Deep‐learned short tau inversion recovery imaging using multi‐contrast MR images

Abstract

Purpose To generate short tau, or short inversion time (TI), inversion recovery (STIR) images from three multi‐contrast MR images, without additional scanning, using a deep neural network. Methods For simulation studies, we used multi‐contrast simulation images. For in‐vivo studies, we acquired knee MR images including 288 slices of T1‐weighted (T1‐w), T2‐weighted (T2‐w), gradient‐recalled echo (GRE), and STIR images taken from 12 healthy volunteers. Our MR image synthesis method generates a new contrast MR image from multi‐contrast MR images. We used a deep neural network to identify the complex relationships between MR images that show various contrasts for the same tissues. Our contrast‐conversion deep neural network (CC‐DNN) is an end‐to‐end architecture that trains the model to create one image from three (T1‐w, T2‐w, and GRE images). We propose a new loss function to take into account intensity differences, misregistration, and local intensity variations. The CC‐DNN‐generated STIR images were evaluated with four quantitative evaluation metrics, including mean squared error, peak signal‐to‐noise ratio (PSNR), structural similarity (SSIM), and multi‐scale SSIM (MS‐SSIM). Furthermore, a subjective evaluation was performed by musculoskeletal radiologists. Results Our method showed improved results in all quantitative evaluations compared with other methods and received the highest scores in subjective evaluations by musculoskeletal radiologists. Conclusion This study suggests the feasibility of our method for generating STIR sequence images without additional scanning that offered a potential alternative to the STIR pulse sequence when additional scanning is limited or STIR artifacts are severe.

Generating Virtual Short Tau Inversion Recovery (STIR) Images from T1- and T2-Weighted Images Using a Conditional Generative Adversarial Network in Spine Imaging

“…This may be based on the fact that both T1 and T2 images contain independent information [ 23 ]; combining those naturally leads to an increase in information for different pathologies. To date, the only publication that combines T1 and T2 to generate a STIR sequence using deep learning was recently published by Kim et al [ 24 ]. With only 12 healthy volunteers, this study demonstrated that deep learning can be used to generate real-looking STIR images of a knee MRI.…”

Synthetic Contrasts in Musculoskeletal MRI

“…An example synthetic fat-saturated image from this study can be seen in Figure 4A. In a similar application, Kim et al 61 trained a neural network to generate synthetic STIR images from multiple input images (ie, T1w and T2w TSE images and 1 gradient-recalled echo image). With training data from 12 subjects, they found that they can produce synthetic STIR images that resemble an actual acquired STIR image (see Fig.…”

Deep Learning and Its Application to Function Approximation for MR in Medicine: An Overview

“…133 For synthesizing a short inversion time inversion recovery (STIR) image, a DNN approximated a function which produced a STIR image from T1-weighted, T2-weighted, and gradient-recalled echo images. 134 As a part of a T2 mapping method, ANNs approximated functions that produced a T2weighted image for several types of tissues from a T1weighted image. 135…”