Imaging biomarker analysis of advanced multiparametric MRI for glioma grading

Vamvakas, Alexandros; Williams, Steven; Theodorou, K.; Kapsalaki, Eftychia Z.; Fountas, Konstantinos; Kappas, Constantin; Vassiou, Katerina; Tsougos, Ioannis

doi:10.1016/j.ejmp.2019.03.014

Cited by 81 publications

(59 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Relative cerebral blood volume (rCBV) mirrors the vascular multiplication; in this way, the level of the neovascularization and can be obtained from dynamic susceptibility contrast magnetic resonance perfusion imaging (DSC-MRI) [7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

The combined role of MR spectroscopy and perfusion imaging in preoperative differentiation between high- and low-grade gliomas

Hasan

Megally

Khallaf

et al. 2019

Egypt J Radiol Nucl Med

View full text Add to dashboard Cite

Background: Brain tumors are an important health problem. The preoperative classification of gliomas by noninvasive techniques is a significant problem. Relative cerebral blood volume and spectroscopy have the ability to sample the entire lesion non-invasively. The present study aims to evaluate the combined role of dynamic susceptibility perfusion and spectroscopy in the classification of primary brain tumors. The combination of both provides overall diagnostic accuracy (100%). Relative cerebral blood volume in peritumoral region plays an important additional role in this regard. Results: On the basis of histopathology, among 50 patients with brain tumors, high-grade gliomas accounted for 58%, while low-grade gliomas accounted for 42%. The relative cerebral blood volume in the tumor had the best sensitivity, specificity, and accuracy of 96.8%, 95.3%, and 96, respectively. The use of relative cerebral blood volume and choline/N-acetyl Aspartate increased diagnostic accuracy by 100%. Conclusion: The combination of magnetic resonance spectroscopy and perfusion can increase sensitivity and positive predictive value to define the degree of glioma.

show abstract

Section: Introductionmentioning

confidence: 99%

The combined role of MR spectroscopy and perfusion imaging in preoperative differentiation between high- and low-grade gliomas

Hasan

Megally

Khallaf

et al. 2019

Egypt J Radiol Nucl Med

View full text Add to dashboard Cite

show abstract

“…LGGs and HGGs of 94.4% and 94% respectively when T1-weighted before and 453 after contrast-enhanced images were studied, and 96.5% and 97% when they studied 454 T2-weighted and FLAIR images. Therefore, in this work conventional MRI (T 1Gd and 455 T 2 contrasts) was studied, while others have analyzed advanced MRI or a combination 456 of both [5,[21][22][23][24][51][52][53][54]. The model was created from a simple mathematical method (a 457 multiple linear regression), in comparison to others in which mathematical tools of 458 higher complexity were utilized [7,[52][53][54]].…”

mentioning

confidence: 99%

“…Therefore, in this work conventional MRI (T 1Gd and 455 T 2 contrasts) was studied, while others have analyzed advanced MRI or a combination 456 of both [5,[21][22][23][24][51][52][53][54]. The model was created from a simple mathematical method (a 457 multiple linear regression), in comparison to others in which mathematical tools of 458 higher complexity were utilized [7,[52][53][54]]. The best model was found to use only 3 459 variables of a single type (quantitative, being also only texture features), instead of a 460 combination of different classes and types of variables [21,24,51,53].…”

mentioning

confidence: 99%

“…The model was created from a simple mathematical method (a 457 multiple linear regression), in comparison to others in which mathematical tools of 458 higher complexity were utilized [7,[52][53][54]]. The best model was found to use only 3 459 variables of a single type (quantitative, being also only texture features), instead of a 460 combination of different classes and types of variables [21,24,51,53]. A texture analysis 461 was performed (which is easy to implement for any type of MRI) and a single texture 462 matrix was used instead of different matrices [24], being the chosen one (GLSZM) a 463 suitable texture matrix when heterogeneity is a predominat characteristic of the object 464 of study.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A simple model for glioma grading based on texture analysis applied to conventional brain MRI

Suárez-García

Hernández-López

Moreno-Barbosa

et al. 2020

Preprint

View full text Add to dashboard Cite

11Accuracy of glioma grading is fundamental for the diagnosis, treatment planning and 12 prognosis of patients. The purpose of this work was to develop a low cost and easy to 13 implement classification model which distinguishes low grade gliomas (LGGs) from high 14 grade gliomas (HGGs), through texture analysis applied to conventional brain MRI. 15Different combinations between MRI contrasts (T 1Gd and T 2 ) and one segmented 16 glioma region (necrotic and non-enhancing tumor core (NCR/NET)) were studied. 17 Texture features obtained from the Gray Level Size Zone Matrix (GLSZM) were 18 calculated. An under-samplig method was proposed to divide the data into different 19 training subsets and subsequently extract complementary information for the creation 20 of distinct classification models. The sensitivity, specificity and accuracy of the models 21 were calculated. The best model was explicitly reported. The best model included only 22 three texture features and reached a sensitivity, specificity and accuracy of 94.12%, 23 88.24% and 91.18% respectively. According to the features of the model, when the 24 NCR/NET region was studied, HGGs had a more heterogeneous texture than LGGs in 25 the T 1Gd images and LGGs had a more heterogeneous texture than HGGs in the T 2 26 images. These novel results partially contrast with results from literature. The best 27 model proved to be useful for the classification of gliomas. Complementary results 28 showed that heterogeneity of gliomas depended on the studied MRI contrast. The 29 model presented stands out as a simple, low cost, easy to implement, reproducible and 30 highly accurate glioma classifier. What is more important, it should be accessible to 31 populations with reduced economic and scientific resources.32

show abstract

“…Combining quantitative image features extracted from conventional T1-weighted contrast-enhanced (T1 CE) and fluid attenuated inversion recovery (FLAIR) images with machine learning algorithms, radiomics can provide comprehensive information that is difficult to perceive with visual inspection [12,13] and is commonly used in tumor diagnosis, staging and prognosis of tumors [14][15][16][17][18][19][20]. However, most previous studies were mainly focused on advanced MR techniques, the varied post-processing models, varied interpretation and evaluation criteria restricted their clinical applications.…”

Section: Introductionmentioning

confidence: 99%

Better efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images

Zhao

Feng

et al. 2020

BMC Neurol

View full text Add to dashboard Cite

Background: The medical imaging to differentiate World Health Organization (WHO) grade II (ODG2) from III (ODG3) oligodendrogliomas still remains a challenge. We investigated whether combination of machine leaning with radiomics from conventional T1 contrast-enhanced (T1 CE) and fluid attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) offered superior efficacy.Methods: Thirty-six patients with histologically confirmed ODGs underwent T1 CE and 33 of them underwent FLAIR MR examination before any intervention from January 2015 to July 2017 were retrospectively recruited in the current study. The volume of interest (VOI) covering the whole tumor enhancement were manually drawn on the T1 CE and FLAIR slice by slice using ITK-SNAP and a total of 1072 features were extracted from the VOI using 3-D slicer software. Random forest (RF) algorithm was applied to differentiate ODG2 from ODG3 and the efficacy was tested with 5-fold cross validation. The diagnostic efficacy of radiomics-based machine learning and radiologist's assessment were also compared. Results: Nineteen ODG2 and 17 ODG3 were included in this study and ODG3 tended to present with prominent necrosis and nodular/ring-like enhancement (P < 0.05). The AUC, ACC, sensitivity, and specificity of radiomics were 0.798, 0.735, 0.672, 0.789 for T1 CE, 0.774, 0.689, 0.700, 0.683 for FLAIR, as well as 0.861, 0.781, 0.778, 0.783 for the combination, respectively. The AUCs of radiologists 1, 2 and 3 were 0.700, 0.687, and 0.714, respectively. The efficacy of machine learning based on radiomics was superior to the radiologists' assessment. Conclusions: Machine-learning based on radiomics of T1 CE and FLAIR offered superior efficacy to that of radiologists in differentiating ODG2 from ODG3.

show abstract

Imaging biomarker analysis of advanced multiparametric MRI for glioma grading

Cited by 81 publications

References 45 publications

The combined role of MR spectroscopy and perfusion imaging in preoperative differentiation between high- and low-grade gliomas

The combined role of MR spectroscopy and perfusion imaging in preoperative differentiation between high- and low-grade gliomas

A simple model for glioma grading based on texture analysis applied to conventional brain MRI

Better efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images

Contact Info

Product

Resources

About