$TrIND$: Representing Anatomical Trees by Denoising Diffusion of Implicit Neural Fields

TL;DR

This paper introduces $TrIND$, a novel method that uses implicit neural representations and denoising diffusion to accurately and efficiently model complex anatomical trees at any resolution, improving over traditional imaging techniques.

Contribution

$TrIND$ is the first approach to combine implicit neural representations with diffusion models for detailed and flexible anatomical tree modeling.

Findings

High-fidelity reconstruction of anatomical trees

Compact storage and arbitrary resolution capabilities

Versatility across different anatomical sites

Abstract

Anatomical trees play a central role in clinical diagnosis and treatment planning. However, accurately representing anatomical trees is challenging due to their varying and complex topology and geometry. Traditional methods for representing tree structures, captured using medical imaging, while invaluable for visualizing vascular and bronchial networks, exhibit drawbacks in terms of limited resolution, flexibility, and efficiency. Recently, implicit neural representations (INRs) have emerged as a powerful tool for representing shapes accurately and efficiently. We propose a novel approach, $TrIND$, for representing anatomical trees using INR, while also capturing the distribution of a set of trees via denoising diffusion in the space of INRs. We accurately capture the intricate geometries and topologies of anatomical trees at any desired resolution. Through extensive qualitative and quantitative evaluation, we demonstrate high-fidelity tree reconstruction with arbitrary resolution yet compact storage, and versatility across anatomical sites and tree complexities. The code is available at: \texttt{\url{https://github.com/sinashish/TreeDiffusion}}.