.16833099336073]
  We propose to self-distill a Transformer-based UNet for medical image segmentation. It simultaneously learns global semantic information and local spatial-detailed features. Our MISSU achieves the best performance over previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-06-02T07:38:53Z)
• Structure-aware Unsupervised Tagged-to-Cine MRI Synthesis with Self Disentanglement [13.442093381065268]
  We learn a general add-on structural feature extractor, by explicitly enforcing the structural alignment between an input and its synthesized image. Specifically, we propose a novel input-output image patches self-training scheme to achieve a disentanglement of underlying anatomical structures and imaging modalities. We train, validate, and test our network on 1,768, 416, and 1,560 unpaired subject-independent slices of tagged and cine magnetic resonance imaging.
  arXiv  Detail & Related papers  (2022-02-25T03:09:46Z)
• Cross-Modality Neuroimage Synthesis: A Survey [71.27193056354741]
  Multi-modality imaging improves disease diagnosis and reveals distinct deviations in tissues with anatomical properties. The existence of completely aligned and paired multi-modality neuroimaging data has proved its effectiveness in brain research. An alternative solution is to explore unsupervised or weakly supervised learning methods to synthesize the absent neuroimaging data.
  arXiv  Detail & Related papers  (2022-02-14T19:29:08Z)
• FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss [58.58979566599889]
  We propose a novel self-supervised learning (FedMed) for brain image synthesis. An affine transform loss (ATL) was formulated to make use of severely distorted images without violating privacy legislation. The proposed method demonstrates advanced performance in both the quality of synthesized results under a severely misaligned and unpaired data setting.
  arXiv  Detail & Related papers  (2022-01-29T13:45:39Z)
• Class-Aware Generative Adversarial Transformers for Medical Image Segmentation [39.14169989603906]
  We present CA-GANformer, a novel type of generative adversarial transformers, for medical image segmentation. First, we take advantage of the pyramid structure to construct multi-scale representations and handle multi-scale variations. We then design a novel class-aware transformer module to better learn the discriminative regions of objects with semantic structures.
  arXiv  Detail & Related papers  (2022-01-26T03:50:02Z)
• InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images [53.4351366246531]
  We construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. We analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance.
  arXiv  Detail & Related papers  (2021-12-23T15:52:37Z)
• ResViT: Residual vision transformers for multi-modal medical image synthesis [0.0]
  We propose a novel generative adversarial approach for medical image synthesis, ResViT, to combine local precision of convolution operators with contextual sensitivity of vision transformers. Our results indicate the superiority of ResViT against competing methods in terms of qualitative observations and quantitative metrics.
  arXiv  Detail & Related papers  (2021-06-30T12:57:37Z)
• METGAN: Generative Tumour Inpainting and Modality Synthesis in Light Sheet Microscopy [4.872960046536882]
  We introduce a novel generative method which leverages real anatomical information to generate realistic image-label pairs of tumours. We construct a dual-pathway generator, for the anatomical image and label, trained in a cycle-consistent setup, constrained by an independent, pretrained segmentor. The generated images yield significant quantitative improvement compared to existing methods.
  arXiv  Detail & Related papers  (2021-04-22T11:18:17Z)
• CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation [95.51455777713092]
  Convolutional neural networks (CNNs) have been the de facto standard for nowadays 3D medical image segmentation. We propose a novel framework that efficiently bridges a bf Convolutional neural network and a bf Transformer bf (CoTr) for accurate 3D medical image segmentation.
  arXiv  Detail & Related papers  (2021-03-04T13:34:22Z)
• Medical Transformer: Gated Axial-Attention for Medical Image Segmentation [73.98974074534497]
  We study the feasibility of using Transformer-based network architectures for medical image segmentation tasks. We propose a Gated Axial-Attention model which extends the existing architectures by introducing an additional control mechanism in the self-attention module. To train the model effectively on medical images, we propose a Local-Global training strategy (LoGo) which further improves the performance.
  arXiv  Detail & Related papers  (2021-02-21T18:35:14Z)

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.