Joint Deformable Image Registration and ADC Map Regularization : Application to DWI-Based Lymphoma Classification
(2022) In IEEE Journal of Biomedical and Health Informatics 26(7). p.3151-3162- Abstract
The Apparent Diffusion Coefficient (ADC) is considered an importantimaging biomarker contributing to the assessment of tissue microstructure and pathophy- siology. It is calculated from Diffusion-Weighted Magnetic Resonance Imaging (DWI) by means of a diffusion model, usually without considering any motion during image acquisition. We propose a method to improve the computation of the ADC by coping jointly with both motion artifacts in whole-body DWI (through group-wise registration) and possible instrumental noise in the diffusion model. The proposed deformable registration method yielded on average the lowest ADC reconstruction error on data with simulated motion and diffusion. Moreover, our approach was applied on whole-body... (More)
The Apparent Diffusion Coefficient (ADC) is considered an importantimaging biomarker contributing to the assessment of tissue microstructure and pathophy- siology. It is calculated from Diffusion-Weighted Magnetic Resonance Imaging (DWI) by means of a diffusion model, usually without considering any motion during image acquisition. We propose a method to improve the computation of the ADC by coping jointly with both motion artifacts in whole-body DWI (through group-wise registration) and possible instrumental noise in the diffusion model. The proposed deformable registration method yielded on average the lowest ADC reconstruction error on data with simulated motion and diffusion. Moreover, our approach was applied on whole-body diffusion weighted images obtained with five different b-values from a cohort of 38 patients with histologically confirmed lymphomas of three different types (Hodgkin, diffuse large B-cell lymphoma and follicular lymphoma). Evaluation on the real data showed that ADC-based features, extracted using our joint optimization approach classified lymphomas with an accuracy of approximately 78.6% (yielding a 11% increase in respect to the standard features extracted from unregistered diffusion-weighted images). Furthermore, the correlation between diffusion characteristics and histopathological findings was higher than any other previous approach of ADC computation.
(Less)
- author
- Kornaropoulos, Evgenios N. LU ; Zacharaki, Evangelia I. ; Zerbib, Pierre ; Lin, Chieh ; Rahmouni, Alain and Paragios, Nikos
- organization
- publishing date
- 2022-07-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- ADC, b-values, classification, deformable, discrete, lymphoma, registration
- in
- IEEE Journal of Biomedical and Health Informatics
- volume
- 26
- issue
- 7
- pages
- 12 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- pmid:35239496
- scopus:85125737972
- ISSN
- 2168-2194
- DOI
- 10.1109/JBHI.2022.3156009
- language
- English
- LU publication?
- yes
- additional info
- Funding Information: This work was supported by the French National Research Agency (ANR) under Grant ADAMANTIUS, with ClinicalTrials.gov Identifier: NCT02300402. Publisher Copyright: © 2013 IEEE.
- id
- 61f90ff5-5bdb-46e9-be60-3f1940fc68a3
- date added to LUP
- 2022-12-29 14:20:30
- date last changed
- 2024-04-18 19:48:16
@article{61f90ff5-5bdb-46e9-be60-3f1940fc68a3,
abstract = {{<p>The Apparent Diffusion Coefficient (ADC) is considered an importantimaging biomarker contributing to the assessment of tissue microstructure and pathophy- siology. It is calculated from Diffusion-Weighted Magnetic Resonance Imaging (DWI) by means of a diffusion model, usually without considering any motion during image acquisition. We propose a method to improve the computation of the ADC by coping jointly with both motion artifacts in whole-body DWI (through group-wise registration) and possible instrumental noise in the diffusion model. The proposed deformable registration method yielded on average the lowest ADC reconstruction error on data with simulated motion and diffusion. Moreover, our approach was applied on whole-body diffusion weighted images obtained with five different b-values from a cohort of 38 patients with histologically confirmed lymphomas of three different types (Hodgkin, diffuse large B-cell lymphoma and follicular lymphoma). Evaluation on the real data showed that ADC-based features, extracted using our joint optimization approach classified lymphomas with an accuracy of approximately 78.6% (yielding a 11% increase in respect to the standard features extracted from unregistered diffusion-weighted images). Furthermore, the correlation between diffusion characteristics and histopathological findings was higher than any other previous approach of ADC computation.</p>}},
author = {{Kornaropoulos, Evgenios N. and Zacharaki, Evangelia I. and Zerbib, Pierre and Lin, Chieh and Rahmouni, Alain and Paragios, Nikos}},
issn = {{2168-2194}},
keywords = {{ADC; b-values; classification; deformable; discrete; lymphoma; registration}},
language = {{eng}},
month = {{07}},
number = {{7}},
pages = {{3151--3162}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Journal of Biomedical and Health Informatics}},
title = {{Joint Deformable Image Registration and ADC Map Regularization : Application to DWI-Based Lymphoma Classification}},
url = {{http://dx.doi.org/10.1109/JBHI.2022.3156009}},
doi = {{10.1109/JBHI.2022.3156009}},
volume = {{26}},
year = {{2022}},
}