Uncertainty-aware self-supervised neural network for liverT1ρmapping with relaxation constraint

Physics-guided self-supervised learning for retrospective T1 and T2 mapping from conventional weighted brain MRI: Technical developments and initial validation in glioblastoma

PURPOSE

To develop a self-supervised learning method to retrospectively estimate T1 and T2 values from clinical weighted MRI.

METHODS

A self-supervised learning approach was constructed to estimate T1, T2, and proton density maps from conventional T1- and T2-weighted images. MR physics models were employed to regenerate the weighted images from the network outputs, and the network was optimized based on loss calculated between the synthesized and input weighted images, alongside additional constraints based on prior information. The method was evaluated on healthy volunteer data, with conventional mapping as references. The reproducibility was examined on two 3.0T scanners. Performance in tumor characterization was inspected by applying the method to a public glioblastoma dataset.

RESULTS

For T1 and T2 estimation from three weighted images (T1 MPRAGE, T1 gradient echo sequences, and T2 turbo spin echo), the deep learning method achieved global voxel-wise error ≤9% in brain parenchyma and regional error ≤12.2% in six types of brain tissues. The regional measurements obtained from two scanners showed mean differences ≤2.4% and correlation coefficients >0.98, demonstrating excellent reproducibility. In the 50 glioblastoma patients, the retrospective quantification results were in line with literature reports from prospective methods, and the T2 values were found to be higher in tumor regions, with sensitivity of 0.90 and specificity of 0.92 in a voxel-wise classification task between normal and abnormal regions.

CONCLUSION

The self-supervised learning method is promising for retrospective T1 and T2 quantification from clinical MR images, with the potential to improve the availability of quantitative MRI and facilitate brain tumor characterization.

An uncertainty aided framework for learning based liverT1ρmapping and analysis

Objective. QuantitativeT1ρimaging has potential for assessment of biochemical alterations of liver pathologies. Deep learning methods have been employed to accelerate quantitativeT1ρimaging. To employ artificial intelligence-based quantitative imaging methods in complicated clinical environment, it is valuable to estimate the uncertainty of the predicatedT1ρvalues 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-basedT1ρmapping 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 improvedT1ρmapping network to further improve the mapping performance and to remove pixels with unreliableT1ρvalues 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 relativeT1ρmapping 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 trustworthyT1ρmapping of the liver.

Uncertainty-weighted Multi-tasking for T1ρ and T2 Mapping in the Liver with Self-supervised Learning

Multi-parametric mapping of MRI relaxations in liver has the potential of revealing pathological information of the liver. A self-supervised learning based multi-parametric mapping method is proposed to map T1ρ and T2 simultaneously, by utilising the relaxation constraint in the learning process. Data noise of different mapping tasks is utilised to make the model uncertainty-aware, which adaptively weight different mapping tasks during learning. The method was examined on a dataset of 51 patients with non-alcoholic fatter liver disease. Results showed that the proposed method can produce comparable parametric maps to the traditional multi-contrast pixel wise fitting method, with a reduced number of images and less computation time. The uncertainty weighting also improves the model performance. It has the potential of accelerating MRI quantitative imaging.