Comparison of MRI Sequences to Predict IDH Mutation Status in Gliomas Using Radiomics-Based Machine Learning.

OBJECTIVES: Regarding the 2021 World Health Organization (WHO) classification of central nervous system (CNS) tumors, the isocitrate dehydrogenase (IDH) mutation status is one of the most important factors for CNS tumor classification. The aim of our study is to analyze which of the commonly used magnetic resonance imaging (MRI) sequences is best suited to obtain this information non-invasively using radiomics-based machine learning models. We developed machine learning models based on different MRI sequences and determined which of the MRI sequences analyzed yields the highest discriminatory power in predicting the IDH mutation status. MATERIAL AND METHODS: In our retrospective IRB-approved study, we used the MRI images of 106 patients with histologically confirmed gliomas. The MRI images were acquired using the T1 sequence with and without administration of a contrast agent, the T2 sequence, and the Fluid-Attenuated Inversion Recovery (FLAIR) sequence. To objectively compare performance in predicting the IDH mutation status as a function of the MRI sequence used, we included only patients in our study cohort for whom MRI images of all four sequences were available. Seventy-one of the patients had an IDH mutation, and the remaining 35 patients did not have an IDH mutation (IDH wild-type). For each of the four MRI sequences used, 107 radiomic features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects associated with the data partitioning. Feature preselection and subsequent model development were performed using Random Forest, Lasso regression, LDA, and Naïve Bayes. The performance of all models was determined with independent test data. RESULTS: Among the different approaches we examined, the T1-weighted contrast-enhanced sequence was found to be the most suitable for predicting IDH mutations status using radiomics-based machine learning models. Using contrast-enhanced T1-weighted MRI images, our seven-feature model developed with Lasso regression achieved a mean area under the curve (AUC) of 0.846, a mean accuracy of 0.792, a mean sensitivity of 0.847, and a mean specificity of 0.681. The administration of contrast agents resulted in a significant increase in the achieved discriminatory power. CONCLUSIONS: Our analyses show that for the prediction of the IDH mutation status using radiomics-based machine learning models, among the MRI images acquired with the commonly used MRI sequences, the contrast-enhanced T1-weighted images are the most suitable.

Comparison of MRI Sequences to Predict ATRX Status Using Radiomics-Based Machine Learning.

ATRX is an important molecular marker according to the 2021 WHO classification of adult-type diffuse glioma. We aim to predict the ATRX mutation status non-invasively using radiomics-based machine learning models on MRI and to determine which MRI sequence is best suited for this purpose. In this retrospective study, we used MRI images of patients with histologically confirmed glioma, including the sequences T1w without and with the administration of contrast agent, T2w, and the FLAIR. Radiomics features were extracted from the corresponding MRI images by hand-delineated regions of interest. Data partitioning into training data and independent test data was repeated 100 times to avoid random effects. Feature preselection and subsequent model development were performed using Lasso regression. The T2w sequence was found to be the most suitable and the FLAIR sequence the least suitable for predicting ATRX mutations using radiomics-based machine learning models. For the T2w sequence, our seven-feature model developed with Lasso regression achieved a mean AUC of 0.831, a mean accuracy of 0.746, a mean sensitivity of 0.772, and a mean specificity of 0.697. In conclusion, for the prediction of ATRX mutation using radiomics-based machine learning models, the T2w sequence is the most suitable among the commonly used MRI sequences.

Use Test of Automated Machine Learning in Cancer Diagnostics.

Our aim is to investigate the added value of automated machine learning (AutoML) for potential future applications in cancer diagnostics. Using two important diagnostic questions, the non-invasive determination of IDH mutation status and ATRX status, we analyze whether it is possible to use AutoML to develop models that are comparable in performance to conventional machine learning models (ML) developed by experts. For this purpose, we develop AutoML models using different feature preselection methods and compare the results with previously developed conventional ML models. The cohort used for our study comprises T2-weighted MRI images of 124 patients with histologically confirmed gliomas. Using AutoML, we were able to develop sophisticated models in a very short time with only a few lines of computer code. In predicting IDH mutation status, we obtained a mean AUC of 0.7400 and a mean AUPRC of 0.8582. ATRX mutation status was predicted with very similar discriminatory power, with a mean AUC of 0.7810 and a mean AUPRC of 0.8511. In both cases, AutoML was even able to achieve a discriminatory power slightly above that of the respective conventionally developed models in a very short computing time, thus making such methods accessible to non-experts in the near future.

Radiomics for pseudoprogression prediction in high grade gliomas: added value of MR contrast agent.

Objective: Our aim is to define the capabilities of radiomics in predicting pseudoprogression from pre-treatment MR images in patients diagnosed with high-grade gliomas using T1 non-contrast-enhanced and contrast-enhanced images. Material & methods: In this retrospective IRB-approved study, image segmentation of high-grade gliomas was semi-automatically performed using 3D Slicer. Non-contrast-enhanced T1-weighted images and contrast-enhanced T1-weighted images were used prior to surgical therapy or radio-chemotherapy. Imaging data was split into a training sample and an independent test sample at random. We extracted 107 radiomic features by use of PyRadiomics. Feature selection and model construction were performed using Generalized Boosted Regression Models (GBM). Results: Our cohort included 124 patients (female: n = 53), diagnosed with progressive (n = 61) and pseudoprogressive disease (n = 63) of primary high-grade gliomas. Based on non-contrast-enhanced T1-weighted images of the independent test sample, the mean area under the curve (AUC), mean sensitivity, mean specificity and mean accuracy of our model were 0.651 [0.576, 0.761], 0.616 [0.417, 0.833], 0.578 [0.417, 0.750] and 0.597 [0.500, 0.708] to predict the development of pseudoprogression. In comparison, the independent test data of contrast-enhanced T1-weighted images yielded significantly higher values of AUC = 0.819 [0.760, 0.872], sensitivity = 0.817 [0.750, 0.833], specificity = 0.723 [0.583, 0.833] and accuracy = 0.770 [0.687, 0.833]. Conclusion: Our findings show that it is possible to predict pseudoprogression of high-grade gliomas with a Radiomics model using contrast-enhanced T1-weighted images with comparatively good discriminatory power. The use of a contrast agent results in a clear added value.

Pseudoprogression prediction in high grade primary CNS tumors by use of radiomics.

Our aim is to define the capabilities of radiomics and machine learning in predicting pseudoprogression development from pre-treatment MR images in a patient cohort diagnosed with high grade gliomas. In this retrospective analysis, we analysed 131 patients with high grade gliomas. Segmentation of the contrast enhancing parts of the tumor before administration of radio-chemotherapy was semi-automatically performed using the 3D Slicer open-source software platform (version 4.10) on T1 post contrast MR images. Imaging data was split into training data, test data and an independent validation sample at random. We extracted a total of 107 radiomic features by hand-delineated regions of interest (ROI). Feature selection and model construction were performed using Generalized Boosted Regression Models (GBM). 131 patients were included, of which 64 patients had a histopathologically proven progressive disease and 67 were diagnosed with mixed or pure pseudoprogression after initial treatment. Our Radiomics approach is able to predict the occurrence of pseudoprogression with an AUC, mean sensitivity, mean specificity and mean accuracy of 91.49% [86.27%, 95.89%], 79.92% [73.08%, 87.55%], 88.61% [85.19%, 94.44%] and 84.35% [80.19%, 90.57%] in the full development group, 78.51% [75.27%, 82.46%], 66.26% [57.95%, 73.02%], 78.31% [70.48%, 84.19%] and 72.40% [68.06%, 76.85%] in the testing group and finally 72.87% [70.18%, 76.28%], 71.75% [62.29%, 75.00%], 80.00% [69.23%, 84.62%] and 76.04% [69.90%, 80.00%] in the independent validation sample, respectively. Our results indicate that radiomics is a promising tool to predict pseudo-progression, thus potentially allowing to reduce the use of biopsies and invasive histopathology.