Application of Spherical Convolutional Neural Networks to Image Reconstruction and Denoising in Nuclear Medicine

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hashemi, Amirreza, Feng, Yuemeng, Rahmim, Arman, Sabet, Hamid
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915129958858752
author Hashemi, Amirreza
Feng, Yuemeng
Rahmim, Arman
Sabet, Hamid
author_facet Hashemi, Amirreza
Feng, Yuemeng
Rahmim, Arman
Sabet, Hamid
contents This work investigates use of equivariant neural networks as efficient and high-performance frameworks for image reconstruction and denoising in nuclear medicine. Our work aims to tackle limitations of conventional Convolutional Neural Networks (CNNs), which require significant training. We investigated equivariant networks, aiming to reduce CNN's dependency on specific training sets. Specifically, we implemented and evaluated equivariant spherical CNNs (SCNNs) for 2- and 3-dimensional medical imaging problems. Our results demonstrate superior quality and computational efficiency of SCNNs in both image reconstruction and denoising benchmark problems. Furthermore, we propose a novel approach to employ SCNNs as a complement to conventional image reconstruction tools, enhancing the outcomes while reducing reliance on the training set. Across all cases, we observed significant decrease in computational cost by leveraging the inherent inclusion of equivariant representatives while achieving the same or higher quality of image processing using SCNNs compared to CNNs. Additionally, we explore the potential of SCNNs for broader tomography applications, particularly those requiring rotationally variant representation.
format Preprint
id arxiv_https___arxiv_org_abs_2307_03298
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Application of Spherical Convolutional Neural Networks to Image Reconstruction and Denoising in Nuclear Medicine
Hashemi, Amirreza
Feng, Yuemeng
Rahmim, Arman
Sabet, Hamid
Image and Video Processing
Machine Learning
Medical Physics
This work investigates use of equivariant neural networks as efficient and high-performance frameworks for image reconstruction and denoising in nuclear medicine. Our work aims to tackle limitations of conventional Convolutional Neural Networks (CNNs), which require significant training. We investigated equivariant networks, aiming to reduce CNN's dependency on specific training sets. Specifically, we implemented and evaluated equivariant spherical CNNs (SCNNs) for 2- and 3-dimensional medical imaging problems. Our results demonstrate superior quality and computational efficiency of SCNNs in both image reconstruction and denoising benchmark problems. Furthermore, we propose a novel approach to employ SCNNs as a complement to conventional image reconstruction tools, enhancing the outcomes while reducing reliance on the training set. Across all cases, we observed significant decrease in computational cost by leveraging the inherent inclusion of equivariant representatives while achieving the same or higher quality of image processing using SCNNs compared to CNNs. Additionally, we explore the potential of SCNNs for broader tomography applications, particularly those requiring rotationally variant representation.
title Application of Spherical Convolutional Neural Networks to Image Reconstruction and Denoising in Nuclear Medicine
topic Image and Video Processing
Machine Learning
Medical Physics
url https://arxiv.org/abs/2307.03298