CardioTrace: Motion-Aware Cine Synthesis via Coupled Tracing and Segmentation

Zhi Chen, Le ZhangarXiv 2026 · arXiv

TL;DR

CardioTrace is a motion-aware framework designed to synthesize high-quality cardiac cine MRI sequences from limited input data. By coupling explicit motion tracing (deformation fields) with anatomical segmentation and direct image synthesis, it ensures that generated sequences are both visually realistic and medically plausible, outperforming standard GAN and diffusion-based baselines.

What Problem Does This Paper Address?

Cardiac cine MRI is the gold standard for evaluating heart function, but clinical reality often gets in the way. Scans can be temporally sparse (low frame rate) or degraded by patient motion and arrhythmias, making it difficult for doctors to calculate vital metrics like ejection fraction.

While deep learning models like GANs and Diffusion models can synthesize missing frames, they often struggle with "temporal drift"—where the heart's shape becomes unrealistic over time—or "anatomical distortion," where the boundaries of the ventricles blur or shift in ways that don't make physical sense. The authors aim to bridge this gap by forcing the model to understand how the heart moves, rather than just what it looks like.

Methods

The core of CardioTrace is a multi-branch architecture that shares a single encoder but uses three distinct decoders to tackle different aspects of the synthesis problem:

  1. Flow Field Branch: This branch estimates time-resolved deformation fields. It essentially "warps" the initial end-diastolic (ED) frame to subsequent time points, providing an interpretable map of how every pixel moves.
  2. Pixel Translation Branch: This branch directly predicts the appearance of cine frames using a residual formulation. It focuses on the fine details and appearance changes that simple warping might miss.
  3. Segmentation Branch: To ensure anatomical correctness, this branch performs segmentation of the left ventricle (LV), right ventricle (RV), and myocardium (MYO) at key phases (ED and ES).
Fig. 1. Overview of the CardioTrace framework. An encoder extracts features from the ED frame, which are processed by three decoders: the Pixel Translation Branch gener- ates the sequence prediction, and the Flow Field Branch predicts the deformation field to ensure structural correspondence among the whole sequence, while discriminators optimize translation fidelity and anatomical consistency. The Segmentation Branch does segmentation at end-diastolic (ED) and end-systolic (ES) frames.

A key innovation is the Cross-Domain Consistency Loss, where the flow-guided branch acts as a "teacher" for the pixel translation branch. This forces the synthesized images to follow the explicit motion guidance, preventing unrealistic shape transitions. Additionally, the model uses FiLM (Feature-wise Linear Modulation) to inject patient metadata (like age or scanner vendor) as "prompts," helping the model generalize across different hospitals and equipment.

Datasets

The researchers evaluated CardioTrace on two major public datasets:

  • M&M (Multi-Centre, Multi-Vendor): 375 subjects from various centers using different scanner types.
  • ACDC (Automated Cardiac Diagnosis Challenge): 150 subjects. The data was processed into 4D volumes (time, depth, height, width) and sampled into fixed-length sequences of 8 frames for the experiments.

Key Insights and Ideas

  • Motion as a Regularizer: Instead of treating image synthesis as a pure "translation" task, CardioTrace treats it as a "motion" task. By explicitly modeling deformation fields, the model is constrained by the physics of movement.
  • Anatomical Anchoring: By supervising the model with segmentation masks at the start (ED) and end (ES) of the cardiac cycle, the authors provide "anchors" that prevent the model from drifting into anatomically impossible shapes during the intermediate frames.
  • Robustness via Metadata: The inclusion of prompt-style conditioning (FiLM) acknowledges that MRI appearance varies wildly between scanner vendors (e.g., Siemens vs. Philips). This makes the model more "controllable" and robust for multi-center clinical use.

Key Results

CardioTrace consistently outperformed representative baselines, including Pix2Pix, CycleGAN, and Med-DDPM, across several metrics:

  • Quantitative: On the M&M dataset, CardioTrace achieved the highest SSIM (80.04%), PSNR (22.34), and NMI (0.4235).
  • Qualitative: As shown in the error maps, CardioTrace significantly reduces errors in regions undergoing large cardiac deformations compared to other methods. It preserves sharper ventricular boundaries and more accurate morphology.
Table 1. Quantitative comparison on the M&Ms dataset. CardioTrace obtained the best result in the majority of metrics on this dataset.
Fig. 2. Qualitative comparison on the M&M dataset. From left to right: ground-truth reference, Pix2Pix, CycleGAN, Med-DDPM, TraceTrans, and the proposed Cardio- Trace. For each method, the top row shows the synthesized end-systolic (ES) frame conditioned on the end-diastolic (ED) input, with dashed boxes indicating regions of interest that are enlarged below. The bottom row visualizes the corresponding abso- lute error maps with respect to the ground-truth ES frame. Compared with baseline methods, CardioTrace better preserves ventricular morphology and boundary sharp- ness, while reducing errors in regions undergoing large cardiac deformation.

Ablation studies (Table 3) confirmed that every component—the flow branch, the segmentation branch, and the metadata conditioning—contributes significantly to the final performance.

Table 3. Quantitative ablation study evaluating the contribution of different model components to correspondence performance on the M&M dataset.

Limitations and Future Work

While CardioTrace shows strong results, the authors note a few areas for improvement:

  • Fixed Sequence Length: The current experiments used a fixed length of $T=8$ frames. Real-world cine sequences vary in length.
  • Supervision Requirements: The model relies on having segmentation labels for the ED and ES phases during training, which may not always be available in every dataset.
  • Future Directions: The authors suggest that future work could involve real-time synthesis and extending the framework to handle more extreme cardiac pathologies where motion patterns are highly irregular.

Summary updated

Abstract

Cardiac cine MRI provides time-resolved visualization of cardiac motion and is essential for evaluating ventricular function and anatomy. In routine clinical acquisition, however, cine sequences are frequently temporally sparse or degraded by arrhythmia, motion, and scan-time constraints, which can hinder reliable quantification and downstream analysis. We present CardioTrace, a motion-aware cine synthesis framework that generates a full cardiac cine sequence from limited input while explicitly modeling and tracing cardiac motion. CardioTrace couples two complementary pathways: a pixel-translation branch that directly predicts cine frames in a residual formulation, and a flow-field branch that estimates time-resolved deformation fields from a reference phase to provide interpretable motion correspondences across frames. To further preserve anatomical plausibility, a segmentation branch supervises clinically meaningful cardiac structures at key phases, and a cross-branch consistency objective encourages the synthesized appearance dynamics to follow the explicit motion guidance, mitigating temporal drift and unrealistic shape transitions over long sequences. The framework also supports prompt-style conditioning to incorporate auxiliary patient or acquisition information, improving robustness across heterogeneous multi-center data. Experiments on public cardiac cine MRI datasets demonstrate that CardioTrace improves perceptual quality and temporal coherence over representative GAN- and diffusion-based baselines, while better preserving ventricular morphology throughout the cardiac cycle. \textit{Our codes are available after review}.
BibTeX
@misc{chen2026cardiotrace,
  author = {Zhi Chen and Le Zhang},
  title = {{CardioTrace: Motion-Aware Cine Synthesis via Coupled Tracing and Segmentation}},
  year = {2026},
  eprint = {2611.17909},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.17909},
}
Figure