Comparative Study of Relevant Methods
for MRI/X Brain Image Registration
Marwa Abderrahim
1(B) , Abir Baˆ azaoui
1 , and Walid Barhoumi
1,2
1 Institut Sup´ erieur d’Informatique d’El Manar, LR16ES06 Laboratoire de recherche
en Informatique, Mod´ elisation et Traitement de l’Information et de la Connaissance
(LIMTIC), Universit´ e de Tunis El Manar, 2080 Ariana, Tunisia
Abderrahimmarwa1@outlook.fr, a.baazaoui@hotmail.fr
2 Ecole Nationale d’Ing´ enieurs de Carthage, Universit´ e de Carthage,
Tunis-Carthage, Tunisia
walid.barhoumi@enicarthage.rnu.tn
Abstract. Several methods of brain image registration have been proposed in order to overcome the requirement of clinicians. In this paper,
we assess the performance of a hybrid method for brain image registration against the most used standard registration tools. Most traditional
registration tools use different methods for mono- and multi-modal registration, whereas the hybrid registration method is providing both mono
and multi-modal brain registration of PET, MRI and CT images. To
determine the appropriate registration method, we used two challenging
brain image datasets as well as two evaluation metrics. Results show that
the hybrid method outperforms all other standard registration tools and
has achieved promising accuracy for MRI/X brain image registration.
Keywords: MRI/X brain image registration · Hybrid method ·
Standard registration tools · Brain diagnosis
1 Introduction
Hundreds of millions of people worldwide suffer from neurological disorders, and
early detection coupled with appropriate treatment can generally cure these diseases. In this context, Computer Aided Diagnosis (CAD) explains the need to
design automatic and semi-automatic tools to effectively process brain medical
imaging. This could help clinicians to detect affected organs in order to specify
appropriate treatments. However, there are still many challenges (e.g. noise, resolution, partial volume effect . . .) that need to be investigated. There are several
brain medical imaging modalities, and each of them has a different aspect of
anatomy and/or functionality. Anatomical medical imaging (e.g. Magnetic Resonance Imaging (MRI), Computed Tomography (CT) . . .) provides information
on the structure, the shape, the edge, and the contents of organs. Functional
medical imaging (e.g. Positron Emission Tomography (PET) . . .) focuses on
the function of organs, tissues or cells. In clinical routines, experts generally
c
The Author(s) 2020
M. Jmaiel et al. (Eds.): ICOST 2020, LNCS 12157, pp. 338–347, 2020.
https://doi.org/10.1007/978-3-030-51517-1_30
for MRI/X Brain Image Registration
Marwa Abderrahim
1(B) , Abir Baˆ azaoui
1 , and Walid Barhoumi
1,2
1 Institut Sup´ erieur d’Informatique d’El Manar, LR16ES06 Laboratoire de recherche
en Informatique, Mod´ elisation et Traitement de l’Information et de la Connaissance
(LIMTIC), Universit´ e de Tunis El Manar, 2080 Ariana, Tunisia
Abderrahimmarwa1@outlook.fr, a.baazaoui@hotmail.fr
2 Ecole Nationale d’Ing´ enieurs de Carthage, Universit´ e de Carthage,
Tunis-Carthage, Tunisia
walid.barhoumi@enicarthage.rnu.tn
Abstract. Several methods of brain image registration have been proposed in order to overcome the requirement of clinicians. In this paper,
we assess the performance of a hybrid method for brain image registration against the most used standard registration tools. Most traditional
registration tools use different methods for mono- and multi-modal registration, whereas the hybrid registration method is providing both mono
and multi-modal brain registration of PET, MRI and CT images. To
determine the appropriate registration method, we used two challenging
brain image datasets as well as two evaluation metrics. Results show that
the hybrid method outperforms all other standard registration tools and
has achieved promising accuracy for MRI/X brain image registration.
Keywords: MRI/X brain image registration · Hybrid method ·
Standard registration tools · Brain diagnosis
1 Introduction
Hundreds of millions of people worldwide suffer from neurological disorders, and
early detection coupled with appropriate treatment can generally cure these diseases. In this context, Computer Aided Diagnosis (CAD) explains the need to
design automatic and semi-automatic tools to effectively process brain medical
imaging. This could help clinicians to detect affected organs in order to specify
appropriate treatments. However, there are still many challenges (e.g. noise, resolution, partial volume effect . . .) that need to be investigated. There are several
brain medical imaging modalities, and each of them has a different aspect of
anatomy and/or functionality. Anatomical medical imaging (e.g. Magnetic Resonance Imaging (MRI), Computed Tomography (CT) . . .) provides information
on the structure, the shape, the edge, and the contents of organs. Functional
medical imaging (e.g. Positron Emission Tomography (PET) . . .) focuses on
the function of organs, tissues or cells. In clinical routines, experts generally
c
The Author(s) 2020
M. Jmaiel et al. (Eds.): ICOST 2020, LNCS 12157, pp. 338–347, 2020.
https://doi.org/10.1007/978-3-030-51517-1_30