Magnetic resonance imaging texture analyses in lower-grade gliomas with a commercially available software: correlation of apparent diffusion coefficient and T2 skewness with 1p/19q codeletion

Deep-learning and conventional radiomics to predict IDH genotyping status based on magnetic resonance imaging data in adult diffuse glioma

Objectives

In adult diffuse glioma, preoperative detection of isocitrate dehydrogenase (IDH) status helps clinicians develop surgical strategies and evaluate patient prognosis. Here, we aim to identify an optimal machine-learning model for prediction of IDH genotyping by combining deep-learning (DL) signatures and conventional radiomics (CR) features as model predictors.

Methods

In this study, a total of 486 patients with adult diffuse gliomas were retrospectively collected from our medical center (n=268) and the public database (TCGA, n=218). All included patients were randomly divided into the training and validation sets by using nested 10-fold cross-validation. A total of 6,736 CR features were extracted from four MRI modalities in each patient, namely T1WI, T1CE, T2WI, and FLAIR. The LASSO algorithm was performed for CR feature selection. In each MRI modality, we applied a CNN+LSTM-based neural network to extract DL features and integrate these features into a DL signature after the fully connected layer with sigmoid activation. Eight classic machine-learning models were analyzed and compared in terms of their prediction performance and stability in IDH genotyping by combining the LASSO-selected CR features and integrated DL signatures as model predictors. In the validation sets, the prediction performance was evaluated by using accuracy and the area under the curve (AUC) of the receiver operating characteristics, while the model stability was analyzed by using the relative standard deviation of the AUC (RSDAUC). Subgroup analyses of DL signatures and CR features were also individually conducted to explore their independent prediction values.

Results

Logistic regression (LR) achieved favorable prediction performance (AUC: 0.920 ± 0.043, accuracy: 0.843 ± 0.044), whereas support vector machine with the linear kernel (l-SVM) displayed low prediction performance (AUC: 0.812 ± 0.052, accuracy: 0.821 ± 0.050). With regard to stability, LR also showed high robustness against data perturbation (RSDAUC: 4.7%). Subgroup analyses showed that DL signatures outperformed CR features (DL, AUC: 0.915 ± 0.054, accuracy: 0.835 ± 0.061, RSDAUC: 5.9%; CR, AUC: 0.830 ± 0.066, accuracy: 0.771 ± 0.051, RSDAUC: 8.0%), while DL and DL+CR achieved similar prediction results.

Conclusion

In IDH genotyping, LR is a promising machine-learning classification model. Compared with CR features, DL signatures exhibit markedly superior prediction values and discriminative capability.

Diagnostic performance of radiomics using machine learning algorithms to predict MGMT promoter methylation status in glioma patients: a meta-analysis

PURPOSE

We aimed to assess the diagnostic performance of radiomics using machine learning algorithms to predict the methylation status of the O6-methylguanine-DNA methyltransferase (MGMT) promoter in glioma patients.

METHODS

A comprehensive literature search of PubMed, EMBASE, and Web of Science until 27 July 2021 was performed to identify eligible studies. Stata SE 15.0 and Meta-Disc 1.4 were used for data analysis.

RESULTS

A total of fifteen studies with 1663 patients were included: five studies with training and validation cohorts and ten with only training cohorts. The pooled sensitivity and specificity of machine learning for predicting MGMT promoter methylation in gliomas were 85% (95% CI 79%-90%) and 84% (95% CI 78%-88%) in the training cohort (n=15) and 84% (95% CI 70%-92%) and 78% (95% CI 63%-88%) in the validation cohort (n=5). The AUC was 0.91 (95% CI 0.88-0.93) in the training cohort and 0.88 (95% CI 0.85-0.91) in the validation cohort. The meta-regression demonstrated that magnetic resonance imaging sequences were related to heterogeneity. The sensitivity analysis showed that heterogeneity was reduced by excluding one study with the lowest diagnostic performance.

CONCLUSION

This meta-analysis demonstrated that machine learning is a promising, reliable and repeatable candidate method for predicting MGMT promoter methylation status in glioma and showed a higher performance than non-machine learning methods.

Performances of Whole Tumor Texture Analysis Based on MRI: Predicting Preoperative T Stage of Rectal Carcinomas

Objective

To determine whether there is a correlation between texture features extracted from high-resolution T2-weighted imaging (HR-T2WI) or apparent diffusion coefficient (ADC) maps and the preoperative T stage (stages T1–2 versus T3–4) in rectal carcinomas.

Materials and Methods

One hundred and fifty four patients with rectal carcinomas who underwent preoperative HR-T2WI and diffusion-weighted imaging were enrolled. Patients were divided into training (n = 89) and validation (n = 65) cohorts. 3D Slicer was used to segment the entire volume of interest for whole tumors based on HR-T2WI and ADC maps. The least absolute shrinkage and selection operator (LASSO) was performed to select feature. The significantly difference was tested by the independent sample t-test and Mann-Whitney U test. The support vector machine (SVM) model was used to develop classification models. The correlation between features and T stage was assessed by Spearman’s correlation analysis. Multivariate logistic regression analysis was performed to identify independent predictors of tumor invasion. The performance of classifiers was evaluated by the receiver operating characteristic (ROC) curves.

Results

The wavelet HHH NGTDM strength (R_S = -0.364, P < 0.001) from HR-T2WI was an independent predictor of stage T3–4 tumors. The shape maximum 2D diameter column (R_S = 0.431, P < 0.001), log σ = 5.0 mm 3D first-order maximum (R_S = 0.276, P = 0.009), and log σ = 5.0 mm 3D first-order interquartile range (R_S = -0.229, P = 0.032) from ADC maps were independent predictors. In training cohorts, the classification models from HR-T2WI, ADC maps and the combination of two achieved the area under the ROC curves (AUCs) of 0.877, 0.902 and 0.941, with the accuracy of 79.78%, 89.86% and 89.89%, respectively. In validation cohorts, the three models achieved AUCs of 0.845, 0.881 and 0.910, with the accuracy of 78.46%, 83.08% and 87.69%, respectively.

Conclusions

Texture analysis based on ADC maps shows more potential than HR-T2WI in identifying preoperative T stage in rectal carcinomas. The combined application of HR-T2WI and ADC maps may help to improve the accuracy of preoperative diagnosis of rectal cancer invasion.

Radiological model based on the standard magnetic resonance sequences for detecting methylguanine methyltransferase methylation in glioma using texture analysis

This study aims to build a radiological model based on standard MR sequences for detecting methylguanine methyltransferase (MGMT) methylation in gliomas using texture analysis. A retrospective cross‐sectional study was undertaken in a cohort of 53 glioma patients who underwent standard preoperative magnetic resonance (MR) imaging. Conventional visual radiographic features and clinical factors were compared between MGMT promoter methylated and unmethylated groups. Texture analysis extracted the top five most powerful texture features of MR images in each sequence quantitatively for detecting the MGMT promoter methylation status. The radiomic signature (Radscore) was generated by a linear combination of the five features and estimates in each sequence. The combined model based on each Radscore was established using multivariate logistic regression analysis. A receiver operating characteristic (ROC) curve, nomogram, calibration, and decision curve analysis (DCA) were used to evaluate the performance of the model. No significant differences were observed in any of the visual radiographic features or clinical factors between different MGMT methylated statuses. The top five most powerful features were selected from a total of 396 texture features of T1, contrast‐enhanced T1, T2, and T2 FLAIR. Each sequence’s Radscore can distinguish MGMT methylated status. A combined model based on Radscores showed differentiation between methylated MGMT and unmethylated MGMT both in the glioblastoma (GBM) dataset as well as the dataset for all other gliomas. The area under the ROC curve values for the combined model was 0.818, with 90.5% sensitivity and 72.7% specificity, in the GBM dataset, and 0.833, with 70.2% sensitivity and 90.6% specificity, in the overall gliomas dataset. Nomogram, calibration, and DCA also validated the performance of the combined model. The combined model based on texture features could be considered as a noninvasive imaging marker for detecting MGMT methylation status in glioma.