Evaluation of Machine Learning Reconstruction Techniques for Accelerated Brain MRI Scans

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mandel, Jonathan I., Hiremath, Shivaprakash, Keshtgar, Hedyeh, Scholl, Timothy, Raeisi, Sadegh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918138076987392
author Mandel, Jonathan I.
Hiremath, Shivaprakash
Keshtgar, Hedyeh
Scholl, Timothy
Raeisi, Sadegh
author_facet Mandel, Jonathan I.
Hiremath, Shivaprakash
Keshtgar, Hedyeh
Scholl, Timothy
Raeisi, Sadegh
contents This retrospective-prospective study evaluated whether a deep learning-based MRI reconstruction algorithm can preserve diagnostic quality in brain MRI scans accelerated up to fourfold, using both public and prospective clinical data. The study included 18 healthy volunteers (scans acquired at 3T, January 2024-March 2025), as well as selected fastMRI public datasets with diverse pathologies. Phase-encoding-undersampled 2D/3D T1, T2, and FLAIR sequences were reconstructed with DeepFoqus-Accelerate and compared with standard-of-care (SOC). Three board-certified neuroradiologists and two MRI technologists independently reviewed 36 paired SOC/AI reconstructions from both datasets using a 5-point Likert scale, while quantitative similarity was assessed for 408 scans and 1224 datasets using Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Haar wavelet-based Perceptual Similarity Index (HaarPSI). No AI-reconstructed scan scored below 3 (minimally acceptable), and 95% scored $\geq 4$. Mean SSIM was 0.95 $\pm$ 0.03 (90% cases >0.90), PSNR >41.0 dB, and HaarPSI >0.94. Inter-rater agreement was slight to moderate. Rare artifacts did not affect diagnostic interpretation. These findings demonstrate that DeepFoqus-Accelerate enables robust fourfold brain MRI acceleration with 75% reduced scan time, while preserving diagnostic image quality and supporting improved workflow efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07193
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluation of Machine Learning Reconstruction Techniques for Accelerated Brain MRI Scans
Mandel, Jonathan I.
Hiremath, Shivaprakash
Keshtgar, Hedyeh
Scholl, Timothy
Raeisi, Sadegh
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
This retrospective-prospective study evaluated whether a deep learning-based MRI reconstruction algorithm can preserve diagnostic quality in brain MRI scans accelerated up to fourfold, using both public and prospective clinical data. The study included 18 healthy volunteers (scans acquired at 3T, January 2024-March 2025), as well as selected fastMRI public datasets with diverse pathologies. Phase-encoding-undersampled 2D/3D T1, T2, and FLAIR sequences were reconstructed with DeepFoqus-Accelerate and compared with standard-of-care (SOC). Three board-certified neuroradiologists and two MRI technologists independently reviewed 36 paired SOC/AI reconstructions from both datasets using a 5-point Likert scale, while quantitative similarity was assessed for 408 scans and 1224 datasets using Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Haar wavelet-based Perceptual Similarity Index (HaarPSI). No AI-reconstructed scan scored below 3 (minimally acceptable), and 95% scored $\geq 4$. Mean SSIM was 0.95 $\pm$ 0.03 (90% cases >0.90), PSNR >41.0 dB, and HaarPSI >0.94. Inter-rater agreement was slight to moderate. Rare artifacts did not affect diagnostic interpretation. These findings demonstrate that DeepFoqus-Accelerate enables robust fourfold brain MRI acceleration with 75% reduced scan time, while preserving diagnostic image quality and supporting improved workflow efficiency.
title Evaluation of Machine Learning Reconstruction Techniques for Accelerated Brain MRI Scans
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.07193