Novel feature-based method for multi-modal biomedical image registration compared to intensity-based technique

Abstract Multimodal image registration plays a crucial role in biomedical research, enabling the integration of complementary information from different imaging techniques. We present a novel feature-based approach for multimodal image registration, alongside traditional intensity-based methods. Our...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammad Javad Shojaei, Lichen Yang, Kazem Shojaei, Jeerapat Doungchawee, Richard W. Vachet
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-12862-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763812558766080
author Mohammad Javad Shojaei
Lichen Yang
Kazem Shojaei
Jeerapat Doungchawee
Richard W. Vachet
author_facet Mohammad Javad Shojaei
Lichen Yang
Kazem Shojaei
Jeerapat Doungchawee
Richard W. Vachet
author_sort Mohammad Javad Shojaei
collection DOAJ
description Abstract Multimodal image registration plays a crucial role in biomedical research, enabling the integration of complementary information from different imaging techniques. We present a novel feature-based approach for multimodal image registration, alongside traditional intensity-based methods. Our method, inspired by SPP-net architecture, employs multi-level feature extraction for robust image alignment. Additionally, we perform t-SNE dimensionality reduction on the MALDI-MSI dataset to enhance feature discrimination and visualization. We evaluated both approaches using datasets from the ANHIR Grand Challenge and mass spectrometry imaging modalities (LA-ICP-MS and MALDI-MSI). The proposed feature-based method achieved comparable accuracy to optimized intensity-based approaches, with Dice Coefficients of 0.95 for ANHIR samples (e.g., COAD_05) and 0.97 for mass spectrometry data, while requiring approximately 50% less computational time. Quantitative evaluation through Mutual Information metrics and Hausdorff Distance demonstrated high registration accuracy across different tissue types and imaging modalities. These results establish our feature-based approach as an efficient alternative to traditional intensity-based methods for multimodal image registration in biomedical applications.
format Article
id doaj-art-67def5749a4745c490f77f2ac1e982e4
institution DOAJ
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-67def5749a4745c490f77f2ac1e982e42025-08-20T03:05:18ZengNature PortfolioScientific Reports2045-23222025-08-0115111710.1038/s41598-025-12862-2Novel feature-based method for multi-modal biomedical image registration compared to intensity-based techniqueMohammad Javad Shojaei0Lichen Yang1Kazem Shojaei2Jeerapat Doungchawee3Richard W. Vachet4Department of Materials, Imperial College LondonSchool of Computing, Newcastle UniversitySchool of Medicine, Tehran University of Medical SciencesDepartment of Chemistry, University of Massachusetts AmherstDepartment of Chemistry, University of Massachusetts AmherstAbstract Multimodal image registration plays a crucial role in biomedical research, enabling the integration of complementary information from different imaging techniques. We present a novel feature-based approach for multimodal image registration, alongside traditional intensity-based methods. Our method, inspired by SPP-net architecture, employs multi-level feature extraction for robust image alignment. Additionally, we perform t-SNE dimensionality reduction on the MALDI-MSI dataset to enhance feature discrimination and visualization. We evaluated both approaches using datasets from the ANHIR Grand Challenge and mass spectrometry imaging modalities (LA-ICP-MS and MALDI-MSI). The proposed feature-based method achieved comparable accuracy to optimized intensity-based approaches, with Dice Coefficients of 0.95 for ANHIR samples (e.g., COAD_05) and 0.97 for mass spectrometry data, while requiring approximately 50% less computational time. Quantitative evaluation through Mutual Information metrics and Hausdorff Distance demonstrated high registration accuracy across different tissue types and imaging modalities. These results establish our feature-based approach as an efficient alternative to traditional intensity-based methods for multimodal image registration in biomedical applications.https://doi.org/10.1038/s41598-025-12862-2
spellingShingle Mohammad Javad Shojaei
Lichen Yang
Kazem Shojaei
Jeerapat Doungchawee
Richard W. Vachet
Novel feature-based method for multi-modal biomedical image registration compared to intensity-based technique
Scientific Reports
title Novel feature-based method for multi-modal biomedical image registration compared to intensity-based technique
title_full Novel feature-based method for multi-modal biomedical image registration compared to intensity-based technique
title_fullStr Novel feature-based method for multi-modal biomedical image registration compared to intensity-based technique
title_full_unstemmed Novel feature-based method for multi-modal biomedical image registration compared to intensity-based technique
title_short Novel feature-based method for multi-modal biomedical image registration compared to intensity-based technique
title_sort novel feature based method for multi modal biomedical image registration compared to intensity based technique
url https://doi.org/10.1038/s41598-025-12862-2
work_keys_str_mv AT mohammadjavadshojaei novelfeaturebasedmethodformultimodalbiomedicalimageregistrationcomparedtointensitybasedtechnique
AT lichenyang novelfeaturebasedmethodformultimodalbiomedicalimageregistrationcomparedtointensitybasedtechnique
AT kazemshojaei novelfeaturebasedmethodformultimodalbiomedicalimageregistrationcomparedtointensitybasedtechnique
AT jeerapatdoungchawee novelfeaturebasedmethodformultimodalbiomedicalimageregistrationcomparedtointensitybasedtechnique
AT richardwvachet novelfeaturebasedmethodformultimodalbiomedicalimageregistrationcomparedtointensitybasedtechnique