Neural Modulation Fields for Conditional Cone Beam Neural Tomography

Samuele Papa, David M Knigge, Riccardo Valperga, Nikita Moriakov, Miltiadis Kofinas, Jan-jakob Sonke, Efstratios Gavves

Keywords: tomography, inverse problems, neural fields, physics-inspired machine learning, neural networks

TL;DR: CondCBNT is a deep learning method for accurate CBCT density reconstructions. It uses a conditional neural field and patient-specific modulations, achieving improved performance with varying projection numbers on noise-free and noisy data.

Abstract: Conventional Computed Tomography (CT) methods require large numbers of noise-free projections for accurate density reconstructions, limiting their applicability to the more complex class of Cone Beam Geometry CT (CBCT) reconstruction. Recently, deep learning methods have been proposed to overcome these limitations. Our focus is improving methods based on neural fields (NFs), which have shown strong results by approximating in a continuous field the reconstructed density through a neural network. Unlike previous work, which requires training an NF from scratch for each new set of projections, we instead propose to leverage anatomical consistencies over different scans by training a single conditional NF on a dataset of projections. We propose a novel conditioning method where local modulations are modeled per patient as a field over the input domain through a Neural Modulation Field (NMF). The resulting Conditional Cone Beam Neural Tomography (CondCBNT) shows improved performance for both high and low numbers of available projections on noise-free and noisy data.

Submission Number: 56