Improving Sensitivity of Arterial Spin Labeling Perfusion MRI in Alzheimer's Disease Using Transfer Learning of Deep Learning-Based ASL Denoising

Abstract

Background: Arterial spin labeling (ASL) perfusion magnetic resonance imaging (MRI) denoising through deep learning (DL) often faces insufficient training data from patients. One solution is to train DL models using healthy subjects' data which are more widely available and transfer them to patients' data.

Purpose: To evaluate the transferability of a DL-based ASL MRI denoising method (DLASL).

Study type: Retrospective.

Subjects: Four hundred and twenty-eight subjects (189 females) from three cohorts.

Field strength/sequence: 3 T two-dimensional (2D) echo-planar imaging (EPI)-based pseudo-continuous ASL (PCASL) and 2D EPI-based pulsed ASL (PASL) sequences.

Assessment: DLASL was trained using young healthy adults' PCASL data (Dataset 1: 250/30 subjects as training/validation set) and was directly transferred (DTF) to PCASL data from Dataset 2 (45 subjects test set) of normal controls (NC) and Alzheimer's disease (AD) groups. DLASL was fine-tuned (DLASLFT) and tested on PASL data from Dataset 3 (103 subjects test set) of NC and AD. An existing non-DL method (NonDL) was used for comparison. Cerebral blood flow (CBF) images from ASL MRI were compared between NC and AD to assess characteristic hypoperfusion (lower CBF) patterns in AD. CBF image quality and CBF map sensitivity for detecting hypoperfusion using peak t-value and suprathreshold cluster size are outcome measures.

Statistical tests: Paired t-test, two-sample t-test, one-way analysis of variance, and Tukey honestly significant difference, and linear mixed-effects models were used. P < 0.05 was considered statistically significant.

Results: Mean contrast-to-noise ratio (CNR) of Dataset 2 showed that DTF outperformed NonDL (AD: 3.38 vs. 2.64, NC: 3.80 vs. 3.36). On Dataset 3, DLASLFT outperformed NonDL measured by mean CNR (AD: 2.45 vs. 1.87, NC: 2.54 vs. 2.17) and mean radiologic score (2.86 vs. 2.44). Image quality improvement was significant on both test sets. DTF and DLASLFT improved sensitivity for detecting AD-related hypoperfusion patterns compared with NonDL.

Data conclusion: We demonstrated the DLASL's transferability across different ASL sequences and different populations.

Level of evidence: 3 TECHNICAL EFFICACY: Stage 2.

Keywords: Alzheimer's disease; arterial spin labeling perfusion MRI; deep learning; denoising; transfer learning.