# Memory Efficient Invertible Neural Networks for 3D Photoacoustic Imaging

arXiv: https://arxiv.org/abs/2204.11850 · HTML: https://mlsanity.com/paper/2204.11850/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 24 Apr 2022.

## Builds on (most cited first, 2 of 2)

- [Model based learning for accelerated, limited-view 3D photoacoustic tomography](https://mlsanity.com/paper/1708.09832/) (2017)
- [i-RIM applied to the fastMRI challenge](https://mlsanity.com/paper/1910.08952/) (2019)

## Built on by (most cited first, 3 of 3)

- [Solving multiphysics-based inverse problems with learned surrogates and constraints](https://mlsanity.com/paper/2307.11099/) (2023)
- [Model-corrected learned primal-dual models for fast limited-view photoacoustic tomography](https://mlsanity.com/paper/2304.01963/) (2023)
- [InvertibleNetworks.jl: A Julia package for scalable normalizing flows](https://mlsanity.com/paper/2312.13480/) (2023)

## Abstract (arXiv)

Photoacoustic imaging (PAI) can image high-resolution structures of clinical interest such as vascularity in cancerous tumor monitoring. When imaging human subjects, geometric restrictions force limited-view data retrieval causing imaging artifacts. Iterative physical model based approaches reduce artifacts but require prohibitively time consuming PDE solves. Machine learning (ML) has accelerated PAI by combining physical models and learned networks. However, the depth and overall power of ML methods is limited by memory intensive training. We propose using invertible neural networks (INNs) to alleviate memory pressure. We demonstrate INNs can image 3D photoacoustic volumes in the setting of limited-view, noisy, and subsampled data. The frugal constant memory usage of INNs enables us to train an arbitrary depth of learned layers on a consumer GPU with 16GB RAM.