Physics‐guided self‐supervised learning for retrospective T1 and T2 map** from conventional weighted brain MRI: Technical developments and initial validation …
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 …
T2 values from clinical weighted MRI. Methods A self‐supervised learning approach was …
Deep learning-based water-fat separation from dual-echo chemical shift-encoded imaging
Conventional water–fat separation approaches suffer long computational times and are
prone to water/fat swaps. To solve these problems, we propose a deep learning-based dual …
prone to water/fat swaps. To solve these problems, we propose a deep learning-based dual …
Breathing freely: self-supervised liver T1rho map** from a single T1rho-weighted image
Quantitative T1rho imaging is a promising technique for assessment of chronic liver disease.
The standard approach requires acquisition of multiple T1rho-weighted images of the liver to …
The standard approach requires acquisition of multiple T1rho-weighted images of the liver to …
[PDF][PDF] Tackling Distribution Shifts in Machine Learning-Based Medical Image Analysis
N Karani - 2022 - research-collection.ethz.ch
Machine learning algorithms-in particular, those based on convolutional neural networks
(CNNs)-have demonstrated remarkable promise in a number of medical image analysis …
(CNNs)-have demonstrated remarkable promise in a number of medical image analysis …