CTSL: Codebook-based Temporal-Spatial Learning for Accurate Non-Contrast Cardiac Risk Prediction Using Cine MRIs

• URL: http://arxiv.org/abs/2507.16612v1
• Date: Tue, 22 Jul 2025 14:12:41 GMT
• Title: CTSL: Codebook-based Temporal-Spatial Learning for Accurate Non-Contrast Cardiac Risk Prediction Using Cine MRIs
• Abstract summary: Existing methods require supervised learning based on human-refined masks in the ventricular mycardium.<n>We introduce a self-supervised framework, namely Codebook-based temporal-Spatial Learning (TSL), that learns from raw Cine data without requiring segmentation masks.<n>High-confidence MACE risk predictions are achieved through our model, providing a rapid, non-invasive solution for cardiac risk assessment.
• Score: 2.668073128790639
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate and contrast-free Major Adverse Cardiac Events (MACE) prediction from Cine MRI sequences remains a critical challenge. Existing methods typically necessitate supervised learning based on human-refined masks in the ventricular myocardium, which become impractical without contrast agents. We introduce a self-supervised framework, namely Codebook-based Temporal-Spatial Learning (CTSL), that learns dynamic, spatiotemporal representations from raw Cine data without requiring segmentation masks. CTSL decouples temporal and spatial features through a multi-view distillation strategy, where the teacher model processes multiple Cine views, and the student model learns from reduced-dimensional Cine-SA sequences. By leveraging codebook-based feature representations and dynamic lesion self-detection through motion cues, CTSL captures intricate temporal dependencies and motion patterns. High-confidence MACE risk predictions are achieved through our model, providing a rapid, non-invasive solution for cardiac risk assessment that outperforms traditional contrast-dependent methods, thereby enabling timely and accessible heart disease diagnosis in clinical settings.

Related papers

• A Unified Model for Highly Accurate ECG-Free Dynamic Coronary Roadmapping Using Spatio-Temporal Transformers [3.991042132764926]
  Frequent contrast injections increase radiation exposure and the risk of contrast-induced nephropathy in patients.<n>Dynamic Coronary Road (DRM) overlays a precomputed angiographic vessel map onto live fluoroscopy and continuously updating it throughout the procedure.<n>DRM relies on precise cardiac phase matching between angiography and fluoroscopy, together with reliable catheter tip tracking for motion compensation.<n>We present a unified DRM framework that simultaneously performs cardiac phase matching and catheter tip tracking for accurate real-time guidance.
  arXiv  Detail & Related papers  (2026-07-09T18:57:15Z)
• Uncertainty-Aware Concept and Motion Segmentation for Semi-Supervised Angiography Videos [15.975499220724044]
  We propose a SAM3-based Teacher-student framework with Motion-Aware consistency and Progressive Confidence Regularization.<n>Our method utilizes SAM3's unique promptable concept segmentation design and innovates a SAM3-based teacher-student framework to maximize the performance potential of both the teacher and the student.
  arXiv  Detail & Related papers  (2026-03-01T03:04:43Z)
• T-CACE: A Time-Conditioned Autoregressive Contrast Enhancement Multi-Task Framework for Contrast-Free Liver MRI Synthesis, Segmentation, and Diagnosis [5.9273237904788045]
  We propose a Time-Conditioned Autoregressive Contrast Enhancement (T-CACE) framework for synthesizing contrast-enhanced MRI (CEMRI) directly from non-contrast MRI (NCMRI)<n>T-CACE introduces three core innovations: a conditional token encoding (CTE) mechanism that unifies anatomical priors and temporal phase information into latent representations; and a dynamic time-aware attention mask (DTAM) that adaptively modulates inter-phase information flow.<n>Experiments on two independent liver MRI datasets demonstrate that T-CACE outperforms state-of-the-art methods in image synthesis, segmentation, and lesion
  arXiv  Detail & Related papers  (2025-08-13T16:14:14Z)
• Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation [21.738308923180767]
  We present DISCOVR, a self-supervised dual branch framework for cardiac ultrasound video representation learning.<n>DISCOVR combines a clustering-based video encoder that models temporal dynamics with an online image encoder that extracts fine-grained spatial semantics.
  arXiv  Detail & Related papers  (2025-06-13T13:36:33Z)
• StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning [51.003833566279006]
  Class-Incremental Learning (CIL) seeks to develop models that continuously learn new action categories over time without previously acquired knowledge.<n>Existing approaches either rely on forgetting, raising concerns over memory and privacy, or adapt static image-based methods that neglect temporal modeling.<n>We propose a unified and exemplar-free VCIL framework that explicitly disentangles and preserves information.
  arXiv  Detail & Related papers  (2025-05-20T06:46:51Z)
• Deep Learning Assisted Outer Volume Removal for Highly-Accelerated Real-Time Dynamic MRI [2.512491726995032]
  Real-time (RT) dynamic MRI plays a vital role in capturing rapid physiological processes.<n>RT cine MRI is important for functional assessment of the heart with high temporal resolution.<n> achieving high acceleration rates in RT cine MRI is challenging due to aliasing artifacts from extra-cardiac tissues.
  arXiv  Detail & Related papers  (2025-05-01T16:31:52Z)
• CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis [46.56667527672019]
  We introduce a Cross-Modal Temporal Pattern Discovery (CTPD) framework, designed to efficiently extract meaningful cross-modal temporal patterns from multimodal EHR data.<n>Our approach introduces shared initial temporal pattern representations which are refined using slot attention to generate temporal semantic embeddings.
  arXiv  Detail & Related papers  (2024-11-01T15:54:07Z)
• Self-supervised inter-intra period-aware ECG representation learning for detecting atrial fibrillation [41.82319894067087]
  We propose an inter-intra period-aware ECG representation learning approach. Considering ECGs of atrial fibrillation patients exhibit the irregularity in RR intervals and the absence of P-waves, we develop specific pre-training tasks for interperiod and intraperiod representations. Our approach demonstrates remarkable AUC performances on the BTCH dataset, textiti.e., 0.953/0.996 for paroxysmal/persistent atrial fibrillation detection.
  arXiv  Detail & Related papers  (2024-10-08T10:03:52Z)
• Synthesizing Late-Stage Contrast Enhancement in Breast MRI: A Comprehensive Pipeline Leveraging Temporal Contrast Enhancement Dynamics [0.3499870393443268]
  This study presents a pipeline for synthesizing late-phase DCE-MRI images from early-phase data.<n>The proposed approach introduces a novel loss function, Time Intensity Loss (TI-loss), leveraging the temporal behavior of contrast agents to guide the training of a generative model.<n>Two metrics are proposed to evaluate image quality: the Contrast Agent Pattern Score ($mathcalCP_s$), which validates enhancement patterns in annotated regions, and the Average Difference in Enhancement ($mathcalED$), measuring differences between real and generated enhancements.
  arXiv  Detail & Related papers  (2024-09-03T04:31:49Z)
• Autonomous Path Planning for Intercostal Robotic Ultrasound Imaging Using Reinforcement Learning [45.5123007404575]
  The US examination for thoracic application is still challenging due to the acoustic shadow cast by the subcutaneous rib cage. We present a reinforcement learning approach for planning scanning paths between ribs to monitor changes in lesions on internal organs. Experiments have been carried out on unseen CTs with randomly defined single or multiple scanning targets.
  arXiv  Detail & Related papers  (2024-04-15T16:52:53Z)
• DDSB: An Unsupervised and Training-free Method for Phase Detection in Echocardiography [37.32413956117856]
  We propose an unsupervised and training-free method to identify End-Diastolic (ED) and End-Systolic (ES) frames. By identifying anchor points and analyzing directional deformation, we effectively reduce dependence on the accuracy of initial segmentation images. Our method achieves comparable accuracy to learning-based models without their associated drawbacks.
  arXiv  Detail & Related papers  (2024-03-19T14:51:01Z)
• Deep Separable Spatiotemporal Learning for Fast Dynamic Cardiac MRI [22.7085949508143]
  MRI plays an indispensable role in cardiac diagnosis. To enable fast imaging, the k-space data can be undersampled. This challenge necessitates extensive training data in deep learning reconstruction methods. We propose a novel and efficient approach, leveraging a dimension separable learning scheme that can perform exceptionally well even with highly limited training data.
  arXiv  Detail & Related papers  (2024-02-24T23:56:15Z)
• Learning Successor Features with Distributed Hebbian Temporal Memory [44.99833362998488]
  This paper presents a novel approach to address the challenge of online sequence learning for decision making under uncertainty.<n>The proposed algorithm, Distributed Hebbian Temporal Memory (DHTM), is based on the factor graph formalism and a multi-component neuron model.<n> Experimental results show that DHTM outperforms LSTM, RWKV and a biologically inspired HMM-like algorithm, CSCG, on non-stationary data sets.
  arXiv  Detail & Related papers  (2023-10-20T10:03:14Z)
• MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts [63.30352394004674]
  Multi-task Self-super-vised Continual Learning (MUSCLE) is a novel self-supervised pre-training pipeline for medical imaging tasks. MUSCLE aggregates X-rays collected from multiple body parts for representation learning, and adopts a well-designed continual learning procedure. We evaluate MUSCLE using 9 real-world X-ray datasets with various tasks, including pneumonia classification, skeletal abnormality classification, lung segmentation, and tuberculosis (TB) detection.
  arXiv  Detail & Related papers  (2023-10-03T12:19:19Z)
• Unsupervised sequence-to-sequence learning for automatic signal quality assessment in multi-channel electrical impedance-based hemodynamic monitoring [0.6875312133832077]
  This study proposes an unsupervised sequence-to-sequence learning approach that automatically assesses the motion-induced reliability of the cardiac volume signal (CVS) in hemodynamic monitoring. An encoder-decoder model is trained not only to self-reproduce an input sequence of the CVS but also to extrapolate the future in a parallel fashion. A motion-influenced CVS of low-quality is detected, based on the residual between the input sequence and its neural representation with a cut-off value determined from the two-sigma rule of thumb over the training set.
  arXiv  Detail & Related papers  (2023-05-16T11:52:06Z)
• Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images [49.1861463923357]
  We propose an uncertainty-guided dual-consistency learning network (UDC-Net) for semi-supervised COVID-19 lesion segmentation from CT images. Our proposed UDC-Net improves the fully supervised method by 6.3% in Dice and outperforms other competitive semi-supervised approaches by significant margins.
  arXiv  Detail & Related papers  (2021-04-07T16:23:35Z)

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.