arXiv subjects

Mingke Li

Publications and source records attributed to Mingke Li.

3 recordsLinked to original sources

arXiv2026

DrivenMorph: Bridging Attention Mechanism and Variational Image Registration via Difference Modeling

Medical image registration benefits significantly from deep learning, yet existing approaches often lack physical explainability and fine-grained deformation control. Motivated by Demons algorithms, we propose a novel DrivenMorph framework that bridges attention mechanisms with variational image registration by incorporating difference modeling as a physically inspired inductive bias. The resulting driving force, computed from local differences in the latent feature space, provides explicit semantic guidance throughout the registration process. It directly drives the registration process through a neural Demons layer that simulates force-displacement interactions to generate smooth and anatomically consistent deformation. Unlike previous methods, our approach not only integrates traditional registration principles with popular deep networks, providing an explainable and efficient solution for learning-based medical image registration, but also separates difference modeling from deformation, improving modularity and explainability. Extensive experiments on multiple 3D brain MRI datasets demonstrate superior performance over state of-the-art learning-based and optimization-based methods. Furthermore, visualizations and statistical analyses confirm that the learned driving force aligns closely with actual deformation patterns, supporting its explanatory value.

cs.CV↗

arXiv2024

A Symmetric Dynamic Learning Framework for Diffeomorphic Medical Image Registration

Diffeomorphic image registration is crucial for various medical imaging applications because it can preserve the topology of the transformation. This study introduces DCCNN-LSTM-Reg, a learning framework that evolves dynamically and learns a symmetrical registration path by satisfying a specified control increment system. This framework aims to obtain symmetric diffeomorphic deformations between moving and fixed images. To achieve this, we combine deep learning networks with diffeomorphic mathematical mechanisms to create a continuous and dynamic registration architecture, which consists of multiple Symmetric Registration (SR) modules cascaded on five different scales. Specifically, our method first uses two U-nets with shared parameters to extract multiscale feature pyramids from the images. We then develop an SR-module comprising a sequential CNN-LSTM architecture to progressively correct the forward and reverse multiscale deformation fields using control increment learning and the homotopy continuation technique. Through extensive experiments on three 3D registration tasks, we demonstrate that our method outperforms existing approaches in both quantitative and qualitative evaluations.

eess.IV↗

arXiv2023

Collective action and spontaneity cycles: Cascading dynamics under Bayesian games

The formation mechanisms and cyclical conditions of collective action have become open issues in research involving public choice, social movements, and more. For this reason, on the basis of rational decision-making and social assimilation, this paper proposes an action model that combines Bayesian game and social network dynamics, and incorporates exogenous cycles into it. For this model, this paper proves the spontaneous action theorem and action cycle theorem of collective action, and based on numerical simulation and empirical calibration, further confirms the theoretical mechanism involving elements such as risk/risk-free incentives and the number of social ties. Based on such conclusions and evidence, this paper proposes a theory of spontaneous cycles as an integrative answer to the open question of collective action formation/cycles.

cs.SI↗