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

arXiv: https://arxiv.org/abs/2605.15895 · HTML: https://mlsanity.com/paper/2605.15895/

## 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 (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [fastai: A Layered API for Deep Learning](https://mlsanity.com/paper/2002.04688/) (2020)
- [DaViT: Dual Attention Vision Transformers](https://mlsanity.com/paper/2204.03645/) (2022)
- [Multi-Contrast Super-Resolution MRI Through a Progressive Network](https://mlsanity.com/paper/1908.01612/) (2019)
- [Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize](https://mlsanity.com/paper/1707.02937/) (2017)
- [SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networks](https://mlsanity.com/paper/2106.02599/) (2021)
- [Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledge](https://mlsanity.com/paper/2102.02711/) (2021)
- [Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI](https://mlsanity.com/paper/2106.13188/) (2021)
- [Angular Super-Resolution in Diffusion MRI with a 3D Recurrent Convolutional Autoencoder](https://mlsanity.com/paper/2203.15598/) (2022)
- [Edge-Aware Deep Image Deblurring](https://mlsanity.com/paper/1907.02282/) (2019)
- [SRDTI: Deep learning-based super-resolution for diffusion tensor MRI](https://mlsanity.com/paper/2102.09069/) (2021)

## 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.