ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2207.03105
33
7

Uncertainty-Aware Self-supervised Neural Network for Liver T1ρT_{1ρ}T1ρ​ Mapping with Relaxation Constraint

7 July 2022
Chaoxing Huang
Yurui Qian
S. Yu
Jian Hou
B. Jiang
Queenie Chan
V. Wong
Winnie Chiu Wing Chu
Weitian Chen
ArXivPDFHTML
Abstract

T1ρT_{1\rho}T1ρ​ mapping is a promising quantitative MRI technique for the non-invasive assessment of tissue properties. Learning-based approaches can map T1ρT_{1\rho}T1ρ​ from a reduced number of T1ρT_{1\rho}T1ρ​ weighted images, but requires significant amounts of high quality training data. Moreover, existing methods do not provide the confidence level of the T1ρT_{1\rho}T1ρ​ estimation. To address these problems, we proposed a self-supervised learning neural network that learns a T1ρT_{1\rho}T1ρ​ mapping using the relaxation constraint in the learning process. Epistemic uncertainty and aleatoric uncertainty are modelled for the T1ρT_{1\rho}T1ρ​ quantification network to provide a Bayesian confidence estimation of the T1ρT_{1\rho}T1ρ​ mapping. The uncertainty estimation can also regularize the model to prevent it from learning imperfect data. We conducted experiments on T1ρT_{1\rho}T1ρ​ data collected from 52 patients with non-alcoholic fatty liver disease. The results showed that our method outperformed the existing methods for T1ρT_{1\rho}T1ρ​ quantification of the liver using as few as two T1ρT_{1\rho}T1ρ​-weighted images. Our uncertainty estimation provided a feasible way of modelling the confidence of the self-supervised learning based T1ρT_{1\rho}T1ρ​ estimation, which is consistent with the reality in liver T1ρT_{1\rho}T1ρ​ imaging.

View on arXiv
Comments on this paper