Generation of high-resolution MPRAGE-like images from 3D head MRI localizer (AutoAlign Head) images using a deep learning-based model

TL;DR

This study uses deep learning to convert MRI localizer images into high-quality MPRAGE-like images, which could help in diagnosing dementia and neurodegenerative diseases.

Contribution

A novel deep learning model is proposed to generate high-resolution MPRAGE-like images from 3D MRI localizers for improved diagnostic evaluation.

Findings

The model achieved high image quality metrics: PSNR 35.4, SSIM 0.871, and LPIPS 0.045 on the test dataset.

Dice scores for major brain structures ranged from 0.788 to 0.926, indicating good structural similarity.

Visual scores showed strong agreement (kappa 0.80–0.88) for medial temporal lobe atrophy assessment.

Abstract

Magnetization prepared rapid gradient echo (MPRAGE) is a useful three-dimensional (3D) T1-weighted sequence, but is not a priority in routine brain examinations. We hypothesized that converting 3D MRI localizer (AutoAlign Head) images to MPRAGE-like images with deep learning (DL) would be beneficial for diagnosing and researching dementia and neurodegenerative diseases. We aimed to establish and evaluate a DL-based model for generating MPRAGE-like images from MRI localizers.

Brain MRI examinations including MPRAGE taken at a single institution for investigation of mild cognitive impairment, dementia and epilepsy between January 2020 and December 2022 were included retrospectively. Images taken in 2020 or 2021 were assigned to training and validation datasets, and images from 2022 were used for the test dataset. Using the training and validation set, we determined one model using visual evaluation by radiologists with reference to image quality metrics of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Learned Perceptual Image Patch Similarity (LPIPS). The test dataset was evaluated by visual assessment and quality metrics. Voxel-based morphometric analysis was also performed, and we evaluated Dice score and volume differences between generated and original images of major structures were calculated as absolute symmetrized percent change.

Training, validation, and test datasets comprised 340 patients (mean age, 56.1 ± 24.4 years; 195 women), 36 patients (67.3 ± 18.3 years, 20 women), and 193 patients (59.5 ± 24.4 years; 111 women), respectively. The test dataset showed: PSNR, 35.4 ± 4.91; SSIM, 0.871 ± 0.058; and LPIPS 0.045 ± 0.017. No overfitting was observed. Dice scores for the segmentation of main structures ranged from 0.788 (left amygdala) to 0.926 (left ventricle). Quadratic weighted Cohen kappa values of visual score for medial temporal lobe between original and generated images were 0.80–0.88.

Images generated using our DL-based model can be used for post-processing and visual evaluation of medial temporal lobe atrophy.

The online version contains supplementary material available at 10.1007/s11604-024-01728-8.

Figures