MRI Contrast Enhancement Kinetics World Model

2026-02-22

AI Summary

This study addresses the limitations of clinical MRI contrast-enhanced imaging, which relies on inefficient, sparse, and fixed sampling strategies that incur high acquisition costs, elevated patient risk, and poor alignment with diagnostic needs. To overcome these challenges, the authors propose CEKWorld—the first world model for MRI contrast-enhancement kinetics—that jointly incorporates Latent Alignment Learning (LAL), grounded in patient-specific anatomical consistency, and Latent Differential Learning (LDL), informed by temporal smoothness of enhancement dynamics, within a latent space. This dual constraint effectively enforces spatiotemporal coherence, enabling the generation of continuous, contrast-free dynamic enhancement sequences from low-temporal-resolution inputs. Experiments on two datasets demonstrate that CEKWorld significantly outperforms existing methods, producing more realistic and temporally coherent enhancement trajectories.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Clinical MRI contrast acquisition suffers from inefficient information yield, which presents as a mismatch between the risky and costly acquisition protocol and the fixed and sparse acquisition sequence. Applying world models to simulate the contrast enhancement kinetics in the human body enables continuous contrast-free dynamics. However, the low temporal resolution in MRI acquisition restricts the training of world models, leading to a sparsely sampled dataset. Directly training a generative model to capture the kinetics leads to two limitations: (a) Due to the absence of data on missing time, the model tends to overfit to irrelevant features, leading to content distortion. (b) Due to the lack of continuous temporal supervision, the model fails to learn the continuous kinetics law over time, causing temporal discontinuities. For the first time, we propose MRI Contrast Enhancement Kinetics World model (MRI CEKWorld) with SpatioTemporal Consistency Learning (STCL). For (a), guided by the spatial law that patient-level structures remain consistent during enhancement, we propose Latent Alignment Learning (LAL) that constructs a patient-specific template to constrain contents to align with this template. For (b), guided by the temporal law that the kinetics follow a consistent smooth trend, we propose Latent Difference Learning (LDL) which extends the unobserved intervals by interpolation and constrains smooth variations in the latent space among interpolated sequences. Extensive experiments on two datasets show our MRI CEKWorld achieves better realistic contents and kinetics. Codes will be available at https://github.com/DD0922/MRI-Contrast-Enhancement-Kinetics-World-Model.

Problem

• MRI contrast enhancement
• world model
• temporal resolution
• kinetics modeling
• sparsely sampled data

Innovation

• World Model
• Contrast Enhancement Kinetics
• SpatioTemporal Consistency
• Latent Alignment Learning
• Latent Difference Learning