# Deeper Image Quality Transfer: Training Low-Memory Neural Networks for 3D Images

arXiv: https://arxiv.org/abs/1808.05577 · HTML: https://mlsanity.com/paper/1808.05577/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2018.

## Built on by (most cited first, 8 of 8)

- [Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge](https://mlsanity.com/paper/2405.03328/) (2024)
- [Low-field magnetic resonance image enhancement via stochastic image quality transfer](https://mlsanity.com/paper/2304.13385/) (2023)
- [Brain Latent Progression: Individual-based Spatiotemporal Disease Progression on 3D Brain MRIs via Latent Diffusion](https://mlsanity.com/paper/2502.08560/) (2025)
- [Diffusion MRI with Machine Learning](https://mlsanity.com/paper/2402.00019/) (2024)
- [Alternative Learning Paradigms for Image Quality Transfer](https://mlsanity.com/paper/2411.05885/) (2024)
- [Short-Term Memory Convolutions](https://mlsanity.com/paper/2302.04331/) (2023)
- [Transfer Learning in Conversational Analysis through Reusing Preprocessing Data as Supervisors](https://mlsanity.com/paper/2112.03032/) (2021)
- [Deformably-Scaled Transposed Convolution](https://mlsanity.com/paper/2210.09446/) (2022)

## Abstract (arXiv)

In this paper we address the memory demands that come with the processing of 3-dimensional, high-resolution, multi-channeled medical images in deep learning. We exploit memory-efficient backpropagation techniques, to reduce the memory complexity of network training from being linear in the network's depth, to being roughly constant  -  permitting us to elongate deep architectures with negligible memory increase. We evaluate our methodology in the paradigm of Image Quality Transfer, whilst noting its potential application to various tasks that use deep learning. We study the impact of depth on accuracy and show that deeper models have more predictive power, which may exploit larger training sets. We obtain substantially better results than the previous state-of-the-art model with a slight memory increase, reducing the root-mean-squared-error by  13% . Our code is publicly available.