Preoperative and Noninvasive Prediction of Gliomas Histopathological Grades and IDH Molecular Types Using Multiple MRI Characteristics.
Ontology highlight
ABSTRACT: Background and purpose
Gliomas are one of the most common tumors in the central nervous system. This study aimed to explore the correlation between MRI morphological characteristics, apparent diffusion coefficient (ADC) parameters and pathological grades, as well as IDH gene phenotypes of gliomas.Methods
Preoperative MRI data from 166 glioma patients with pathological confirmation were retrospectively analyzed to compare the differences of MRI characteristics and ADC parameters between the low-grade and high-grade gliomas (LGGs vs. HGGs), IDH mutant and wild-type gliomas (IDHmut vs. IDHwt). Multivariate models were constructed to predict the pathological grades and IDH gene phenotypes of gliomas and the performance was assessed by the receiver operating characteristic (ROC) analysis.Results
Two multivariable logistic regression models were developed by incorporating age, ADC parameters, and MRI morphological characteristics to predict pathological grades, and IDH gene phenotypes of gliomas, respectively. The Noninvasive Grading Model classified tumor grades with areas under the ROC curve (AUROC) of 0.934 (95% CI=0.895-0.973), sensitivity of 91.2%, and specificity of 78.6%. The Noninvasive IDH Genotyping Model differentiated IDH types with an AUROC of 0.857 (95% CI=0.787-0.926), sensitivity of 88.2%, and specificity of 63.8%.Conclusion
MRI features were correlated with glioma grades and IDH mutation status. Multivariable logistic regression models combined with MRI morphological characteristics and ADC parameters may provide a noninvasive and preoperative approach to predict glioma grades and IDH mutation status.
SUBMITTER: Du N
PROVIDER: S-EPMC9196247 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background: Deep learning (DL) could predict isocitrate dehydrogenase (IDH) mutation status from MRIs. Yet, previous work focused on CNNs with refined tumor segmentation. To bridge the gap, this study aimed to evaluate the feasibility of developing a Transformer-based network to predict the IDH mutation status free of refined tumor segmentation. Methods: A total of 493 glioma patients were recruited from two independent institutions for model development (TCIA; N = 259) and external test (AHXZ; N = 234). IDH mutation status was predicted directly from T2 images with a Swin Transformer and conventional ResNet. Furthermore, to investigate the necessity of refined tumor segmentation, seven strategies for the model input image were explored: (i) whole tumor slice; (ii-iii) tumor mask and/or not edema; (iv-vii) tumor bounding box of 0.8, 1.0, 1.2, 1.5 times. Performance comparison was made among the networks of different architectures along with different image input strategies, using area under the curve (AUC) and accuracy (ACC). Finally, to further boost the performance, a hybrid model was built by incorporating the images with clinical features. Results: With the seven proposed input strategies, seven Swin Transformer models and seven ResNet models were built, respectively. Based on the seven Swin Transformer models, an averaged AUC of 0.965 (internal test) and 0.842 (external test) were achieved, outperforming 0.922 and 0.805 resulting from the seven ResNet models, respectively. When a bounding box of 1.0 times was used, Swin Transformer (AUC = 0.868, ACC = 80.7%), achieved the best results against the one that used tumor segmentation (Tumor + Edema, AUC = 0.862, ACC = 78.5%). The hybrid model that integrated age and location features into images yielded improved performance (AUC = 0.878, Accuracy = 82.0%) over the model that used images only. Conclusions: Swin Transformer outperforms the CNN-based ResNet in IDH prediction. Using bounding box input images benefits the DL networks in IDH prediction and makes the IDH prediction free of refined glioma segmentation feasible.
| S-EPMC9369996 | biostudies-literature
Project description:To address the current lack of dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI)-based radiomics to predict isocitrate dehydrogenase (IDH) mutations in gliomas, we present a multicenter study that featured an independent exploratory set for radiomics model development and external validation using two independent cohorts. The maximum performance of the IDH mutation status prediction on the validation set had an accuracy of 0.544 (Cohen's kappa: 0.145, F1-score: 0.415, area under the curve-AUC: 0.639, sensitivity: 0.733, specificity: 0.491), which significantly improved to an accuracy of 0.706 (Cohen's kappa: 0.282, F1-score: 0.474, AUC: 0.667, sensitivity: 0.6, specificity: 0.736) when dynamic-based standardization of the images was performed prior to the radiomics. Model explainability using local interpretable model-agnostic explanations (LIME) and Shapley additive explanations (SHAP) revealed potential intuitive correlations between the IDH-wildtype increased heterogeneity and the texture complexity. These results strengthened our hypothesis that DSC-MRI radiogenomics in gliomas hold the potential to provide increased predictive performance from models that generalize well and provide understandable patterns between IDH mutation status and the extracted features toward enabling the clinical translation of radiogenomics in neuro-oncology.
| S-EPMC8391559 | biostudies-literature
Project description:Isocitrate dehydrogenase mutational status defines distinct biologic behavior and clinical outcomes in low-grade gliomas. We sought to determine magnetic resonance imaging characteristics associated with isocitrate dehydrogenase mutational status to evaluate the predictive roles of magnetic resonance imaging features in isocitrate dehydrogenase mutational status and therefore their potential impact on the determination of clinical target volume in radiotherapy. Forty-eight isocitrate dehydrogenase-mutant and 28 isocitrate dehydrogenase-wild-type low-grade gliomas were studied. Isocitrate dehydrogenase mutation was related to more frequency of cortical involvement compared to isocitrate dehydrogenase-wild-type group (34/46 vs 6/24, P = .0001). Peritumoral edema was less frequent in isocitrate dehydrogenase-mutant tumors (32.6% vs 58.3% for isocitrate dehydrogenase-wild-type tumors, P = .0381). Isocitrate dehydrogenase-wild-type tumors were more likely to have a nondefinable border, while isocitrate dehydrogenase-mutant tumors had well-defined borders (66.7% vs 39.1%, P = .0287). Only 8 (17.4%) of 46 of the isocitrate dehydrogenase-mutant tumors demonstrated marked enhancement, while this was 66.7% in isocitrate-wild-type tumors (P < .0001). Choline-creatinine ratio for isocitrate dehydrogenase-wild-type tumors was significantly higher than that for isocitrate dehydrogenase-mutant tumors. In conclusion, frontal location, well-defined border, cortical involvement, less peritumoral edema, lack of enhancement, and low choline-creatinine ratio were predictive for the definition of isocitrate dehydrogenase-mutant low-grade gliomas. Magnetic resonance imaging can provide an advantage in the detection of isocitrate dehydrogenase status indirectly and indicate the need to explore new design for treatment planning in gliomas. Choline-creatinine ratio in magnetic resonance spectroscopy could be a potential more reasonable reference for the new design of delineation of target volume in low-grade gliomas.
| S-EPMC6767744 | biostudies-literature
Project description:ObjectivesGliomas with comutations of isocitrate dehydrogenase (IDH) genes and telomerase reverse transcriptase (TERT) gene promoter (IDHmut pTERTmut) show distinct biological features and respond to first-line treatment differently in comparison with other gliomas. This study aimed to characterize the IDHmut pTERTmut gliomas in multimodal MRI using the radiomic method and establish a precise diagnostic model identifying this group of gliomas.MethodsA total of 140 patients with untreated primary gliomas were admitted between 2016 and 2020 to West China Hospital as a discovery cohort, including 22 IDHmut pTERTmut patients. Thirty-four additional cases from a different hospital were included in the study as an independent validation cohort. A total of 3654 radiomic features were extracted from the preoperative multimodal MRI images (T1c, FLAIR, and ADC maps) and filtered in a data-driven approach. The discovery cohort was split into training and test sets by a 4:1 ratio. A diagnostic model (multilayer perceptron classifier) for detecting the IDHmut pTERTmut gliomas was trained using an automatic machine-learning algorithm named tree-based pipeline optimization tool (TPOT). The most critical radiomic features in the model were identified and visualized.ResultsThe model achieved an area under the receiver-operating curve (AUROC) of 0.971 (95% CI, 0.902-1.000), the sensitivity of 0.833 (95% CI, 0.333-1.000), and the specificity of 0.966 (95% CI, 0.931-1.000) in the test set. The area under the precision-recall curve (AUCPR) was 0.754 (95% CI, 0.572-0.833) and the F1 score was 0.833 (95% CI, 0.500-1.000). In the independent validation set, the model reached 0.952 AUROC, 0.714 sensitivity, 0.963 specificity, 0.841 AUCPR, and 0.769 F1 score. MR radiomic features of the IDHmut pTERTmut gliomas represented homogenous low-complexity texture in three modalities.ConclusionsAn accurate diagnostic model was constructed for detecting IDHmut pTERTmut gliomas using multimodal radiomic features. The most important features were associated with the homogenous simple texture of IDHmut pTERTmut gliomas in MRI images transformed using Laplacian of Gaussian and wavelet filters.
| S-EPMC9939206 | biostudies-literature
Project description:Mutations in isocitrate dehydrogenase genes IDH1 and IDH2 are frequently found in diffuse and anaplastic astrocytic and oligodendroglial tumours as well as in secondary glioblastomas. As IDH is a very important prognostic, diagnostic and therapeutic biomarker for glioma, it is of paramount importance to determine its mutational status. The haematoxylin and eosin (H&E) staining is a valuable tool in precision oncology as it guides histopathology-based diagnosis and proceeding patient's treatment. However, H&E staining alone does not determine the IDH mutational status of a tumour. Deep learning methods applied to MRI data have been demonstrated to be a useful tool in IDH status prediction, however the effectiveness of deep learning on H&E slides in the clinical setting has not been investigated so far. Furthermore, the performance of deep learning methods in medical imaging has been practically limited by small sample sizes currently available. Here we propose a data augmentation method based on the Generative Adversarial Networks (GAN) deep learning methodology, to improve the prediction performance of IDH mutational status using H&E slides. The H&E slides were acquired from 266 grade II-IV glioma patients from a mixture of public and private databases, including 130 IDH-wildtype and 136 IDH-mutant patients. A baseline deep learning model without data augmentation achieved an accuracy of 0.794 (AUC = 0.920). With GAN-based data augmentation, the accuracy of the IDH mutational status prediction was improved to 0.853 (AUC = 0.927) when the 3,000 GAN generated training samples were added to the original training set (24,000 samples). By integrating also patients' age into the model, the accuracy improved further to 0.882 (AUC = 0.931). Our findings show that deep learning methodology, enhanced by GAN data augmentation, can support physicians in gliomas' IDH status prediction.
| S-EPMC7206037 | biostudies-literature
Project description:PurposeTo assess the amide proton transfer-weighted (APTw) MRI features of isocitrate dehydrogenase (IDH)-wildtype and IDH-mutant grade II gliomas and to test the hypothesis that the APTw signal is a surrogate imaging marker for identifying IDH mutation status preoperatively.MethodsTwenty-seven patients with pathologically confirmed low-grade glioma, who were previously scanned at 3T, were retrospectively analyzed. The Mann-Whitney test was used to evaluate relationships between APTw intensities for IDH-mutant and IDH-wildtype groups, and receiver operator characteristic (ROC) analysis was used to assess the diagnostic performance of APTw.ResultsBased on histopathology and molecular analysis, seven cases were diagnosed as IDH-wildtype grade II gliomas and 20 cases as IDH-mutant grade II gliomas. The maximum and minimum APTw values, based on multiple regions of interest, as well as the whole-tumor histogram-based mean and 50th percentile APTw values, were significantly higher in the IDH-wildtype gliomas than in the IDH-mutant groups. This corresponded to the areas under the ROC curves of 0.89, 0.76, 0.75, and 0.75, respectively, for the prediction of the IDH mutation status.ConclusionIDH-wildtype lesions typically were associated with relatively high APTw signal intensities as compared with IDH-mutant lesions. The APTw signal could be a valuable imaging biomarker by which to identify IDH1 mutation status in grade II gliomas. Magn Reson Med 78:1100-1109, 2017. © 2017 International Society for Magnetic Resonance in Medicine.
| S-EPMC5561497 | biostudies-literature
Project description:BackgroundThis study aimed to assess the validity and pathophysiology of the T2/FLAIR-mismatch sign for noninvasive identification of isocitrate dehydrogenase (IDH)-mutant 1p/19q non-codeleted glioma.MethodsMagnetic resonance imaging scans from 408 consecutive patients with newly diagnosed glioma (113 lower-grade gliomas and 295 glioblastomas) were evaluated for the presence of T2/FLAIR-mismatch sign by 2 independent reviewers. Sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated to assess the performance of the T2/FLAIR-mismatch sign for identifying IDH-mutant 1p/19q non-codeleted tumors. An exploratory analysis of differences in contrast-enhancing tumor volumes, apparent diffusion coefficient (ADC) values, and relative cerebral blood volume (rCBV) values in IDH-mutant gliomas with versus without the presence of a T2/FLAIR-mismatch sign (as well as analysis of spatial differences within tumors with the presence of a T2/FLAIR-mismatch sign) was performed.ResultsThe T2/FLAIR-mismatch sign was present in 12 cases with lower-grade glioma (10.6%), all of them being IDH-mutant 1p/19q non-codeleted tumors (sensitivity = 10.9%, specificity = 100%, PPV = 100%, NPV = 3.0%, accuracy = 13.3%). There was a substantial interrater agreement to identify the T2/FLAIR-mismatch sign (Cohen's kappa = 0.75 [95% CI, 0.57-0.93]). The T2/FLAIR-mismatch sign was not identified in any other molecular subgroup, including IDH-mutant glioblastoma cases (n = 5). IDH-mutant gliomas with a T2/FLAIR-mismatch sign showed significantly higher ADC (P < .0001) and lower rCBV values (P = .0123) as compared to IDH-mutant gliomas without a T2/FLAIR-mismatch sign. Moreover, in IDH-mutant gliomas with T2/FLAIR-mismatch sign the ADC values were significantly lower in the FLAIR-hyperintense rim as compared to the FLAIR-hypointense core of the tumor (P = .0005).ConclusionsThis study confirms the high specificity of the T2/FLAIR-mismatch sign for noninvasive identification of IDH-mutant 1p/19q non-codeleted gliomas; however, sensitivity is low and applicability is limited to lower-grade gliomas. Whether the higher ADC and lower rCBV values in IDH-mutant gliomas with a T2/FLAIR-mismatch sign (as compared to those without) translate into a measurable prognostic effect requires investigation in future studies. Moreover, spatial differences in ADC values between the core and rim of tumors with a T2/FLAIR-mismatch sign potentially reflect specific distinctions in tumor cellularity and microenvironment.
| S-EPMC7212872 | biostudies-literature
Project description:OBJECTIVES:Vessel size imaging (VSI) could reveal average microvessel diameter. The aim was to investigate microvascular characteristics and the efficacy of VSI in lower-grade glioma (LGG) grading and subtype differentiation based on 2016 classification of central nervous system tumours. METHODS:Fifty-seven LGG (grade II/III, 36/21) patients who received VSI examination before surgery were retrospectively analysed. The average (Rmean) and maximum (Rmax) vessel size indexes were obtained. The long (VDmax) and short (VDmin) vascular diameter, microvascular area (MVA) and density (MVD) were obtained using paraffin specimens. The patients were divided into grades II and III, and histological and molecular subtypes. The differences among microvascular parameters of different subtypes and grades were compared. Two-sample t-test, analysis of variance test, Mann-Whitney test, the Kruskal-Wallis test and Pearson correlation analysis were used for statistics. RESULTS:Rmean, Rmax, VDmin, VDmax, and MVA were higher in grade-III than in grade-II LGGs (p < 0.05) in each type except the isocitrate dehydrogenase (IDH) mutant with 1p/19q-intact type. For grade II, the IDH mutant with 1p/19q co-deleted and IDH wildtype possessed more dominant angiogenesis than IDH mutant with 1p/19q-intact type, revealed by lower Rmean, Rmax and VDmin while higher MVD for the former (p < 0.05), the same as oligodendroglioma versus astrocytoma. Rmean and Rmax correlated with VDmin (r = 0.804, 0.815, p < 0.05), VDmax (r = 0.766, 0.774, p < 0.05) and MVA (r = 0.755, 0.759, p < 0.05), respectively, while they had no correlation with MVD (r = -0.085, -0.080, p > 0.05). CONCLUSIONS:VSI holds great potential for non-invasively revealing microvascular characteristics of LGGs pre-surgery and differentiating their grades and molecular subtypes. KEY POINTS:• VSI can assist in differentiating grade-II and -III gliomas. • The IDH gene and 1p/19q chromosome may influence the angiogenesis in grade-II gliomas. • VSI is valuable for differentiating the molecular subtypes of grade-II gliomas.
| S-EPMC6420610 | biostudies-literature
Project description:BackgroundIncidence and characteristics of pseudoprogression in isocitrate dehydrogenase-mutant high-grade gliomas (IDHmt HGG) remain to be specifically described.MethodsWe analyzed pseudoprogression characteristics and explored the possibility of pseudoprogression misdiagnosis in IDHmt HGG patients, treated with radiotherapy (RT) (with or without chemotherapy [CT]), included in the French POLA network. Pseudoprogression was analyzed in patients with MRI available for review (reference cohort, n = 200). Pseudoprogression misdiagnosis was estimated in this cohort and in an independent cohort (control cohort, n = 543) based on progression-free survival before and after first progression.ResultsIn the reference cohort, 38 patients (19%) presented a pseudoprogression after a median time of 10.5 months after RT. Pseudoprogression characteristics were similar across IDHmt HGG subtypes. In most patients, it consisted of the appearance of one or several infracentimetric, asymptomatic, contrast-enhanced lesions occurring within 2 years after RT. The only factor associated with pseudoprogression occurrence was adjuvant PCV CT. Among patients considered as having a first true progression, 7 out of 41 (17%) in the reference cohort and 35 out of 203 (17%) in the control cohort were retrospectively suspected to have a misdiagnosed pseudoprogression. Patients with a misdiagnosed pseudoprogression were characterized by a time to event and an outcome similar to that of patients with a pseudoprogression but presented with larger and more symptomatic lesions.ConclusionIn patients with an IDHmt HGG, pseudoprogression occurs later than in IDH-wildtype glioblastomas and seems not only frequent but also frequently misdiagnosed. Within the first 2 years after RT, the possibility of a pseudoprogression should be carefully considered.
| S-EPMC10013645 | biostudies-literature
Project description: Not available
| S-EPMC10713834 | biostudies-literature