# An Uncertainty Aided Framework for Learning based Liver T1ρ Mapping and Analysis

arXiv: https://arxiv.org/abs/2307.02736 · HTML: https://mlsanity.com/paper/2307.02736/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 6 Jul 2023.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference](https://mlsanity.com/paper/1909.13550/) (2019)
- [BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks](https://mlsanity.com/paper/2207.06873/) (2022)
- [Calibration of Model Uncertainty for Dropout Variational Inference](https://mlsanity.com/paper/2006.11584/) (2020)
- [Robust Depth Completion with Uncertainty-Driven Loss Functions](https://mlsanity.com/paper/2112.07895/) (2021)
- [Uncertainty-Aware Self-supervised Neural Network for Liver T1ρ Mapping with Relaxation Constraint](https://mlsanity.com/paper/2207.03105/) (2022)
- [Highly accelerated MR parametric mapping by undersampling the k-space and reducing the contrast number simultaneously with deep learning](https://mlsanity.com/paper/2112.00730/) (2021)

## Built on by (most cited first, 1 of 1)

- [Chemical Shift Encoding based Double Bonds Quantification in Triglycerides using Deep Image Prior](https://mlsanity.com/paper/2407.01926/) (2024)

## Abstract (arXiv)

Objective: Quantitative T1ρ imaging has potential for assessment of biochemical alterations of liver pathologies. Deep learning methods have been employed to accelerate quantitative T1ρ imaging. To employ artificial intelligence-based quantitative imaging methods in complicated clinical environment, it is valuable to estimate the uncertainty of the predicated T1ρ values to provide the confidence level of the quantification results. The uncertainty should also be utilized to aid the post-hoc quantitative analysis and model learning tasks. Approach: To address this need, we propose a parametric map refinement approach for learning-based T1ρ mapping and train the model in a probabilistic way to model the uncertainty. We also propose to utilize the uncertainty map to spatially weight the training of an improved T1ρ mapping network to further improve the mapping performance and to remove pixels with unreliable T1ρ values in the region of interest. The framework was tested on a dataset of 51 patients with different liver fibrosis stages. Main results: Our results indicate that the learning-based map refinement method leads to a relative mapping error of less than 3% and provides uncertainty estimation simultaneously. The estimated uncertainty reflects the actual error level, and it can be used to further reduce relative T1ρ mapping error to 2.60% as well as removing unreliable pixels in the region of interest effectively. Significance: Our studies demonstrate the proposed approach has potential to provide a learning-based quantitative MRI system for trustworthy T1ρ mapping of the liver.