CogGen: Cognitive-Load-Informed Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction
This work addresses MRI reconstruction for medical imaging when training data or compute are limited, but it is incremental as it builds on existing unsupervised methods like DIP and INR.
The paper tackled the problem of fully unsupervised deep generative modeling for compressively sampled MRI reconstruction by proposing CogGen, which uses a cognitive-load-informed approach with staged inversion and easy-to-hard scheduling, resulting in improved reconstruction fidelity and convergence behavior compared to baselines.
Fully unsupervised deep generative modeling (FU-DGM) is promising for compressively sampled MRI (CS-MRI) when training data or compute are limited. Classical FU-DGMs such as DIP and INR rely on architectural priors, but the ill-conditioned inverse problem often demands many iterations and easily overfits measurement noise. We propose CogGen, a cognitive-load-informed FU-DGM that casts CS-MRI as staged inversion and regulates task-side "cognitive load" by progressively scheduling intrinsic difficulty and extraneous interference. CogGen replaces uniform data fitting with an easy-to-hard k-space weighting/selection strategy: early iterations emphasize low-frequency, high-SNR, structure-dominant samples, while higher-frequency or noise-dominated measurements are introduced later. We realize this schedule through self-paced curriculum learning (SPCL) with complementary criteria: a student mode that reflects what the model can currently learn and a teacher mode that indicates what it should follow, supporting both soft weighting and hard selection. Experiments and analyses show that CogGen-DIP and CogGen-INR improve reconstruction fidelity and convergence behavior compared with strong unsupervised baselines and competitive supervised pipelines.