CogGen: Cognitive-Load-Informed Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhu, Qingyong, Tan, Yumin, Gu, Xiang, Liang, Dong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910057032056832
author Zhu, Qingyong
Tan, Yumin
Gu, Xiang
Liang, Dong
author_facet Zhu, Qingyong
Tan, Yumin
Gu, Xiang
Liang, Dong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_04438
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CogGen: Cognitive-Load-Informed Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction
Zhu, Qingyong
Tan, Yumin
Gu, Xiang
Liang, Dong
Image and Video Processing
Artificial Intelligence
Machine Learning
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.
title CogGen: Cognitive-Load-Informed Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction
topic Image and Video Processing
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.04438