+1 Recommend
0 collections
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

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


      Read this article at

          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.



          To compare the efficacies of univariate and radiomics analyses of amide proton transfer weighted (APT W) imaging in predicting isocitrate dehydrogenase 1 ( IDH1) mutation of grade II/III gliomas.


          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 APT W 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.


          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.


          Radiomics strategy based on APT image features is potentially useful for preoperative estimating IDH1 mutation status.

          Related collections

          Most cited references 25

          • Record: found
          • Abstract: found
          • Article: not found

          Type and frequency of IDH1 and IDH2 mutations are related to astrocytic and oligodendroglial differentiation and age: a study of 1,010 diffuse gliomas.

          Somatic mutations in the IDH1 gene encoding cytosolic NADP+-dependent isocitrate dehydrogenase have been shown in the majority of astrocytomas, oligodendrogliomas and oligoastrocytomas of WHO grades II and III. IDH2 encoding mitochondrial NADP+-dependent isocitrate dehydrogenase is also mutated in these tumors, albeit at much lower frequencies. Preliminary data suggest an importance of IDH1 mutation for prognosis showing that patients with anaplastic astrocytomas, oligodendrogliomas and oligoastrocytomas harboring IDH1 mutations seem to fare much better than patients without this mutation in their tumors. To determine mutation types and their frequencies, we examined 1,010 diffuse gliomas. We detected 716 IDH1 mutations and 31 IDH2 mutations. We found 165 IDH1 (72.7%) and 2 IDH2 mutations (0.9%) in 227 diffuse astrocytomas WHO grade II, 146 IDH1 (64.0%) and 2 IDH2 mutations (0.9%) in 228 anaplastic astrocytomas WHO grade III, 105 IDH1 (82.0%) and 6 IDH2 mutations (4.7%) in 128 oligodendrogliomas WHO grade II, 121 IDH1 (69.5%) and 9 IDH2 mutations (5.2%) in 174 anaplastic oligodendrogliomas WHO grade III, 62 IDH1 (81.6%) and 1 IDH2 mutations (1.3%) in 76 oligoastrocytomas WHO grade II and 117 IDH1 (66.1%) and 11 IDH2 mutations (6.2%) in 177 anaplastic oligoastrocytomas WHO grade III. We report on an inverse association of IDH1 and IDH2 mutations in these gliomas and a non-random distribution of the mutation types within the tumor entities. IDH1 mutations of the R132C type are strongly associated with astrocytoma, while IDH2 mutations predominantly occur in oligodendroglial tumors. In addition, patients with anaplastic glioma harboring IDH1 mutations were on average 6 years younger than those without these alterations.
            • Record: found
            • Abstract: found
            • Article: not found

            Amide proton transfer (APT) contrast for imaging of brain tumors.

            In this work we demonstrate that specific MR image contrast can be produced in the water signal that reflects endogenous cellular protein and peptide content in intracranial rat 9L gliosarcomas. Although the concentration of these mobile proteins and peptides is only in the millimolar range, a detection sensitivity of several percent on the water signal (molar concentration) was achieved. This was accomplished with detection sensitivity enhancement by selective radiofrequency (RF) labeling of the amide protons, and by utilizing the effective transfer of this label to water via hydrogen exchange. Brain tumors were also assessed by conventional T(1)-weighted, T(2)-weighted, and diffusion-weighted imaging. Whereas these commonly-used approaches yielded heterogeneous images, the new amide proton transfer (APT) technique showed a single well-defined region of hyperintensity that was assigned to brain tumor tissue. Copyright 2003 Wiley-Liss, Inc.
              • Record: found
              • Abstract: found
              • Article: not found

              Glioblastoma multiforme: exploratory radiogenomic analysis by using quantitative image features.

              To derive quantitative image features from magnetic resonance (MR) images that characterize the radiographic phenotype of glioblastoma multiforme (GBM) lesions and to create radiogenomic maps associating these features with various molecular data.

                Author and article information

                Front Neurosci
                Front Neurosci
                Front. Neurosci.
                Frontiers in Neuroscience
                Frontiers Media S.A.
                21 February 2020
                : 14
                Department of Radiology & Functional and Molecular Imaging Key Lab of Shaanxi Province, Tangdu Hospital, Fourth Military Medical University , Xi’an, China
                Author notes

                Edited by: Miguel Castelo-Branco, Coimbra Institute for Biomedical Imaging and Translational Research (CIBIT), Portugal

                Reviewed by: Dong-Hoon Lee, The University of Sydney, Australia; Bing Zhang, Nanjing Drum Tower Hospital, China

                *Correspondence: Guang-Bin Cui, cuigbtd@ 123456fmmu.edu.cn ; cgbtd@ 123456126.com

                These authors have contributed equally to this work

                This article was submitted to Brain Imaging Methods, a section of the journal Frontiers in Neuroscience

                Copyright © 2020 Han, Wang, Yang, Sun, Xiao, Tian, Zhang, Cui and Yan.

                This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

                Page count
                Figures: 6, Tables: 3, Equations: 2, References: 40, Pages: 11, Words: 0
                Original Research


                Comment on this article