Principled Feature Disentanglement for High-Fidelity Unified Brain MRI Synthesis

• URL: http://arxiv.org/abs/2406.14954v2
• Date: Mon, 20 Oct 2025 15:00:52 GMT
• Title: Principled Feature Disentanglement for High-Fidelity Unified Brain MRI Synthesis
• Authors: Jihoon Cho, Jonghye Woo, Jinah Park,
• Abstract summary: We propose a novel unified framework for multisequence MR images, called hybrid-fusion GAN (HF-GAN)<n>A powerful many-to-one stream is constructed for the extraction of complex complementary features, while utilizing parallel, one-to-one streams to process modality-specific information.<n>We validated our framework on public datasets of both healthy and pathological brain MRI.
• Score: 5.657045602016982
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multisequence Magnetic Resonance Imaging (MRI) provides a more reliable diagnosis in clinical applications through complementary information across sequences. However, in practice, the absence of certain MR sequences is a common problem that can lead to inconsistent analysis results. In this work, we propose a novel unified framework for synthesizing multisequence MR images, called hybrid-fusion GAN (HF-GAN). The fundamental mechanism of this work is principled feature disentanglement, which aligns the design of the architecture with the complexity of the features. A powerful many-to-one stream is constructed for the extraction of complex complementary features, while utilizing parallel, one-to-one streams to process modality-specific information. These disentangled features are dynamically integrated into a common latent space by a channel attention-based fusion module (CAFF) and then transformed via a modality infuser to generate the target sequence. We validated our framework on public datasets of both healthy and pathological brain MRI. Quantitative and qualitative results show that HF-GAN achieves state-of-the-art performance, with our 2D slice-based framework notably outperforming a leading 3D volumetric model. Furthermore, the utilization of HF-GAN for data imputation substantially improves the performance of the downstream brain tumor segmentation task, demonstrating its clinical relevance.

Related papers

• Frequency Error-Guided Under-sampling Optimization for Multi-Contrast MRI Reconstruction [24.246450246745905]
  Multi-contrast MRI reconstruction has emerged as a promising direction by leveraging complementary information from fully-sampled reference scans.<n>Existing approaches suffer from three major limitations: (1) superficial reference fusion strategies, (2) insufficient utilization of the complementary information provided by the reference contrast, and (3) fixed under-sampling patterns.<n>We propose an efficient and interpretable frequency error-guided reconstruction framework to tackle these issues.
  arXiv  Detail & Related papers  (2026-01-14T09:40:34Z)
• A Unified Attention U-Net Framework for Cross-Modality Tumor Segmentation in MRI and CT [0.0]
  This study presents a unified Attention U-Net architecture trained jointly on MRI (BraTS 2021) and CT (LIDC-IDRI) datasets.<n>Our proposed pipeline incorporates modality-harmonized preprocessing, attention-gated skip connections, and a modality-aware Focal Tversky loss function.
  arXiv  Detail & Related papers  (2026-01-07T23:50:45Z)
• Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction [65.67001243986981]
  We propose MindHier, a coarse-to-fine fMRI-to-image reconstruction framework built on scale-wise autoregressive modeling.<n>MindHier achieves superior semantic fidelity, 4.67x faster inference, and more deterministic results than the diffusion-based baselines.
  arXiv  Detail & Related papers  (2025-10-25T15:40:07Z)
• NeuroMoE: A Transformer-Based Mixture-of-Experts Framework for Multi-Modal Neurological Disorder Classification [3.5313393560458826]
  Deep Learning has recently emerged as a powerful tool for extracting meaningful patterns from medical data to aid in diagnosis.<n>We propose a novel transformer-based Mixture-of-Experts (MoE) framework for classifying neurological disorders.<n>Our framework achieves a validation accuracy of 82.47%, outperforming baseline methods by over 10%.
  arXiv  Detail & Related papers  (2025-06-17T20:40:06Z)
• Unified Cross-Modal Attention-Mixer Based Structural-Functional Connectomics Fusion for Neuropsychiatric Disorder Diagnosis [17.40353435750778]
  ConneX is a multimodal fusion method that integrates cross-attention mechanism and multilayer perceptron (MLP)-Mixer for refined feature fusion.<n>We show improved performance on two distinct clinical datasets, highlighting the robustness of our proposed framework.
  arXiv  Detail & Related papers  (2025-05-21T05:49:13Z)
• Interactive Gadolinium-Free MRI Synthesis: A Transformer with Localization Prompt Learning [6.716077690014641]
  We propose a novel Transformer with Localization Prompts framework for synthesizing CE-MRI from non-contrast MR images. Our architecture introduces three key innovations: a hierarchical backbone that uses efficient Transformer to process multi-scale features; a multi-stage fusion system that hierarchically integrate complementary information via spatial attention operations and cross-attention mechanisms, respectively. The framework enables interactive clinical integration by allowing radiologists to input diagnostic prompts during inference, synergizing artificial intelligence with medical expertise.
  arXiv  Detail & Related papers  (2025-03-03T07:44:28Z)
• Multi-modal Contrastive Learning for Tumor-specific Missing Modality Synthesis [1.4132765964347058]
  High-quality multi-modal MRI in a clinical setting is difficult due to time constraints, high costs, and patient movement artifacts. Our team, PLAVE, design a generative model for missing MRI that integrates multi-modal contrastive learning with a focus on critical tumor regions. Our results in the Brain MR Image Synthesis challenge demonstrate that the proposed model excelled in generating the missing modality.
  arXiv  Detail & Related papers  (2025-02-26T18:34:58Z)
• Towards General Text-guided Image Synthesis for Customized Multimodal Brain MRI Generation [51.28453192441364]
  Multimodal brain magnetic resonance (MR) imaging is indispensable in neuroscience and neurology. Current MR image synthesis approaches are typically trained on independent datasets for specific tasks. We present TUMSyn, a Text-guided Universal MR image Synthesis model, which can flexibly generate brain MR images.
  arXiv  Detail & Related papers  (2024-09-25T11:14:47Z)
• Accelerated Multi-Contrast MRI Reconstruction via Frequency and Spatial Mutual Learning [50.74383395813782]
  We propose a novel Frequency and Spatial Mutual Learning Network (FSMNet) to explore global dependencies across different modalities. The proposed FSMNet achieves state-of-the-art performance for the Multi-Contrast MR Reconstruction task with different acceleration factors.
  arXiv  Detail & Related papers  (2024-09-21T12:02:47Z)
• 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)
• Disentangled Multimodal Brain MR Image Translation via Transformer-based Modality Infuser [12.402947207350394]
  We propose a transformer-based modality infuser designed to synthesize multimodal brain MR images. In our method, we extract modality-agnostic features from the encoder and then transform them into modality-specific features. We carried out experiments on the BraTS 2018 dataset, translating between four MR modalities.
  arXiv  Detail & Related papers  (2024-02-01T06:34:35Z)
• Cross-modality Guidance-aided Multi-modal Learning with Dual Attention for MRI Brain Tumor Grading [47.50733518140625]
  Brain tumor represents one of the most fatal cancers around the world, and is very common in children and the elderly. We propose a novel cross-modality guidance-aided multi-modal learning with dual attention for addressing the task of MRI brain tumor grading.
  arXiv  Detail & Related papers  (2024-01-17T07:54:49Z)
• A Compact Implicit Neural Representation for Efficient Storage of Massive 4D Functional Magnetic Resonance Imaging [14.493622422645053]
  fMRI compressing poses unique challenges due to its intricate temporal dynamics, low signal-to-noise ratio, and complicated underlying redundancies. This paper reports a novel compression paradigm specifically tailored for fMRI data based on Implicit Neural Representation (INR)
  arXiv  Detail & Related papers  (2023-11-30T05:54:37Z)
• fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding [54.17776744076334]
  We propose fMRI-PTE, an innovative auto-encoder approach for fMRI pre-training. Our approach involves transforming fMRI signals into unified 2D representations, ensuring consistency in dimensions and preserving brain activity patterns. Our contributions encompass introducing fMRI-PTE, innovative data transformation, efficient training, a novel learning strategy, and the universal applicability of our approach.
  arXiv  Detail & Related papers  (2023-11-01T07:24:22Z)
• BrainVoxGen: Deep learning framework for synthesis of Ultrasound to MRI [2.982610402087728]
  The work proposes a novel deep-learning framework for the synthesis of three-dimensional MRI volumes from corresponding 3D ultrasound images of the brain. This research holds promise for transformative applications in medical diagnostics and treatment planning within the neuroimaging domain.
  arXiv  Detail & Related papers  (2023-10-11T20:37:59Z)
• Source-Free Collaborative Domain Adaptation via Multi-Perspective Feature Enrichment for Functional MRI Analysis [55.03872260158717]
  Resting-state MRI functional (rs-fMRI) is increasingly employed in multi-site research to aid neurological disorder analysis. Many methods have been proposed to reduce fMRI heterogeneity between source and target domains. But acquiring source data is challenging due to concerns and/or data storage burdens in multi-site studies. We design a source-free collaborative domain adaptation framework for fMRI analysis, where only a pretrained source model and unlabeled target data are accessible.
  arXiv  Detail & Related papers  (2023-08-24T01:30:18Z)
• K-Space-Aware Cross-Modality Score for Synthesized Neuroimage Quality Assessment [71.27193056354741]
  The problem of how to assess cross-modality medical image synthesis has been largely unexplored. We propose a new metric K-CROSS to spur progress on this challenging problem. K-CROSS uses a pre-trained multi-modality segmentation network to predict the lesion location.
  arXiv  Detail & Related papers  (2023-07-10T01:26:48Z)
• Two-stage MR Image Segmentation Method for Brain Tumors based on Attention Mechanism [27.08977505280394]
  A coordination-spatial attention generation adversarial network (CASP-GAN) based on the cycle-consistent generative adversarial network (CycleGAN) is proposed. The performance of the generator is optimized by introducing the Coordinate Attention (CA) module and the Spatial Attention (SA) module. The ability to extract the structure information and the detailed information of the original medical image can help generate the desired image with higher quality.
  arXiv  Detail & Related papers  (2023-04-17T08:34:41Z)
• IMPORTANT-Net: Integrated MRI Multi-Parameter Reinforcement Fusion Generator with Attention Network for Synthesizing Absent Data [16.725225424047256]
  We develop a novel $textbfI$ntegrated MRI $textbfM$ulti-$textbfP$arameter reinf$textbfO$rcement fusion generato$textbfR$ wi$textbfT$h. We show that our IMPORTANT-Net is capable of generating missing MRI parameters and outperforms comparable state-of-the-art networks.
  arXiv  Detail & Related papers  (2023-02-03T14:56:10Z)
• A Novel Unified Conditional Score-based Generative Framework for Multi-modal Medical Image Completion [54.512440195060584]
  We propose the Unified Multi-Modal Conditional Score-based Generative Model (UMM-CSGM) to take advantage of Score-based Generative Model (SGM) UMM-CSGM employs a novel multi-in multi-out Conditional Score Network (mm-CSN) to learn a comprehensive set of cross-modal conditional distributions. Experiments on BraTS19 dataset show that the UMM-CSGM can more reliably synthesize the heterogeneous enhancement and irregular area in tumor-induced lesions.
  arXiv  Detail & Related papers  (2022-07-07T16:57:21Z)
• Multi-modal Aggregation Network for Fast MR Imaging [85.25000133194762]
  We propose a novel Multi-modal Aggregation Network, named MANet, which is capable of discovering complementary representations from a fully sampled auxiliary modality. In our MANet, the representations from the fully sampled auxiliary and undersampled target modalities are learned independently through a specific network. Our MANet follows a hybrid domain learning framework, which allows it to simultaneously recover the frequency signal in the $k$-space domain.
  arXiv  Detail & Related papers  (2021-10-15T13:16:59Z)
• Deep Learning based Multi-modal Computing with Feature Disentanglement for MRI Image Synthesis [8.363448006582065]
  We propose a deep learning based multi-modal computing model for MRI synthesis with feature disentanglement strategy. The proposed approach decomposes each input modality into modality-invariant space with shared information and modality-specific space with specific information. To address the lack of specific information of the target modality in the test phase, a local adaptive fusion (LAF) module is adopted to generate a modality-like pseudo-target.
  arXiv  Detail & Related papers  (2021-05-06T17:22:22Z)
• Mapping individual differences in cortical architecture using multi-view representation learning [0.0]
  We introduce a novel machine learning method which allows combining the activation-and connectivity-based information respectively measured through task-fMRI and resting-state fMRI. It combines a multi-view deep autoencoder which is designed to fuse the two fMRI modalities into a joint representation space within which a predictive model is trained to guess a scalar score that characterizes the patient.
  arXiv  Detail & Related papers  (2020-04-01T09:01:25Z)
• Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis [143.55901940771568]
  We propose a novel Hybrid-fusion Network (Hi-Net) for multi-modal MR image synthesis. In our Hi-Net, a modality-specific network is utilized to learn representations for each individual modality. A multi-modal synthesis network is designed to densely combine the latent representation with hierarchical features from each modality.
  arXiv  Detail & Related papers  (2020-02-11T08:26:42Z)

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.