No Image, No Problem: End-to-End Multi-Task Cardiac Analysis from Undersampled k-Space

• URL: http://arxiv.org/abs/2603.09945v1
• Date: Tue, 10 Mar 2026 17:38:38 GMT
• Title: No Image, No Problem: End-to-End Multi-Task Cardiac Analysis from Undersampled k-Space
• Abstract summary: Conventional clinical CMR pipelines rely on a sequential "reconstruct-then-analyze" paradigm.<n>We propose k-MTR, a k-space representation learning framework that aligns undersampled k-space data and fully-sampled images into a shared semantic manifold.<n>We demonstrate that this latent alignment enables the dense latent space embedded with high-level physiological semantics directly from undersampled frequencies.
• Score: 18.698217373650092
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conventional clinical CMR pipelines rely on a sequential "reconstruct-then-analyze" paradigm, forcing an ill-posed intermediate step that introduces avoidable artifacts and information bottlenecks. This creates a fundamental mathematical paradox: it attempts to recover high-dimensional pixel arrays (i.e., images) from undersampled k-space, rather than directly extracting the low-dimensional physiological labels actually required for diagnosis. To unlock the direct diagnostic potential of k-space, we propose k-MTR (k-space Multi-Task Representation), a k-space representation learning framework that aligns undersampled k-space data and fully-sampled images into a shared semantic manifold. Leveraging a large-scale controlled simulation of 42,000 subjects, k-MTR forces the k-space encoder to restore anatomical information lost to undersampling directly within the latent space, bypassing the explicit inverse problem for downstream analysis. We demonstrate that this latent alignment enables the dense latent space embedded with high-level physiological semantics directly from undersampled frequencies. Across continuous phenotype regression, disease classification, and anatomical segmentation, k-MTR achieves highly competitive performance against state-of-the-art image-domain baselines. By showcasing that precise spatial geometries and multi-task features can be successfully recovered directly from the k-space representations, k-MTR provides a robust architectural blueprint for task-aware cardiac MRI workflows.

Related papers

• Towards Voxel Spacing Consistency for Medical Image Segmentation [56.992050146446495]
  We study the correlation between image resampling and segmentation, and propose Consispace, a semantic-aware resampling framework.<n> Consispace achieves consistent voxel spacing in the axial direction while preserving anatomical and semantic consistency.
  arXiv  Detail & Related papers  (2026-06-30T15:42:23Z)
• Single-Subject Multi-View MRI Super-Resolution via Implicit Neural Representations [4.471119405879635]
  We introduce Single-Subject Implicit Multi-View Super-Resolution for MRI (SIMS-MRI)<n>SIMS-MRI operates solely on anisotropic multi-view scans from a single patient without requiring pre- or post-processing.<n>Our method combines a multi-resolution hash-encoded implicit representation with learned inter-view alignment to generate a spatially consistent isotropic reconstruction.
  arXiv  Detail & Related papers  (2026-03-23T23:00:18Z)
• Low-Field Magnetic Resonance Image Enhancement using Undersampled k-Space [1.2599533416395765]
  We propose a novel deep learning framework based on a U-Net variant that operates directly in k-space to super-resolve low-field MR images.<n>Our results show that undersampled k-space reconstructions achieve comparable quality to full k-space acquisitions.
  arXiv  Detail & Related papers  (2026-03-14T21:25:46Z)
• 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)
• Direct low-field MRI super-resolution using undersampled k-space [1.376408511310322]
  We propose a novel framework for reconstructing high-field MR like images directly from undersampled low-field k-space.<n>Our approach employs a k-space dual channel U-Net that processes the real and imaginary components of undersampled k-space to restore missing frequency content.
  arXiv  Detail & Related papers  (2026-02-28T14:23:31Z)
• Resolution-Independent Neural Operators for Multi-Rate Sparse-View CT [67.14700058302016]
  Deep learning methods achieve high-fidelity reconstructions but often overfit to a fixed acquisition setup.<n>We propose Computed Tomography neural Operator (CTO), a unified CT reconstruction framework that extends to continuous function space.<n>CTO enables consistent multi-sampling-rate and cross-resolution performance, with on average >4dB PSNR gain over CNNs.
  arXiv  Detail & Related papers  (2025-12-13T08:31:46Z)
• ContextMRI: Enhancing Compressed Sensing MRI through Metadata Conditioning [51.26601171361753]
  We propose ContextMRI, a text-conditioned diffusion model for MRI that integrates granular metadata into the reconstruction process.<n>We show that increasing the fidelity of metadata, ranging from slice location and contrast to patient age, sex, and pathology, systematically boosts reconstruction performance.
  arXiv  Detail & Related papers  (2025-01-08T05:15:43Z)
• Continuous K-space Recovery Network with Image Guidance for Fast MRI Reconstruction [5.910509015352437]
  Fast MRI reconstruction aims to restore high-quality images from the undersampled k-space.<n>Existing methods typically train deep learning models to map the undersampled data to artifact-free MRI images.<n>We propose a continuous k-space recovery network from a new perspective of implicit neural representation with image domain guidance.
  arXiv  Detail & Related papers  (2024-11-18T04:54:04Z)
• A Unified Model for Compressed Sensing MRI Across Undersampling Patterns [69.19631302047569]
  We propose a unified MRI reconstruction model robust to various measurement undersampling patterns and image resolutions.<n>Our model improves SSIM by 11% and PSNR by 4 dB over a state-of-the-art CNN (End-to-End VarNet) with 600$times$ faster inference than diffusion methods.
  arXiv  Detail & Related papers  (2024-10-05T20:03:57Z)
• Encoding Enhanced Complex CNN for Accurate and Highly Accelerated MRI [15.966488917066048]
  We propose an encoding enhanced (EN2) complex CNN for highly undersampled pulmonary MRI reconstruction. EN2 employs convolution along either the frequency or phase-encoding direction, resembling the mechanisms of k-space sampling. We also employ complex convolution to learn rich representations from the complex k-space data.
  arXiv  Detail & Related papers  (2023-06-21T02:08:27Z)
• Multi-Modal MRI Reconstruction with Spatial Alignment Network [51.74078260367654]
  In clinical practice, magnetic resonance imaging (MRI) with multiple contrasts is usually acquired in a single study. Recent researches demonstrate that, considering the redundancy between different contrasts or modalities, a target MRI modality under-sampled in the k-space can be better reconstructed with the helps from a fully-sampled sequence. In this paper, we integrate the spatial alignment network with reconstruction, to improve the quality of the reconstructed target modality.
  arXiv  Detail & Related papers  (2021-08-12T08:46:35Z)

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.