Estimating Neural Orientation Distribution Fields on High Resolution Diffusion MRI Scans

TL;DR

This paper introduces HashEnc, a grid-hash-encoding method for estimating neural orientation distribution fields in high-resolution diffusion MRI scans, improving quality and efficiency over existing approaches.

Contribution

The paper presents HashEnc, a novel encoding technique that scales neural ODF estimation to large MRI scans with better quality and reduced computational cost.

Findings

HashEnc achieves 10% better image quality.

Requires 3x less computational resources.

Effective in preserving structural details.

Abstract

The Orientation Distribution Function (ODF) characterizes key brain microstructural properties and plays an important role in understanding brain structural connectivity. Recent works introduced Implicit Neural Representation (INR) based approaches to form a spatially aware continuous estimate of the ODF field and demonstrated promising results in key tasks of interest when compared to conventional discrete approaches. However, traditional INR methods face difficulties when scaling to large-scale images, such as modern ultra-high-resolution MRI scans, posing challenges in learning fine structures as well as inefficiencies in training and inference speed. In this work, we propose HashEnc, a grid-hash-encoding-based estimation of the ODF field and demonstrate its effectiveness in retaining structural and textural features. We show that HashEnc achieves a 10% enhancement in image quality while requiring 3x less computational resources than current methods. Our code can be found at https://github.com/MunzerDw/NODF-HashEnc.