Automated fusion of multimodal imaging data for identifying
epileptogenic lesions in patients with inconclusive magnetic
resonance imaging

J 2021

Automated fusion of multimodal imaging data for identifying epileptogenic lesions in patients with inconclusive magnetic resonance imaging

MAREČEK, Radek, Pavel ŘÍHA, Michaela BARTOŇOVÁ, Martin KOJAN, Martin LAMOŠ et. al.

Basic information

Original name

Automated fusion of multimodal imaging data for identifying epileptogenic lesions in patients with inconclusive magnetic resonance imaging

Authors

MAREČEK, Radek (203 Czech Republic, belonging to the institution), Pavel ŘÍHA (203 Czech Republic, belonging to the institution), Michaela BARTOŇOVÁ (703 Slovakia, belonging to the institution), Martin KOJAN (703 Slovakia, belonging to the institution), Martin LAMOŠ (203 Czech Republic, belonging to the institution), Martin GAJDOŠ (203 Czech Republic, belonging to the institution), Lubomír VOJTÍŠEK (203 Czech Republic, belonging to the institution), Michal MIKL (203 Czech Republic, belonging to the institution), Marek BARTOŇ (203 Czech Republic, belonging to the institution), Irena DOLEŽALOVÁ (203 Czech Republic, belonging to the institution), Martin PAIL (203 Czech Republic, belonging to the institution), Ondřej STRÝČEK (203 Czech Republic, belonging to the institution), Marta PAŽOURKOVÁ (203 Czech Republic), Milan BRÁZDIL (203 Czech Republic, belonging to the institution) and Ivan REKTOR (203 Czech Republic, guarantor, belonging to the institution)

Edition

Human Brain mapping, Hoboken, WILEY-BLACKWELL, 2021, 1065-9471

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

30103 Neurosciences

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 5.399

RIV identification code

RIV/00216224:14740/21:00120107

Organization unit

Central European Institute of Technology

DOI

http://dx.doi.org/10.1002/hbm.25413

UT WoS

000633522300001

Keywords in English

data fusion; neuroimaging; nonlesional epilepsy; seizure onset zone

Abstract

V originále

Many methods applied to data acquired by various imaging modalities have been evaluated for their benefit in localizing lesions in magnetic resonance (MR) negative epilepsy patients. No approach has proven to be a stand-alone method with sufficiently high sensitivity and specificity. The presented study addresses the potential benefit of the automated fusion of results of individual methods in presurgical evaluation. We collected electrophysiological, MR, and nuclear imaging data from 137 patients with pharmacoresistant MR-negative/inconclusive focal epilepsy. A subgroup of 32 patients underwent surgical treatment with known postsurgical outcomes and histopathology. We employed a Gaussian mixture model to reveal several classes of gray matter tissue. Classes specific to epileptogenic tissue were identified and validated using the surgery subgroup divided into two disjoint sets. We evaluated the classification accuracy of the proposed method at a voxel-wise level and assessed the effect of individual methods. The training of the classifier resulted in six classes of gray matter tissue. We found a subset of two classes specific to tissue located in resected areas. The average classification accuracy (i.e., the probability of correct classification) was significantly higher than the level of chance in the training group (0.73) and even better in the validation surgery subgroup (0.82). Nuclear imaging, diffusion-weighted imaging, and source localization of interictal epileptic discharges were the strongest methods for classification accuracy. We showed that the automatic fusion of results can identify brain areas that show epileptogenic gray matter tissue features. The method might enhance the presurgical evaluations of MR-negative epilepsy patients.

Links

LM2018129, research and development project

Name: Národní infrastruktura pro biologické a medicínské zobrazování Czech-BioImaging

Investor: Ministry of Education, Youth and Sports of the CR

NV17-32292A, research and development project

Name: Detekce léze u nelezionální epilepsie s využitím multimodálního zobrazování

Citovat

MAREČEK, Radek, Pavel ŘÍHA, Michaela BARTOŇOVÁ, Martin KOJAN, Martin LAMOŠ, Martin GAJDOŠ, Lubomír VOJTÍŠEK, Michal MIKL, Marek BARTOŇ, Irena DOLEŽALOVÁ, Martin PAIL, Ondřej STRÝČEK, Marta PAŽOURKOVÁ, Milan BRÁZDIL and Ivan REKTOR. Automated fusion of multimodal imaging data for identifying epileptogenic lesions in patients with inconclusive magnetic resonance imaging. Human Brain mapping. Hoboken: WILEY-BLACKWELL, 2021, vol. 42, No 9, p. 2921-2930. ISSN 1065-9471. Available from: https://dx.doi.org/10.1002/hbm.25413.

@article{1781359,
   author = {Mareček, Radek and Říha, Pavel and Bartoňová, Michaela and Kojan, Martin and Lamoš, Martin and Gajdoš, Martin and Vojtíšek, Lubomír and Mikl, Michal and Bartoň, Marek and Doležalová, Irena and Pail, Martin and Strýček, Ondřej and Pažourková, Marta and Brázdil, Milan and Rektor, Ivan},
   article_location = {Hoboken},
   article_number = {9},
   doi = {http://dx.doi.org/10.1002/hbm.25413},
   keywords = {data fusion; neuroimaging; nonlesional epilepsy; seizure onset zone},
   language = {eng},
   issn = {1065-9471},
   journal = {Human Brain mapping},
   title = {Automated fusion of multimodal imaging data for identifying epileptogenic lesions in patients with inconclusive magnetic resonance imaging},
   url = {https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/hbm.25413},
   volume = {42},
   year = {2021}
}

TY  - JOUR
ID  - 1781359
AU  - Mareček, Radek - Říha, Pavel - Bartoňová, Michaela - Kojan, Martin - Lamoš, Martin - Gajdoš, Martin - Vojtíšek, Lubomír - Mikl, Michal - Bartoň, Marek - Doležalová, Irena - Pail, Martin - Strýček, Ondřej - Pažourková, Marta - Brázdil, Milan - Rektor, Ivan
PY  - 2021
TI  - Automated fusion of multimodal imaging data for identifying epileptogenic lesions in patients with inconclusive magnetic resonance imaging
JF  - Human Brain mapping
VL  - 42
IS  - 9
SP  - 2921-2930
EP  - 2921-2930
PB  - WILEY-BLACKWELL
SN  - 10659471
KW  - data fusion
KW  - neuroimaging
KW  - nonlesional epilepsy
KW  - seizure onset zone
UR  - https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/hbm.25413
N2  - Many methods applied to data acquired by various imaging modalities have been evaluated for their benefit in localizing lesions in magnetic resonance (MR) negative epilepsy patients. No approach has proven to be a stand-alone method with sufficiently high sensitivity and specificity. The presented study addresses the potential benefit of the automated fusion of results of individual methods in presurgical evaluation. We collected electrophysiological, MR, and nuclear imaging data from 137 patients with pharmacoresistant MR-negative/inconclusive focal epilepsy. A subgroup of 32 patients underwent surgical treatment with known postsurgical outcomes and histopathology. We employed a Gaussian mixture model to reveal several classes of gray matter tissue. Classes specific to epileptogenic tissue were identified and validated using the surgery subgroup divided into two disjoint sets. We evaluated the classification accuracy of the proposed method at a voxel-wise level and assessed the effect of individual methods. The training of the classifier resulted in six classes of gray matter tissue. We found a subset of two classes specific to tissue located in resected areas. The average classification accuracy (i.e., the probability of correct classification) was significantly higher than the level of chance in the training group (0.73) and even better in the validation surgery subgroup (0.82). Nuclear imaging, diffusion-weighted imaging, and source localization of interictal epileptic discharges were the strongest methods for classification accuracy. We showed that the automatic fusion of results can identify brain areas that show epileptogenic gray matter tissue features. The method might enhance the presurgical evaluations of MR-negative epilepsy patients.
ER  -

MAREČEK, Radek, Pavel ŘÍHA, Michaela BARTOŇOVÁ, Martin KOJAN, Martin LAMOŠ, Martin GAJDOŠ, Lubomír VOJTÍŠEK, Michal MIKL, Marek BARTOŇ, Irena DOLEŽALOVÁ, Martin PAIL, Ondřej STRÝČEK, Marta PAŽOURKOVÁ, Milan BRÁZDIL and Ivan REKTOR. Automated fusion of multimodal imaging data for identifying epileptogenic lesions in patients with inconclusive magnetic resonance imaging. \textit{Human Brain mapping}. Hoboken: WILEY-BLACKWELL, 2021, vol.~42, No~9, p.~2921-2930. ISSN~1065-9471. Available from: https://dx.doi.org/10.1002/hbm.25413.

Detailed Information on Publication Record