Radiomics for pseudoprogression prediction in high grade gliomas: added value of MR contrast agent

Orkhan Mammadov; Burak Han Akkurt; Manfred Musigmann; Asena Petek Ari; David A Blömer; Dilek N G Kasap; Dylan J H A Henssen; Nabila Gala Nacul; Elisabeth Sartoretti; Thomas Sartoretti; Philipp Backhaus; Christian Thomas; Walter Stummer; Walter Heindel; Manoj Mannil

doi:10.1016/j.heliyon.2022.e10023

Radiomics for pseudoprogression prediction in high grade gliomas: added value of MR contrast agent

Orkhan Mammadov, Burak Han Akkurt, Manfred Musigmann, Asena Petek Ari, David A Blömer, Dilek N G Kasap, Dylan J H A Henssen, Nabila Gala Nacul, Elisabeth Sartoretti, Thomas Sartoretti, Philipp Backhaus, Christian Thomas, Walter Stummer, Walter Heindel, Manoj Mannil^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Objective: Our aim is to define the capabilities of radiomics in predicting pseudoprogression from pre-treatment MR images in patients diagnosed with high-grade gliomas using T1 non-contrast-enhanced and contrast-enhanced images.

Material & methods: In this retrospective IRB-approved study, image segmentation of high-grade gliomas was semi-automatically performed using 3D Slicer. Non-contrast-enhanced T1-weighted images and contrast-enhanced T1-weighted images were used prior to surgical therapy or radio-chemotherapy. Imaging data was split into a training sample and an independent test sample at random. We extracted 107 radiomic features by use of PyRadiomics. Feature selection and model construction were performed using Generalized Boosted Regression Models (GBM).

Results: Our cohort included 124 patients (female: n = 53), diagnosed with progressive (n = 61) and pseudoprogressive disease (n = 63) of primary high-grade gliomas. Based on non-contrast-enhanced T1-weighted images of the independent test sample, the mean area under the curve (AUC), mean sensitivity, mean specificity and mean accuracy of our model were 0.651 [0.576, 0.761], 0.616 [0.417, 0.833], 0.578 [0.417, 0.750] and 0.597 [0.500, 0.708] to predict the development of pseudoprogression. In comparison, the independent test data of contrast-enhanced T1-weighted images yielded significantly higher values of AUC = 0.819 [0.760, 0.872], sensitivity = 0.817 [0.750, 0.833], specificity = 0.723 [0.583, 0.833] and accuracy = 0.770 [0.687, 0.833].

Conclusion: Our findings show that it is possible to predict pseudoprogression of high-grade gliomas with a Radiomics model using contrast-enhanced T1-weighted images with comparatively good discriminatory power. The use of a contrast agent results in a clear added value.

Original language	English
Article number	e10023
Number of pages	9
Journal	Heliyon
Volume	8
Issue number	8
DOIs	https://doi.org/10.1016/j.heliyon.2022.e10023
Publication status	Published - Aug 2022

Keywords

Artificial intelligence
Glioma
Patient outcome assessment
PHASE-II
RESPONSE ASSESSMENT
GLIOBLASTOMA
CRITERIA
BRAIN

Access to Document

10.1016/j.heliyon.2022.e10023Licence: CC BY-NC-ND

Cite this

Mammadov, O., Akkurt, B. H., Musigmann, M., Ari, A. P., Blömer, D. A., Kasap, D. N. G., Henssen, D. J. H. A., Nacul, N. G., Sartoretti, E., Sartoretti, T., Backhaus, P., Thomas, C., Stummer, W., Heindel, W., & Mannil, M. (2022). Radiomics for pseudoprogression prediction in high grade gliomas: added value of MR contrast agent. Heliyon, 8(8), Article e10023. https://doi.org/10.1016/j.heliyon.2022.e10023

@article{d50d7e2d95634e069c6b352b04f0acbc,

title = "Radiomics for pseudoprogression prediction in high grade gliomas: added value of MR contrast agent",

abstract = "Objective: Our aim is to define the capabilities of radiomics in predicting pseudoprogression from pre-treatment MR images in patients diagnosed with high-grade gliomas using T1 non-contrast-enhanced and contrast-enhanced images.Material & methods: In this retrospective IRB-approved study, image segmentation of high-grade gliomas was semi-automatically performed using 3D Slicer. Non-contrast-enhanced T1-weighted images and contrast-enhanced T1-weighted images were used prior to surgical therapy or radio-chemotherapy. Imaging data was split into a training sample and an independent test sample at random. We extracted 107 radiomic features by use of PyRadiomics. Feature selection and model construction were performed using Generalized Boosted Regression Models (GBM).Results: Our cohort included 124 patients (female: n = 53), diagnosed with progressive (n = 61) and pseudoprogressive disease (n = 63) of primary high-grade gliomas. Based on non-contrast-enhanced T1-weighted images of the independent test sample, the mean area under the curve (AUC), mean sensitivity, mean specificity and mean accuracy of our model were 0.651 [0.576, 0.761], 0.616 [0.417, 0.833], 0.578 [0.417, 0.750] and 0.597 [0.500, 0.708] to predict the development of pseudoprogression. In comparison, the independent test data of contrast-enhanced T1-weighted images yielded significantly higher values of AUC = 0.819 [0.760, 0.872], sensitivity = 0.817 [0.750, 0.833], specificity = 0.723 [0.583, 0.833] and accuracy = 0.770 [0.687, 0.833].Conclusion: Our findings show that it is possible to predict pseudoprogression of high-grade gliomas with a Radiomics model using contrast-enhanced T1-weighted images with comparatively good discriminatory power. The use of a contrast agent results in a clear added value.",

keywords = "Artificial intelligence, Glioma, Patient outcome assessment, PHASE-II, RESPONSE ASSESSMENT, GLIOBLASTOMA, CRITERIA, BRAIN",

author = "Orkhan Mammadov and Akkurt, {Burak Han} and Manfred Musigmann and Ari, {Asena Petek} and Bl{\"o}mer, {David A} and Kasap, {Dilek N G} and Henssen, {Dylan J H A} and Nacul, {Nabila Gala} and Elisabeth Sartoretti and Thomas Sartoretti and Philipp Backhaus and Christian Thomas and Walter Stummer and Walter Heindel and Manoj Mannil",

note = "{\textcopyright} 2022 The Author(s).",

year = "2022",

month = aug,

doi = "10.1016/j.heliyon.2022.e10023",

language = "English",

volume = "8",

journal = "Heliyon",

issn = "2405-8440",

publisher = "Elsevier BV",

number = "8",

}

Mammadov, O, Akkurt, BH, Musigmann, M, Ari, AP, Blömer, DA, Kasap, DNG, Henssen, DJHA, Nacul, NG, Sartoretti, E, Sartoretti, T, Backhaus, P, Thomas, C, Stummer, W, Heindel, W & Mannil, M 2022, 'Radiomics for pseudoprogression prediction in high grade gliomas: added value of MR contrast agent', Heliyon, vol. 8, no. 8, e10023. https://doi.org/10.1016/j.heliyon.2022.e10023

TY - JOUR

T1 - Radiomics for pseudoprogression prediction in high grade gliomas

T2 - added value of MR contrast agent

AU - Mammadov, Orkhan

AU - Akkurt, Burak Han

AU - Musigmann, Manfred

AU - Ari, Asena Petek

AU - Blömer, David A

AU - Kasap, Dilek N G

AU - Henssen, Dylan J H A

AU - Nacul, Nabila Gala

AU - Sartoretti, Elisabeth

AU - Sartoretti, Thomas

AU - Backhaus, Philipp

AU - Thomas, Christian

AU - Stummer, Walter

AU - Heindel, Walter

AU - Mannil, Manoj

PY - 2022/8

Y1 - 2022/8

N2 - Objective: Our aim is to define the capabilities of radiomics in predicting pseudoprogression from pre-treatment MR images in patients diagnosed with high-grade gliomas using T1 non-contrast-enhanced and contrast-enhanced images.Material & methods: In this retrospective IRB-approved study, image segmentation of high-grade gliomas was semi-automatically performed using 3D Slicer. Non-contrast-enhanced T1-weighted images and contrast-enhanced T1-weighted images were used prior to surgical therapy or radio-chemotherapy. Imaging data was split into a training sample and an independent test sample at random. We extracted 107 radiomic features by use of PyRadiomics. Feature selection and model construction were performed using Generalized Boosted Regression Models (GBM).Results: Our cohort included 124 patients (female: n = 53), diagnosed with progressive (n = 61) and pseudoprogressive disease (n = 63) of primary high-grade gliomas. Based on non-contrast-enhanced T1-weighted images of the independent test sample, the mean area under the curve (AUC), mean sensitivity, mean specificity and mean accuracy of our model were 0.651 [0.576, 0.761], 0.616 [0.417, 0.833], 0.578 [0.417, 0.750] and 0.597 [0.500, 0.708] to predict the development of pseudoprogression. In comparison, the independent test data of contrast-enhanced T1-weighted images yielded significantly higher values of AUC = 0.819 [0.760, 0.872], sensitivity = 0.817 [0.750, 0.833], specificity = 0.723 [0.583, 0.833] and accuracy = 0.770 [0.687, 0.833].Conclusion: Our findings show that it is possible to predict pseudoprogression of high-grade gliomas with a Radiomics model using contrast-enhanced T1-weighted images with comparatively good discriminatory power. The use of a contrast agent results in a clear added value.

AB - Objective: Our aim is to define the capabilities of radiomics in predicting pseudoprogression from pre-treatment MR images in patients diagnosed with high-grade gliomas using T1 non-contrast-enhanced and contrast-enhanced images.Material & methods: In this retrospective IRB-approved study, image segmentation of high-grade gliomas was semi-automatically performed using 3D Slicer. Non-contrast-enhanced T1-weighted images and contrast-enhanced T1-weighted images were used prior to surgical therapy or radio-chemotherapy. Imaging data was split into a training sample and an independent test sample at random. We extracted 107 radiomic features by use of PyRadiomics. Feature selection and model construction were performed using Generalized Boosted Regression Models (GBM).Results: Our cohort included 124 patients (female: n = 53), diagnosed with progressive (n = 61) and pseudoprogressive disease (n = 63) of primary high-grade gliomas. Based on non-contrast-enhanced T1-weighted images of the independent test sample, the mean area under the curve (AUC), mean sensitivity, mean specificity and mean accuracy of our model were 0.651 [0.576, 0.761], 0.616 [0.417, 0.833], 0.578 [0.417, 0.750] and 0.597 [0.500, 0.708] to predict the development of pseudoprogression. In comparison, the independent test data of contrast-enhanced T1-weighted images yielded significantly higher values of AUC = 0.819 [0.760, 0.872], sensitivity = 0.817 [0.750, 0.833], specificity = 0.723 [0.583, 0.833] and accuracy = 0.770 [0.687, 0.833].Conclusion: Our findings show that it is possible to predict pseudoprogression of high-grade gliomas with a Radiomics model using contrast-enhanced T1-weighted images with comparatively good discriminatory power. The use of a contrast agent results in a clear added value.

KW - Artificial intelligence

KW - Glioma

KW - Patient outcome assessment

KW - PHASE-II

KW - RESPONSE ASSESSMENT

KW - GLIOBLASTOMA

KW - CRITERIA

KW - BRAIN

U2 - 10.1016/j.heliyon.2022.e10023

DO - 10.1016/j.heliyon.2022.e10023

M3 - Article

C2 - 35965975

SN - 2405-8440

VL - 8

JO - Heliyon

JF - Heliyon

IS - 8

M1 - e10023

ER -