Semi-automated detection of cervical spinal cord compression
with the Spinal Cord Toolbox

J 2022

Semi-automated detection of cervical spinal cord compression with the Spinal Cord Toolbox

HORÁKOVÁ, Magda, Tomáš HORÁK, Jan VALOSEK, Tomáš ROHAN, Eva KORIŤÁKOVÁ et. al.

Basic information

Original name

Semi-automated detection of cervical spinal cord compression with the Spinal Cord Toolbox

Authors

HORÁKOVÁ, Magda (203 Czech Republic, belonging to the institution), Tomáš HORÁK (203 Czech Republic, belonging to the institution), Jan VALOSEK (203 Czech Republic), Tomáš ROHAN (203 Czech Republic, belonging to the institution), Eva KORIŤÁKOVÁ (203 Czech Republic, belonging to the institution), Marek DOSTÁL (203 Czech Republic, belonging to the institution), Jan KOČICA (203 Czech Republic, belonging to the institution), Tomáš SKUTIL (203 Czech Republic, belonging to the institution), Miloš KEŘKOVSKÝ (203 Czech Republic, belonging to the institution), Zdeněk KADAŇKA (203 Czech Republic, belonging to the institution), Petr BEDNAŘÍK (203 Czech Republic, belonging to the institution), Alena SVÁTKOVÁ (703 Slovakia, belonging to the institution), Petr HLUSTIK (203 Czech Republic) and Josef BEDNAŘÍK (203 Czech Republic, guarantor, belonging to the institution)

Edition

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, SHATIN, AME PUBL CO, 2022, 2223-4292

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

30224 Radiology, nuclear medicine and medical imaging

Country of publisher

China

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 2.800

RIV identification code

RIV/00216224:14110/22:00125373

Organization unit

Faculty of Medicine

DOI

http://dx.doi.org/10.21037/qims-21-782

UT WoS

000747192600001

Keywords in English

Spinal cord compression (SCC); cervical spinal cord; myelopathy; magnetic resonance imaging (MRI); reproducibility

Abstract

V originále

Background: Degenerative cervical spinal cord compression is becoming increasingly prevalent, yet the MRI criteria that define compression are vague, and vary between studies. This contribution addresses the detection of compression by means of the Spinal Cord Toolbox and assesses the variability of the morphometric parameters extracted with it. Methods: Prospective cross-sectional study. Two types of MRI examination, 3 and 1.5 T, were performed on 66 healthy controls and 118 participants with cervical spinal cord compression. Morphometric parameters from 3T MRI obtained by Spinal Cord Toolbox (cross-sectional area, solidity, compressive ratio, torsion) were combined in multivariate logistic regression models with the outcome (binary dependent variable) being the presence of compression determined by two radiologists. Inter-trial (between 3 and 1.5 T) and inter-rater (three expert raters and SCT) variability of morphometric parameters were assessed in a subset of 35 controls and 30 participants with compression. Results: The logistic model combining compressive ratio, cross-sectional area, solidity, torsion and one binary indicator, whether or not the compression was set at level C6/7, demonstrated outstanding compression detection (area under curve =0.947). The single best cut-off for predicted probability calculated using a multiple regression equation was 0.451, with a sensitivity of 87.3% and a specificity of 90.2%. The inter-trial variability was better in Spinal Cord Toolbox (intraclass correlation coefficient was 0.858 for compressive ratio and 0.735 for cross-sectional area) compared to expert raters (mean coefficient for three expert raters was 0.722 for compressive ratio and 0.486 for cross-sectional area). The analysis of interrater variability demonstrated general agreement between SCT and three expert raters, as the correlations between SCT and raters were generally similar to those of the raters between one another. Conclusions: This study demonstrates successful semi-automated compression detection based on four parameters. The inter-trial variability of parameters established through two MRI examinations was conclusively better for Spinal Cord Toolbox compared with that of three experts' manual ratings.

Links

MUNI/A/1144/2021, interní kód MU

Name: Diagnostika a patofyziologie neuropatické bolesti a dalších symptomů a komorbidit neurologických onemocnění

Investor: Masaryk University

MUNI/A/1600/2020, interní kód MU

Name: Diagnostika a patofyziologie neuropatické bolesti (Acronym: PNB)

Investor: Masaryk University

NV18-04-00159, research and development project

Name: Využití pokročilých magneticko-rezonančních technik k odhalení patofyziologie a zlepšení diagnostiky a praktického managementu degenerativní komprese krční míchy

Investor: Ministry of Health of the CR

90042, large research infrastructures

Name: CESNET II

90129, large research infrastructures

Name: Czech-BioImaging II

Citovat

HORÁKOVÁ, Magda, Tomáš HORÁK, Jan VALOSEK, Tomáš ROHAN, Eva KORIŤÁKOVÁ, Marek DOSTÁL, Jan KOČICA, Tomáš SKUTIL, Miloš KEŘKOVSKÝ, Zdeněk KADAŇKA, Petr BEDNAŘÍK, Alena SVÁTKOVÁ, Petr HLUSTIK and Josef BEDNAŘÍK. Semi-automated detection of cervical spinal cord compression with the Spinal Cord Toolbox. QUANTITATIVE IMAGING IN MEDICINE AND SURGERY. SHATIN: AME PUBL CO, 2022, vol. 12, No 4, p. 2261-2279. ISSN 2223-4292. Available from: https://dx.doi.org/10.21037/qims-21-782.

@article{1834413,
   author = {Horáková, Magda and Horák, Tomáš and Valosek, Jan and Rohan, Tomáš and Koriťáková, Eva and Dostál, Marek and Kočica, Jan and Skutil, Tomáš and Keřkovský, Miloš and Kadaňka, Zdeněk and Bednařík, Petr and Svátková, Alena and Hlustik, Petr and Bednařík, Josef},
   article_location = {SHATIN},
   article_number = {4},
   doi = {http://dx.doi.org/10.21037/qims-21-782},
   keywords = {Spinal cord compression (SCC); cervical spinal cord; myelopathy; magnetic resonance imaging (MRI); reproducibility},
   language = {eng},
   issn = {2223-4292},
   journal = {QUANTITATIVE IMAGING IN MEDICINE AND SURGERY},
   title = {Semi-automated detection of cervical spinal cord compression with the Spinal Cord Toolbox},
   url = {https://qims.amegroups.com/article/view/88416/html},
   volume = {12},
   year = {2022}
}

TY  - JOUR
ID  - 1834413
AU  - Horáková, Magda - Horák, Tomáš - Valosek, Jan - Rohan, Tomáš - Koriťáková, Eva - Dostál, Marek - Kočica, Jan - Skutil, Tomáš - Keřkovský, Miloš - Kadaňka, Zdeněk - Bednařík, Petr - Svátková, Alena - Hlustik, Petr - Bednařík, Josef
PY  - 2022
TI  - Semi-automated detection of cervical spinal cord compression with the Spinal Cord Toolbox
JF  - QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
VL  - 12
IS  - 4
SP  - 2261-2279
EP  - 2261-2279
PB  - AME PUBL CO
SN  - 22234292
KW  - Spinal cord compression (SCC)
KW  - cervical spinal cord
KW  - myelopathy
KW  - magnetic resonance imaging (MRI)
KW  - reproducibility
UR  - https://qims.amegroups.com/article/view/88416/html
N2  - Background: Degenerative cervical spinal cord compression is becoming increasingly prevalent, yet the MRI criteria that define compression are vague, and vary between studies. This contribution addresses the detection of compression by means of the Spinal Cord Toolbox and assesses the variability of the morphometric parameters extracted with it. Methods: Prospective cross-sectional study. Two types of MRI examination, 3 and 1.5 T, were performed on 66 healthy controls and 118 participants with cervical spinal cord compression. Morphometric parameters from 3T MRI obtained by Spinal Cord Toolbox (cross-sectional area, solidity, compressive ratio, torsion) were combined in multivariate logistic regression models with the outcome (binary dependent variable) being the presence of compression determined by two radiologists. Inter-trial (between 3 and 1.5 T) and inter-rater (three expert raters and SCT) variability of morphometric parameters were assessed in a subset of 35 controls and 30 participants with compression. Results: The logistic model combining compressive ratio, cross-sectional area, solidity, torsion and one binary indicator, whether or not the compression was set at level C6/7, demonstrated outstanding compression detection (area under curve =0.947). The single best cut-off for predicted probability calculated using a multiple regression equation was 0.451, with a sensitivity of 87.3% and a specificity of 90.2%. The inter-trial variability was better in Spinal Cord Toolbox (intraclass correlation coefficient was 0.858 for compressive ratio and 0.735 for cross-sectional area) compared to expert raters (mean coefficient for three expert raters was 0.722 for compressive ratio and 0.486 for cross-sectional area). The analysis of interrater variability demonstrated general agreement between SCT and three expert raters, as the correlations between SCT and raters were generally similar to those of the raters between one another. Conclusions: This study demonstrates successful semi-automated compression detection based on four parameters. The inter-trial variability of parameters established through two MRI examinations was conclusively better for Spinal Cord Toolbox compared with that of three experts' manual ratings.
ER  -

HORÁKOVÁ, Magda, Tomáš HORÁK, Jan VALOSEK, Tomáš ROHAN, Eva KORIŤÁKOVÁ, Marek DOSTÁL, Jan KOČICA, Tomáš SKUTIL, Miloš KEŘKOVSKÝ, Zdeněk KADAŇKA, Petr BEDNAŘÍK, Alena SVÁTKOVÁ, Petr HLUSTIK and Josef BEDNAŘÍK. Semi-automated detection of cervical spinal cord compression with the Spinal Cord Toolbox. \textit{QUANTITATIVE IMAGING IN MEDICINE AND SURGERY}. SHATIN: AME PUBL CO, 2022, vol.~12, No~4, p.~2261-2279. ISSN~2223-4292. Available from: https://dx.doi.org/10.21037/qims-21-782.

Detailed Information on Publication Record