mlsanityData to 14 Oct 2026

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

arXiv 2605.15895 ↗First posted 15 May 2026eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 32 references that are in the map. First posted on arXiv 15 May 2026.

Builds on

13 of 32 references.

References · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  3. 2018Self-Attention Generative Adversarial Networkscited by 809
  4. 2020fastai: A Layered API for Deep Learningcited by 183
  5. 2022DaViT: Dual Attention Vision Transformerscited by 175
  6. 2019Multi-Contrast Super-Resolution MRI Through a Progressive Networkcited by 45
  7. 2017Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resizecited by 37
  8. 2021SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networkscited by 18
  9. 2021Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledgecited by 11
  10. 2021Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRIcited by 11
  11. 2022Angular Super-Resolution in Diffusion MRI with a 3D Recurrent Convolutional Autoencodercited by 8
  12. 2019Edge-Aware Deep Image Deblurringcited by 6
1 more
  1. 2021SRDTI: Deep learning-based super-resolution for diffusion tensor MRIcited by 4

Built on by

Not cited yet.