Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging

Yae Won Park, Jongmin Oh, Seng Chan You, Kyunghwa Han, Sung Soo Ahn, Yoon Seong Choi, Jong Hee Chang, Se Hoon Kim, Seung Koo Lee

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Objectives: Preoperative, noninvasive prediction of the meningioma grade is important because it influences the treatment strategy. The purpose of this study was to evaluate the role of radiomics features of postcontrast T1-weighted images (T1C), apparent diffusion coefficient (ADC), and fractional anisotropy (FA) maps, based on the entire tumor volume, in the differentiation of grades and histological subtypes of meningiomas. Methods: One hundred thirty-six patients with pathologically diagnosed meningiomas (108 low-grade [benign], 28 high-grade [atypical and anaplastic]), who underwent T1C and diffusion tensor imaging, were included in the discovery set. The T1C image, ADC, and FA maps were analyzed to derive volume-based data of the entire tumor. Radiomics features were correlated with meningioma grades and histological subtypes. Various machine learning classifiers were trained to build classification models to predict meningioma grades. We tested the model in a validation set (58 patients; 46 low-grade; 12 high-grade). Results: The machine learning classifiers showed variable performances depending on the machine learning algorithms. The best classification system for the prediction of meningioma grades had an area under the curve of 0.86 (95% confidence interval [CI], 0.74–0.98) in the validation set. The accuracy, sensitivity, and specificity of the best classifier were 89.7, 75.0, and 93.5% in the validation set, respectively. Various texture parameters differed significantly between fibroblastic and non-fibroblastic subtypes. Conclusions: Radiomics feature-based machine learning classifiers of T1C images, ADC, and FA maps are useful for differentiating meningioma grades. Key Points: • Preoperative, noninvasive differentiation of the meningioma grade is important because it influences the treatment strategy. • Radiomics feature-based machine learning classifiers of T1C images, ADC, and FA maps are useful for differentiating meningioma grades. • In benign meningiomas, there were significant differences in the various texture parameters between fibroblastic and non-fibroblastic meningioma subtypes.

Original languageEnglish
Pages (from-to)4068-4076
Number of pages9
JournalEuropean Radiology
Volume29
Issue number8
DOIs
Publication statusPublished - 2019 Aug 1

Fingerprint

Diffusion Tensor Imaging
Meningioma
Anisotropy
Machine Learning
Tumor Burden
Area Under Curve
Confidence Intervals

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging

Cite this

Park, Yae Won ; Oh, Jongmin ; You, Seng Chan ; Han, Kyunghwa ; Ahn, Sung Soo ; Choi, Yoon Seong ; Chang, Jong Hee ; Kim, Se Hoon ; Lee, Seung Koo. / Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging. In: European Radiology. 2019 ; Vol. 29, No. 8. pp. 4068-4076.
@article{4af862c99288490c8e8e32514248ba7e,
title = "Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging",
abstract = "Objectives: Preoperative, noninvasive prediction of the meningioma grade is important because it influences the treatment strategy. The purpose of this study was to evaluate the role of radiomics features of postcontrast T1-weighted images (T1C), apparent diffusion coefficient (ADC), and fractional anisotropy (FA) maps, based on the entire tumor volume, in the differentiation of grades and histological subtypes of meningiomas. Methods: One hundred thirty-six patients with pathologically diagnosed meningiomas (108 low-grade [benign], 28 high-grade [atypical and anaplastic]), who underwent T1C and diffusion tensor imaging, were included in the discovery set. The T1C image, ADC, and FA maps were analyzed to derive volume-based data of the entire tumor. Radiomics features were correlated with meningioma grades and histological subtypes. Various machine learning classifiers were trained to build classification models to predict meningioma grades. We tested the model in a validation set (58 patients; 46 low-grade; 12 high-grade). Results: The machine learning classifiers showed variable performances depending on the machine learning algorithms. The best classification system for the prediction of meningioma grades had an area under the curve of 0.86 (95{\%} confidence interval [CI], 0.74–0.98) in the validation set. The accuracy, sensitivity, and specificity of the best classifier were 89.7, 75.0, and 93.5{\%} in the validation set, respectively. Various texture parameters differed significantly between fibroblastic and non-fibroblastic subtypes. Conclusions: Radiomics feature-based machine learning classifiers of T1C images, ADC, and FA maps are useful for differentiating meningioma grades. Key Points: • Preoperative, noninvasive differentiation of the meningioma grade is important because it influences the treatment strategy. • Radiomics feature-based machine learning classifiers of T1C images, ADC, and FA maps are useful for differentiating meningioma grades. • In benign meningiomas, there were significant differences in the various texture parameters between fibroblastic and non-fibroblastic meningioma subtypes.",
author = "Park, {Yae Won} and Jongmin Oh and You, {Seng Chan} and Kyunghwa Han and Ahn, {Sung Soo} and Choi, {Yoon Seong} and Chang, {Jong Hee} and Kim, {Se Hoon} and Lee, {Seung Koo}",
year = "2019",
month = "8",
day = "1",
doi = "10.1007/s00330-018-5830-3",
language = "English",
volume = "29",
pages = "4068--4076",
journal = "European Radiology",
issn = "0938-7994",
publisher = "Springer Verlag",
number = "8",

}

Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging. / Park, Yae Won; Oh, Jongmin; You, Seng Chan; Han, Kyunghwa; Ahn, Sung Soo; Choi, Yoon Seong; Chang, Jong Hee; Kim, Se Hoon; Lee, Seung Koo.

In: European Radiology, Vol. 29, No. 8, 01.08.2019, p. 4068-4076.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging

AU - Park, Yae Won

AU - Oh, Jongmin

AU - You, Seng Chan

AU - Han, Kyunghwa

AU - Ahn, Sung Soo

AU - Choi, Yoon Seong

AU - Chang, Jong Hee

AU - Kim, Se Hoon

AU - Lee, Seung Koo

PY - 2019/8/1

Y1 - 2019/8/1

N2 - Objectives: Preoperative, noninvasive prediction of the meningioma grade is important because it influences the treatment strategy. The purpose of this study was to evaluate the role of radiomics features of postcontrast T1-weighted images (T1C), apparent diffusion coefficient (ADC), and fractional anisotropy (FA) maps, based on the entire tumor volume, in the differentiation of grades and histological subtypes of meningiomas. Methods: One hundred thirty-six patients with pathologically diagnosed meningiomas (108 low-grade [benign], 28 high-grade [atypical and anaplastic]), who underwent T1C and diffusion tensor imaging, were included in the discovery set. The T1C image, ADC, and FA maps were analyzed to derive volume-based data of the entire tumor. Radiomics features were correlated with meningioma grades and histological subtypes. Various machine learning classifiers were trained to build classification models to predict meningioma grades. We tested the model in a validation set (58 patients; 46 low-grade; 12 high-grade). Results: The machine learning classifiers showed variable performances depending on the machine learning algorithms. The best classification system for the prediction of meningioma grades had an area under the curve of 0.86 (95% confidence interval [CI], 0.74–0.98) in the validation set. The accuracy, sensitivity, and specificity of the best classifier were 89.7, 75.0, and 93.5% in the validation set, respectively. Various texture parameters differed significantly between fibroblastic and non-fibroblastic subtypes. Conclusions: Radiomics feature-based machine learning classifiers of T1C images, ADC, and FA maps are useful for differentiating meningioma grades. Key Points: • Preoperative, noninvasive differentiation of the meningioma grade is important because it influences the treatment strategy. • Radiomics feature-based machine learning classifiers of T1C images, ADC, and FA maps are useful for differentiating meningioma grades. • In benign meningiomas, there were significant differences in the various texture parameters between fibroblastic and non-fibroblastic meningioma subtypes.

AB - Objectives: Preoperative, noninvasive prediction of the meningioma grade is important because it influences the treatment strategy. The purpose of this study was to evaluate the role of radiomics features of postcontrast T1-weighted images (T1C), apparent diffusion coefficient (ADC), and fractional anisotropy (FA) maps, based on the entire tumor volume, in the differentiation of grades and histological subtypes of meningiomas. Methods: One hundred thirty-six patients with pathologically diagnosed meningiomas (108 low-grade [benign], 28 high-grade [atypical and anaplastic]), who underwent T1C and diffusion tensor imaging, were included in the discovery set. The T1C image, ADC, and FA maps were analyzed to derive volume-based data of the entire tumor. Radiomics features were correlated with meningioma grades and histological subtypes. Various machine learning classifiers were trained to build classification models to predict meningioma grades. We tested the model in a validation set (58 patients; 46 low-grade; 12 high-grade). Results: The machine learning classifiers showed variable performances depending on the machine learning algorithms. The best classification system for the prediction of meningioma grades had an area under the curve of 0.86 (95% confidence interval [CI], 0.74–0.98) in the validation set. The accuracy, sensitivity, and specificity of the best classifier were 89.7, 75.0, and 93.5% in the validation set, respectively. Various texture parameters differed significantly between fibroblastic and non-fibroblastic subtypes. Conclusions: Radiomics feature-based machine learning classifiers of T1C images, ADC, and FA maps are useful for differentiating meningioma grades. Key Points: • Preoperative, noninvasive differentiation of the meningioma grade is important because it influences the treatment strategy. • Radiomics feature-based machine learning classifiers of T1C images, ADC, and FA maps are useful for differentiating meningioma grades. • In benign meningiomas, there were significant differences in the various texture parameters between fibroblastic and non-fibroblastic meningioma subtypes.

UR - http://www.scopus.com/inward/record.url?scp=85056698975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056698975&partnerID=8YFLogxK

U2 - 10.1007/s00330-018-5830-3

DO - 10.1007/s00330-018-5830-3

M3 - Article

C2 - 30443758

AN - SCOPUS:85056698975

VL - 29

SP - 4068

EP - 4076

JO - European Radiology

JF - European Radiology

SN - 0938-7994

IS - 8

ER -