Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yundi Zhang, Sevgi Gokce Kafali, Niklas Bubeck, Daniel Rueckert, Jiazhen Pan

TL;DR

This work proposes 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 and demonstrates that precise spatial geometries and multi-task features can be successfully recovered directly from the k-space representations.

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.

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

TL;DR

This work proposes 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 and demonstrates that precise spatial geometries and multi-task features can be successfully recovered directly from the k-space representations.

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.
Paper Structure (6 sections, 2 equations, 4 figures, 2 tables)

This paper contains 6 sections, 2 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. k-MTR Methodology
  3. Dataset and Implementation
  4. Results
  5. Conclusion

Figures (4)

  • Figure 1: Overview of the k-MTR framework.(a)$S$ multi-view $2D+t$ slices are tokenized, concatenating image ($Q_i^u$) and k-space ($Q_k^u$) tokens across slices for encoder input. (b--d) Training pipeline (single slice shown). (b) Unsupervised masked reconstruction of undersampled k-space and image slices. (c) Contrastive alignment between undersampled k-space ($T^u_k$) and fully-sampled image ($T_i$) embeddings. (d) Fine-tuning the pretrained k-space encoder via lightweight task-specific decoders.
  • Figure 2: 3D t-SNE visualization of the representations after alignment, colored by ground-truth phenotype groups.
  • Figure 3: Segmentation and Reconstruction Results.(a) Dice Score and example segmentation maps overlayed on fully-sampled images. k-MTR (R=8) is compared against the fully-sampled upper bound (nnU-Net) and undersampled (R=8) image-based baselines (nnU-Net$^u$, LI-Net). (b) Image reconstructions from undersampled k-space compared to k-GIN.
  • Figure 4: Ablation of k-MTR's phenotype prediction accuracy across varying undersampling factors, with 16x prediction failures highlighted in red.