scholarly journals Magnetic resonance radiomics features and prognosticators in different molecular subtypes of pediatric Medulloblastoma

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0255500
Author(s):  
Feng-Chi Chang ◽  
Tai-Tong Wong ◽  
Kuo-Sheng Wu ◽  
Chia-Feng Lu ◽  
Ting-Wei Weng ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Prediction Models ◽  
Gray Level ◽  
Resonance Imaging ◽  
Molecular Subgroups ◽  
Characteristic Analysis ◽  
Group 4 ◽  
Pediatric Medulloblastoma ◽  
Group 3

Purpose Medulloblastoma (MB) is a highly malignant pediatric brain tumor. In the latest classification, medulloblastoma is divided into four distinct groups: wingless (WNT), sonic hedgehog (SHH), Group 3, and Group 4. We analyzed the magnetic resonance imaging radiomics features to find the imaging surrogates of the 4 molecular subgroups of MB. Material and methods Frozen tissue, imaging data, and clinical data of 38 patients with medulloblastoma were included from Taipei Medical University Hospital and Taipei Veterans General Hospital. Molecular clustering was performed based on the gene expression level of 22 subgroup-specific signature genes. A total 253 magnetic resonance imaging radiomic features were generated from each subject for comparison between different molecular subgroups. Results Our cohort consisted of 7 (18.4%) patients with WNT medulloblastoma, 12 (31.6%) with SHH tumor, 8 (21.1%) with Group 3 tumor, and 11 (28.9%) with Group 4 tumor. 8 radiomics gray-level co-occurrence matrix texture (GLCM) features were significantly different between 4 molecular subgroups of MB. In addition, for tumors with higher values in a gray-level run length matrix feature—Short Run Low Gray-Level Emphasis, patients have shorter survival times than patients with low values of this feature (p = 0.04). The receiver operating characteristic analysis revealed optimal performance of the preliminary prediction model based on GLCM features for predicting WNT, Group 3, and Group 4 MB (area under the curve = 0.82, 0.72, and 0.78, respectively). Conclusion The preliminary result revealed that 8 contrast-enhanced T1-weighted imaging texture features were significantly different between 4 molecular subgroups of MB. Together with the prediction models, the radiomics features may provide suggestions for stratifying patients with MB into different risk groups.

scholarly journals Robustness of radiomic features in magnetic resonance imaging: review and a phantom study

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Renee Cattell ◽  
Shenglan Chen ◽  
Chuan Huang
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Prediction Models ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Phantom Study ◽  
Imaging Biomarkers ◽  
Gray Level ◽  
Resonance Imaging ◽  
Size Change

AbstractRadiomic analysis has exponentially increased the amount of quantitative data that can be extracted from a single image. These imaging biomarkers can aid in the generation of prediction models aimed to further personalized medicine. However, the generalizability of the model is dependent on the robustness of these features. The purpose of this study is to review the current literature regarding robustness of radiomic features on magnetic resonance imaging. Additionally, a phantom study is performed to systematically evaluate the behavior of radiomic features under various conditions (signal to noise ratio, region of interest delineation, voxel size change and normalization methods) using intraclass correlation coefficients. The features extracted in this phantom study include first order, shape, gray level cooccurrence matrix and gray level run length matrix. Many features are found to be non-robust to changing parameters. Feature robustness assessment prior to feature selection, especially in the case of combining multi-institutional data, may be warranted. Further investigation is needed in this area of research.

Regional Cerebral Plasma Volume Response to Carbon Dioxide Using Magnetic Resonance Imaging 

1998 ◽  
Vol 88 (4) ◽  
pp. 984-992 ◽  
Author(s):  
Jean-Francois Payen ◽  
Albert Vath ◽  
Blanche Koenigsberg ◽  
Virginie Bourlier ◽  
Michel Decorps
Keyword(s):  
Magnetic Resonance Imaging ◽  
Carbon Dioxide ◽  
Magnetic Resonance ◽  
Plasma Volume ◽  
Resonance Imaging ◽  
Contrast Enhanced ◽  
Group 3 ◽  
Group 2 ◽  
Agent Group ◽  
Group 1

Background Noninvasive techniques used to determine the changes in cerebral blood volume in response to carbon dioxide are hampered by their limited spatial or temporal resolution or both. Using steady state contrast-enhanced magnetic resonance imaging, the authors determined regional changes in cerebral plasma volume (CPV) induced by hypercapnia in halothane-anesthetized rats. Methods Cerebral plasma volume was determined during normocapnia, hypercapnia and recovery in the dorsoparietal neocortex and striatum of each hemisphere, in cerebellum, and in extracerebral tissue of rats with either intact carotid arteries (group 1) or unilateral common carotid ligation (group 2). Another group was studied without injection of a contrast agent (group 3). Results Hypercapnia (partial pressure of carbon dioxide in arterial blood [PaCO2] approximately 65 mmHg) resulted in a significant increase in CPV in the striatum (+42 +/- 8%), neocortex (+34 +/- 6%), and cerebellum (+49 +/- 12%) compared with normocapnic CPV values (group 1). Carotid ligation (group 2) led to a marked reduction of the CPV response to hypercapnia in the ipsilateral striatum (+23 +/- 14%) and neocortex (+27 +/- 17%) compared with the unclamped side (+34 +/- 15% and +38 +/- 16%, respectively). No significant changes in CPV were found in extracerebral tissue. In both groups, the CPV changes were reversed by the carbon dioxide washout period. Negligible changes in contrast imaging were detected during hypercapnia without administration of the contrast agent (group 3). Conclusions The contrast-enhanced magnetic resonance imaging technique is sensitive to detect noninvasively regional CPV changes induced by hypercapnia in rat brain. This could be of clinical interest for determining the cerebrovascular reactivity among different brain regions.

scholarly journals Magnetic Resonance Imaging Derived Biomarkers of IDH Mutation Status and Overall Survival in Grade III Astrocytomas

Diagnostics ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. 247
Author(s):  
Paola Feraco ◽  
Antonella Bacci ◽  
Patrizia Ferrazza ◽  
Luc van den Hauwe ◽  
Riccardo Pertile ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Overall Survival ◽  
Magnetic Resonance ◽  
Idh Mutation ◽  
Wild Type ◽  
Resonance Imaging ◽  
Characteristic Analysis ◽  
Mutation Status ◽  
Mutational Status ◽  
Adc Values

The evaluation of the isocitrate dehydrogenase (IDH) mutation status in the glioma decision-making process has diagnostic, prognostic and therapeutic implications. The aim of this study was to evaluate whether conventional magnetic resonance imaging (MRI) and apparent diffusion coefficient (ADC) can noninvasively predict the most common IDH mutational status (R132H) in GIII-astrocytomas and the overall survival (OS). Hence, twenty-two patients (9-F, 13-M) with a histological diagnosis of GIII-astrocytoma and evaluation of IDH-mutation status (12-wild type, 10-mutant) were retrospectively evaluated. Imaging studies were reviewed for the morphological feature and mean ADC values (ADCm). Statistics included a Fisher’s exact test, Student’s t-test, Spearman’s Test and receiver operating characteristic analysis. A p ≤ 0.05 value was considered statistically significant for all the tests. A younger age and a frontal location were more likely related to mutational status. IDH-wild type (Wt) exhibited a slight enhancement (p = 0.039). The ADCm values in IDH-mutant (Mut) patients were higher than those of IDH-Wt patients (p < 0.0004). The value of ADC ≥ 0.99 × 10−3 mm2/s emerged as a “cut-off” to differentiate the mutation state. In the overall group, a positive relationship between the ADCm values and OS was detected (p = 0.003; r = 0.62). Adding quantitative measures of ADC values to conventional MR imaging could be used routinely as a noninvasive marker of specific molecular patterns.

Evaluation of experimental myocardial infarction models via electromechanical mapping and magnetic resonance imaging

2013 ◽  
Vol 91 (8) ◽  
pp. 617-624 ◽  
Author(s):  
Edit Lukács ◽  
Balázs Magyari ◽  
Levente Tóth ◽  
Örs Petneházy ◽  
Zsolt Petrási ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Myocardial Infarction ◽  
Magnetic Resonance ◽  
Late Enhancement ◽  
Left Ventricular ◽  
Resonance Imaging ◽  
Characteristic Analysis ◽  
Diagnostic Features ◽  
Electromechanical Mapping ◽  
Diagnostic Characteristics

The diagnostic characteristics of electromechanical mapping (EMM) were evaluated in porcine myocardial infarction (MI) models with the parallel application of cardiac magnetic resonance imaging (cMRI) from the aspect of different pathophysiology and localization. Balloon occlusion in the left anterior descending coronary artery (LAD balloon group) or coil deployment in the LAD (LAD coil group) or circumflex artery (Cx coil group) was applied percutaneously in 16 domestic pigs. Regional left ventricular viability data were captured via cMRI and EMM. The unipolar voltage (UV) value was significantly decreased in segments containing transmural and subendocardial late enhancement compared with viable segments in the LAD balloon, LAD coil, and Cx coil groups. Receiver operating characteristic analysis revealed area under the curve values of 0.809 and 0.691 in the LAD infarct territory, and 0.864 and 0.855 in the Cx infarct territory for the UV compared with cMRI viability results as transmural late enhancement or viable tissue and subendocardial late enhancement or viable tissue, respectively. In conclusion, the UV value detected the presence of scar tissue with differential transmural extent and which represented proper diagnostic features both in the reperfused and nonreperfused models. This data could provide additional benefit in the clinical use of EMM for diagnostic purposes.

scholarly journals Magnetic Resonance Imaging Features of Cerebral Infarction in Critical Patients Based on Convolutional Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Yi Bo ◽  
Junli Xie ◽  
Jianguo Zhou ◽  
Shikun Li ◽  
Yuezhan Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Artificial Intelligence ◽  
Magnetic Resonance ◽  
Cerebral Infarction ◽  
Convolutional Neural Network ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Gray Level ◽  
Resonance Imaging

The clinical application of the artificial intelligence-assisted system in imaging was investigated by analyzing the magnetic resonance imaging (MRI) influence characteristics of cerebral infarction in critically ill patients based on the convolutional neural network (CNN). Fifty patients with cerebral infarction were enrolled and examined by MRI. Besides, a CNN artificial intelligence system was established for learning and training. The features were extracted from the MRI image results of the patients, and then, the data were calculated by computer technology. The gray-level cooccurrence matrix (GLCM) of T1-weighted images was 0.872 ± 0.069; the reasonable prediction (ALL) result was 0.766 ± 0.112; the gray-level run-length matrix (GLRLM) was 0.812 ± 0.101; the multigray-level area size matrix (MGLSZM) result was 0.713 ± 0.104; and the result of gray-scale area size matrix (GLSZM) was 0.598 ± 0.099. The GLCM, ALL, GLRLM, MGLSZM, and GLSZM of enhanced T1-weighted images were 0.710 ± 0.169, 0.742 ± 0.099, 0.778 ± 0.096, 0.801 ± 0.104, and 0.598 ± 0.099, respectively. The GLCM, ALL, GLRLM, MGLSZM, and GLSZM of T2-weighted images were 0.780 ± 0.096, 0.798 ± 0.087, 0.888 ± 0.086, 0.768 ± 0.112, and 0.767 ± 0.100, respectively. In short, the image diagnosis method that could reduce the subjective visual judgment error to a certain extent was found by analyzing the characteristics of MRI images of critically ill patients with cerebral infarction based on CNN.

scholarly journals Macrovascular Networks on Contrast-Enhanced Magnetic Resonance Imaging Improves Survival Prediction in Newly Diagnosed Glioblastoma

Cancers ◽  
2019 ◽  
Vol 11 (1) ◽  
pp. 84 ◽  
Author(s):  
Josep Puig ◽  
Carles Biarnés ◽  
Pepus Daunis-i-Estadella ◽  
Gerard Blasco ◽  
Alfredo Gimeno ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Prediction Models ◽  
Survival Prediction ◽  
Dynamic Susceptibility ◽  
Imaging Features ◽  
Newly Diagnosed ◽  
Resonance Imaging ◽  
Contrast Enhanced ◽  
Newly Diagnosed Glioblastoma

A higher degree of angiogenesis is associated with shortened survival in glioblastoma. Feasible morphometric parameters for analyzing vascular networks in brain tumors in clinical practice are lacking. We investigated whether the macrovascular network classified by the number of vessel-like structures (nVS) visible on three-dimensional T1-weighted contrast–enhanced (3D-T1CE) magnetic resonance imaging (MRI) could improve survival prediction models for newly diagnosed glioblastoma based on clinical and other imaging features. Ninety-seven consecutive patients (62 men; mean age, 58 ± 15 years) with histologically proven glioblastoma underwent 1.5T-MRI, including anatomical, diffusion-weighted, dynamic susceptibility contrast perfusion, and 3D-T1CE sequences after 0.1 mmol/kg gadobutrol. We assessed nVS related to the tumor on 1-mm isovoxel 3D-T1CE images, and relative cerebral blood volume, relative cerebral flow volume (rCBF), delay mean time, and apparent diffusion coefficient in volumes of interest for contrast-enhancing lesion (CEL), non-CEL, and contralateral normal-appearing white matter. We also assessed Visually Accessible Rembrandt Images scoring system features. We used ROC curves to determine the cutoff for nVS and univariate and multivariate cox proportional hazards regression for overall survival. Prognostic factors were evaluated by Kaplan-Meier survival and ROC analyses. Lesions with nVS > 5 were classified as having highly developed macrovascular network; 58 (60.4%) tumors had highly developed macrovascular network. Patients with highly developed macrovascular network were older, had higher volumeCEL, increased rCBFCEL, and poor survival; nVS correlated negatively with survival (r = −0.286; p = 0.008). On multivariate analysis, standard treatment, age at diagnosis, and macrovascular network best predicted survival at 1 year (AUC 0.901, 83.3% sensitivity, 93.3% specificity, 96.2% PPV, 73.7% NPV). Contrast-enhanced MRI macrovascular network improves survival prediction in newly diagnosed glioblastoma.

Sign in / Sign up

Export Citation Format

Share Document