Dataset Information

Amide Proton Transfer Imaging in Predicting Isocitrate Dehydrogenase 1 Mutation Status of Grade II/III Gliomas Based on Support Vector Machine.

ABSTRACT: Background:To compare the efficacies of univariate and radiomics analyses of amide proton transfer weighted (APTW) imaging in predicting isocitrate dehydrogenase 1 (IDH1) mutation of grade II/III gliomas. Methods:Fifty-nine grade II/III glioma patients with known IDH1 mutation status were prospectively included (IDH1 wild type, 16; IDH1 mutation, 43). A total of 1044 quantitative radiomics features were extracted from APTW images. The efficacies of univariate and radiomics analyses in predicting IDH1 mutation were compared. Feature values were compared between two groups with independent t-test and receiver operating characteristic (ROC) analysis was applied to evaluate the predicting efficacy of each feature. Cases were randomly assigned to either the training (n = 49) or test cohort (n = 10) for the radiomics analysis. Support vector machine with recursive feature elimination (SVM-RFE) was adopted to select the optimal feature subset. The adverse impact of the imbalance dataset in the training cohort was solved by synthetic minority oversampling technique (SMOTE). Subsequently, the performance of SVM model was assessed on both training and test cohort. Results:As for univariate analysis, 18 features were significantly different between IDH1 wild-type and mutant groups (P < 0.05). Among these parameters, High Gray Level Run Emphasis All Direction offset 8 SD achieved the biggest area under the curve (AUC) (0.769) with the accuracy of 0.799. As for radiomics analysis, SVM model was established using 19 features selected with SVM-RFE. The AUC and accuracy for IDH1 mutation on training set were 0.892 and 0.952, while on the testing set were 0.7 and 0.84, respectively. Conclusion:Radiomics strategy based on APT image features is potentially useful for preoperative estimating IDH1 mutation status.

SUBMITTER: Han Y

PROVIDER: S-EPMC7047712 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Amide Proton Transfer Imaging in Predicting Isocitrate Dehydrogenase 1 Mutation Status of Grade II/III Gliomas Based on Support Vector Machine.

Han Yu Y Wang Wen W Yang Yang Y Sun Ying-Zhi YZ Xiao Gang G Tian Qiang Q Zhang Jin J Cui Guang-Bin GB Yan Lin-Feng LF

Frontiers in neuroscience 20200221

<h4>Background</h4>To compare the efficacies of univariate and radiomics analyses of amide proton transfer weighted (APT<sub>W</sub>) imaging in predicting isocitrate dehydrogenase 1 (<i>IDH1</i>) mutation of grade II/III gliomas.<h4>Methods</h4>Fifty-nine grade II/III glioma patients with known <i>IDH1</i> mutation status were prospectively included (<i>IDH1</i> wild type, 16; <i>IDH1</i> mutation, 43). A total of 1044 quantitative radiomics features were extracted from APT<sub>W</sub> images. ...[more]

PMID: 32153362

Similar Datasets

Project description:BACKGROUND:Mutations in the isocitrate dehydrogenase 1 (IDH1) and IDH2 genes are important for both the integrated diagnosis and the prognosis of diffuse gliomas. The p.R132H mutation of IDH1 is the most frequently observed IDH mutation, while IDH2 mutations were relatively rarely studied. The aim of the study was to determine the pathological and genetic characteristics of lower-grade gliomas that carry IDH2 mutations. METHODS:Data from 238 adult patients with lower-grade gliomas were retrospectively analyzed. The status of IDH1/2 gene mutations, telomerase reverse transcriptase (TERT) promoter mutations, O-methylguanine-DNA-methyltransferase (MGMT) promoter methylation, 1p/19q co-deletion and the expressions of IDH1 R132H, alpha-thalassemia X-linked mental retardation, and p53 were evaluated. Progression-free survival (PFS) and overall survival (OS) were calculated via Kaplan-Meier estimation using the log-rank test. RESULTS:Totally, 71% (169/238) of patients were positive for IDH mutations, including 12 patients harboring mutations in IDH2. Among the 12 patients with IDH2 mutations, ten patients harbored the R172K mutation, one patient harbored the R172S mutation and one harbored the R172W mutation. Of these, 11 tumors occurred in the frontal lobe and showed morphology typical of oligodendroglioma. The proportion of grade II tumors was higher than that of grade III tumors in IDH2 mutant-gliomas. IDH2 mutations were frequently associated with TERT promoter mutations, 1p/19q co-deletion and MGMT promoter methylation. IDH2 mutations were associated with better outcomes compared with IDH wild-type gliomas (P?<?0.05). However, the PFS and OS did not differ from that of IDH1 mutant patients (P?=?0.95 and P?=?0.60, respectively). CONCLUSIONS:IDH2 mutations are more frequent in oligodendrogliomas and associated with a better prognosis. IDH2 mutations may segregate in distinct clinico-pathological and genetic subtypes of gliomas, and therefore may merit routine investigation.

Project description:Isocitrate dehydrogenase 1 gene mutations are found in most World Health Organization grade II and III gliomas and secondary glioblastomas. Isocitrate dehydrogenase 1 mutations are known to have prognostic value in high-grade gliomas. However, their prognostic significance in low-grade gliomas remains controversial. We determined the predictive and prognostic value of isocitrate dehydrogenase 1 status in low-grade gliomas. The association of isocitrate dehydrogenase 1 status with clinicopathological and genetic factors was also evaluated. Clinical information and genetic data including isocitrate dehydrogenase 1 mutation, O 6-methylguanine DNA methyltransferase promoter methylation, 1p/19q chromosome loss, and TP53 mutation of 417 low-grade gliomas were collected from the Chinese Glioma Genome Atlas database. Kaplan-Meier and Cox proportional hazards regression analyses were performed to evaluate the prognostic effect of clinical characteristics and molecular biomarkers. Isocitrate dehydrogenase 1 mutation was identified as an independent prognostic factor for overall, but not progression-free, survival. Notably, isocitrate dehydrogenase 1 mutation was found to be a significant prognostic factor in patients with oligodendrogliomas, but not in patients with astrocytomas. Furthermore, O 6-methylguanine DNA methyltransferase promoter methylation (p = 0.017) and TP53 mutation (p < 0.001), but not 1p/19q loss (p = 0.834), occurred at a higher frequency in isocitrate dehydrogenase 1-mutated tumors than in isocitrate dehydrogenase 1 wild-type tumors. Younger patient age (p = 0.041) and frontal lobe location (p = 0.010) were significantly correlated with isocitrate dehydrogenase 1 mutation. Chemotherapy did not provide a survival benefit in patients with isocitrate dehydrogenase 1-mutated tumors. Isocitrate dehydrogenase 1 mutation was an independent prognostic factor in low-grade gliomas, whereas it showed no predictive value for chemotherapy response. Isocitrate dehydrogenase 1 mutation was highly associated with O 6-methylguanine DNA methyltransferase promoter methylation and TP53 mutation.

Project description:BackgroundAccurate classification of diffuse gliomas, the most common tumors of the central nervous system in adults, is important for appropriate treatment. However, detection of isocitrate dehydrogenase (IDH) mutation and chromosome1p/19q codeletion, biomarkers to classify gliomas, is time- and cost-intensive and diagnostic discordance remains an issue. Adenosine to inosine (A-to-I) RNA editing has emerged as a novel cancer prognostic marker, but its value for glioma classification remains largely unexplored. We aim to (1) unravel the relationship between RNA editing and IDH mutation and 1p/19q codeletion and (2) predict IDH mutation and 1p/19q codeletion status using machine learning algorithms.ResultsBy characterizing genome-wide A-to-I RNA editing signatures of 638 gliomas, we found that tumors without IDH mutation exhibited higher total editing level compared with those carrying it (Kolmogorov-Smirnov test, p?<?0.0001). When tumor grade was considered, however, only grade IV tumors without IDH mutation exhibited higher total editing level. According to 10-fold cross-validation, support vector machines (SVM) outperformed random forest and AdaBoost (DeLong test, p?<?0.05). The area under the receiver operating characteristic curve (AUC) of SVM in predicting IDH mutation and 1p/19q codeletion were 0.989 and 0.990, respectively. After performing feature selection, AUCs of SVM and AdaBoost in predicting IDH mutation were higher than that of random forest (0.985 and 0.983 vs. 0.977; DeLong test, p?<?0.05), but AUCs of the three algorithms in predicting 1p/19q codeletion were similar (0.976-0.982). Furthermore, 67% of the six continuously misclassified samples by our 1p/19q codeletion prediction models were misclassifications in the original labelling after inspection of 1p/19q status and/or pathology report, highlighting the accuracy and clinical utility of our models.ConclusionsThe study represents the first genome-wide analysis of glioma editome and identifies RNA editing as a novel prognostic biomarker for glioma. Our prediction models provide standardized, accurate, reproducible and objective classification of gliomas. Our models are not only useful in clinical decision-making, but also able to identify editing events that have the potential to serve as biomarkers and therapeutic targets in glioma management and treatment.

Dataset Information

Amide Proton Transfer Imaging in Predicting Isocitrate Dehydrogenase 1 Mutation Status of Grade II/III Gliomas Based on Support Vector Machine.

Publications

Amide Proton Transfer Imaging in Predicting Isocitrate Dehydrogenase 1 Mutation Status of Grade II/III Gliomas Based on Support Vector Machine.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets