Cargando…

Homologous point transformer for multi-modality prostate image registration

Registration is the process of transforming images so they are aligned in the same coordinate space. In the medical field, image registration is often used to align multi-modal or multi-parametric images of the same organ. A uniquely challenging subset of medical image registration is cross-modality...

Descripción completa

Detalles Bibliográficos
Autores principales: Ruchti, Alexander, Neuwirth, Alexander, Lowman, Allison K., Duenweg, Savannah R., LaViolette, Peter S., Bukowy, John D.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9748842/
https://www.ncbi.nlm.nih.gov/pubmed/36532813
http://dx.doi.org/10.7717/peerj-cs.1155
_version_ 1784849913379553280
author Ruchti, Alexander
Neuwirth, Alexander
Lowman, Allison K.
Duenweg, Savannah R.
LaViolette, Peter S.
Bukowy, John D.
author_facet Ruchti, Alexander
Neuwirth, Alexander
Lowman, Allison K.
Duenweg, Savannah R.
LaViolette, Peter S.
Bukowy, John D.
author_sort Ruchti, Alexander
collection PubMed
description Registration is the process of transforming images so they are aligned in the same coordinate space. In the medical field, image registration is often used to align multi-modal or multi-parametric images of the same organ. A uniquely challenging subset of medical image registration is cross-modality registration—the task of aligning images captured with different scanning methodologies. In this study, we present a transformer-based deep learning pipeline for performing cross-modality, radiology-pathology image registration for human prostate samples. While existing solutions for multi-modality prostate image registration focus on the prediction of transform parameters, our pipeline predicts a set of homologous points on the two image modalities. The homologous point registration pipeline achieves better average control point deviation than the current state-of-the-art automatic registration pipeline. It reaches this accuracy without requiring masked MR images which may enable this approach to achieve similar results in other organ systems and for partial tissue samples.
format Online
Article
Text
id pubmed-9748842
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-97488422022-12-15 Homologous point transformer for multi-modality prostate image registration Ruchti, Alexander Neuwirth, Alexander Lowman, Allison K. Duenweg, Savannah R. LaViolette, Peter S. Bukowy, John D. PeerJ Comput Sci Bioinformatics Registration is the process of transforming images so they are aligned in the same coordinate space. In the medical field, image registration is often used to align multi-modal or multi-parametric images of the same organ. A uniquely challenging subset of medical image registration is cross-modality registration—the task of aligning images captured with different scanning methodologies. In this study, we present a transformer-based deep learning pipeline for performing cross-modality, radiology-pathology image registration for human prostate samples. While existing solutions for multi-modality prostate image registration focus on the prediction of transform parameters, our pipeline predicts a set of homologous points on the two image modalities. The homologous point registration pipeline achieves better average control point deviation than the current state-of-the-art automatic registration pipeline. It reaches this accuracy without requiring masked MR images which may enable this approach to achieve similar results in other organ systems and for partial tissue samples. PeerJ Inc. 2022-12-01 /pmc/articles/PMC9748842/ /pubmed/36532813 http://dx.doi.org/10.7717/peerj-cs.1155 Text en © 2022 Ruchti et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Bioinformatics
Ruchti, Alexander
Neuwirth, Alexander
Lowman, Allison K.
Duenweg, Savannah R.
LaViolette, Peter S.
Bukowy, John D.
Homologous point transformer for multi-modality prostate image registration
title Homologous point transformer for multi-modality prostate image registration
title_full Homologous point transformer for multi-modality prostate image registration
title_fullStr Homologous point transformer for multi-modality prostate image registration
title_full_unstemmed Homologous point transformer for multi-modality prostate image registration
title_short Homologous point transformer for multi-modality prostate image registration
title_sort homologous point transformer for multi-modality prostate image registration
topic Bioinformatics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9748842/
https://www.ncbi.nlm.nih.gov/pubmed/36532813
http://dx.doi.org/10.7717/peerj-cs.1155
work_keys_str_mv AT ruchtialexander homologouspointtransformerformultimodalityprostateimageregistration
AT neuwirthalexander homologouspointtransformerformultimodalityprostateimageregistration
AT lowmanallisonk homologouspointtransformerformultimodalityprostateimageregistration
AT duenwegsavannahr homologouspointtransformerformultimodalityprostateimageregistration
AT laviolettepeters homologouspointtransformerformultimodalityprostateimageregistration
AT bukowyjohnd homologouspointtransformerformultimodalityprostateimageregistration