Layer Selection in Feature-Based Losses Affects Image Quality and Microstructural Consistency in Deep Learning Super-Resolution of Brain Diffusion MRI

TL;DR

This study explores how different layer selections in feature-based loss functions impact image quality and microstructural consistency in deep learning super-resolution of brain diffusion MRI.

Contribution

It demonstrates that shallow layers in VGG16 minimize artifacts and improve diffusion parameter accuracy in super-resolution MRI.

Findings

Deeper VGG16 layers cause grid-like artifacts in super-resolved images.

Using the shallowest layer preserves diffusion signal and reduces artifacts.

Layer choice significantly affects image quality and microstructural measurement accuracy.

Abstract

Clinical application of high-resolution diffusion MRI is hindered by hardware limitations and prohibitive scan times, motivating computational super-resolution. This study investigates the efficacy of a feature-based loss function in preserving diffusion signal consistency in deep learning super-resolution. Using 7T data from the human connectome project to generate pairs of low- and high-resolution diffusion weighted images (DWI), we trained UNets for 2D super-resolution. Ablation and isolation studies evaluated different VGG16-layers for feature-based losses against an image-based L1 baseline. Deeper layers and combinations thereof resulted in grid-like artifacts in super-resolution DWIs, which persisted in diffusion parameters like quantitative and fractional anisotropy. No such artifacts were present when using the shallowest layer. Downstream analysis for this layer showed great consistency with the ground truth, even for 9-fold super-resolution. Image SNR and used VGG16-layer depths modulated artifact appearance and severity, mandating careful selection of contributing layers for application in and beyond diffusion MRI.