Classification of brain lesions using a machine learning
approach with cross-sectional ADC value dynamics

J 2023

Classification of brain lesions using a machine learning approach with cross-sectional ADC value dynamics

SOLÁR, Peter, Hana VALEKOVÁ, Petr MARCON, Jan MIKULKA, Martin BARÁK et. al.

Basic information

Original name

Classification of brain lesions using a machine learning approach with cross-sectional ADC value dynamics

Authors

SOLÁR, Peter (703 Slovakia, belonging to the institution), Hana VALEKOVÁ (703 Slovakia, belonging to the institution), Petr MARCON (203 Czech Republic), Jan MIKULKA (203 Czech Republic), Martin BARÁK (203 Czech Republic, belonging to the institution), Michal HENDRYCH (203 Czech Republic, belonging to the institution), Matyas STRANSKY (203 Czech Republic), Katerina SIRUCKOVA (203 Czech Republic), Martin KOSTIAL (203 Czech Republic), Klára HOLÍKOVÁ (203 Czech Republic, belonging to the institution), Jindrich BRYCHTA (203 Czech Republic) and Radim JANČÁLEK (203 Czech Republic, guarantor, belonging to the institution)

Edition

Nature Scientific Reports, BERLIN, NATURE RESEARCH, 2023, 2045-2322

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

30210 Clinical neurology

Country of publisher

Germany

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 4.600 in 2022

RIV identification code

RIV/00216224:14110/23:00131736

Organization unit

Faculty of Medicine

DOI

http://dx.doi.org/10.1038/s41598-023-38542-7

UT WoS

001055239000016

Keywords in English

brain lesions; ADC; machine learning

Abstract

V originále

Diffusion-weighted imaging (DWI) and its numerical expression via apparent diffusion coefficient (ADC) values are commonly utilized in non-invasive assessment of various brain pathologies. Although numerous studies have confirmed that ADC values could be pathognomic for various ring-enhancing lesions (RELs), their true potential is yet to be exploited in full. The article was designed to introduce an image analysis method allowing REL recognition independently of either absolute ADC values or specifically defined regions of interest within the evaluated image. For this purpose, the line of interest (LOI) was marked on each ADC map to cross all of the RELs' compartments. Using a machine learning approach, we analyzed the LOI between two representatives of the RELs, namely, brain abscess and glioblastoma (GBM). The diagnostic ability of the selected parameters as predictors for the machine learning algorithms was assessed using two models, the k-NN model and the SVM model with a Gaussian kernel. With the k-NN machine learning method, 80% of the abscesses and 100% of the GBM were classified correctly at high accuracy. Similar results were obtained via the SVM method. The proposed assessment of the LOI offers a new approach for evaluating ADC maps obtained from different RELs and contributing to the standardization of the ADC map assessment.

Links

MUNI/A/1379/2022, interní kód MU

Name: Organotypické kultury glioblastomu – personalizované testování protinádorové léčby II

Investor: Masaryk University

Citovat

SOLÁR, Peter, Hana VALEKOVÁ, Petr MARCON, Jan MIKULKA, Martin BARÁK, Michal HENDRYCH, Matyas STRANSKY, Katerina SIRUCKOVA, Martin KOSTIAL, Klára HOLÍKOVÁ, Jindrich BRYCHTA and Radim JANČÁLEK. Classification of brain lesions using a machine learning approach with cross-sectional ADC value dynamics. Nature Scientific Reports. BERLIN: NATURE RESEARCH, 2023, vol. 13, No 1, p. 1-11. ISSN 2045-2322. Available from: https://dx.doi.org/10.1038/s41598-023-38542-7.

@article{2313837,
   author = {Solár, Peter and Valeková, Hana and Marcon, Petr and Mikulka, Jan and Barák, Martin and Hendrych, Michal and Stransky, Matyas and Siruckova, Katerina and Kostial, Martin and Holíková, Klára and Brychta, Jindrich and Jančálek, Radim},
   article_location = {BERLIN},
   article_number = {1},
   doi = {http://dx.doi.org/10.1038/s41598-023-38542-7},
   keywords = {brain lesions; ADC; machine learning},
   language = {eng},
   issn = {2045-2322},
   journal = {Nature Scientific Reports},
   title = {Classification of brain lesions using a machine learning approach with cross-sectional ADC value dynamics},
   url = {https://www.nature.com/articles/s41598-023-38542-7},
   volume = {13},
   year = {2023}
}

TY  - JOUR
ID  - 2313837
AU  - Solár, Peter - Valeková, Hana - Marcon, Petr - Mikulka, Jan - Barák, Martin - Hendrych, Michal - Stransky, Matyas - Siruckova, Katerina - Kostial, Martin - Holíková, Klára - Brychta, Jindrich - Jančálek, Radim
PY  - 2023
TI  - Classification of brain lesions using a machine learning approach with cross-sectional ADC value dynamics
JF  - Nature Scientific Reports
VL  - 13
IS  - 1
SP  - 1-11
EP  - 1-11
PB  - NATURE RESEARCH
SN  - 20452322
KW  - brain lesions
KW  - ADC
KW  - machine learning
UR  - https://www.nature.com/articles/s41598-023-38542-7
N2  - Diffusion-weighted imaging (DWI) and its numerical expression via apparent diffusion coefficient (ADC) values are commonly utilized in non-invasive assessment of various brain pathologies. Although numerous studies have confirmed that ADC values could be pathognomic for various ring-enhancing lesions (RELs), their true potential is yet to be exploited in full. The article was designed to introduce an image analysis method allowing REL recognition independently of either absolute ADC values or specifically defined regions of interest within the evaluated image. For this purpose, the line of interest (LOI) was marked on each ADC map to cross all of the RELs' compartments. Using a machine learning approach, we analyzed the LOI between two representatives of the RELs, namely, brain abscess and glioblastoma (GBM). The diagnostic ability of the selected parameters as predictors for the machine learning algorithms was assessed using two models, the k-NN model and the SVM model with a Gaussian kernel. With the k-NN machine learning method, 80% of the abscesses and 100% of the GBM were classified correctly at high accuracy. Similar results were obtained via the SVM method. The proposed assessment of the LOI offers a new approach for evaluating ADC maps obtained from different RELs and contributing to the standardization of the ADC map assessment.
ER  -

SOLÁR, Peter, Hana VALEKOVÁ, Petr MARCON, Jan MIKULKA, Martin BARÁK, Michal HENDRYCH, Matyas STRANSKY, Katerina SIRUCKOVA, Martin KOSTIAL, Klára HOLÍKOVÁ, Jindrich BRYCHTA and Radim JANČÁLEK. Classification of brain lesions using a machine learning approach with cross-sectional ADC value dynamics. \textit{Nature Scientific Reports}. BERLIN: NATURE RESEARCH, 2023, vol.~13, No~1, p.~1-11. ISSN~2045-2322. Available from: https://dx.doi.org/10.1038/s41598-023-38542-7.

Detailed Information on Publication Record