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

Novel Imaging Approaches for Glioma Classification in the Era of the World Health Organization 2021 Update: A Scoping Review

The 2021 WHO classification of CNS tumors is a challenge for neuroradiologists due to the central role of the molecular profile of tumors. The potential of novel data analysis tools in neuroimaging must be harnessed to maintain its role in predicting tumor subgroups. We performed a scoping review to determine current evidence and research gaps. A comprehensive literature search was conducted regarding glioma subgroups according to the 2021 WHO classification and the use of MRI, radiomics, machine learning, and deep learning algorithms. Sixty-two original articles were included and analyzed by extracting data on the study design and results. Only 8% of the studies included pediatric patients. Low-grade gliomas and diffuse midline gliomas were represented in one-third of the research papers. Public datasets were utilized in 22% of the studies. Conventional imaging sequences prevailed; data on functional MRI (DWI, PWI, CEST, etc.) are underrepresented. Multiparametric MRI yielded the best prediction results. IDH mutation and 1p/19q codeletion status prediction remain in focus with limited data on other molecular subgroups. Reported AUC values range from 0.6 to 0.98. Studies designed to assess generalizability are scarce. Performance is worse for smaller subgroups (e.g., 1p/19q codeleted or IDH1/2 mutated gliomas). More high-quality study designs with diversity in the analyzed population and techniques are needed.

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.

Meta-analysis of the impact of laser interstitial hyperthermia on wound healing complications in brain tumors

High-grade gliomas (HGGs) may be amenable to the neurosurgical technique known as laser interstitial thermal therapy (LITT), which delivers thermal energy to interstitial brain injuries and wounds with pinpoint accuracy. The purpose of this extensive meta-analysis was to evaluate the effects of LITT on wound complications among patients who have brain tumours. Diverse conclusions emerge from a systematic review of pertinent studies, necessitating a comprehensive examination. The meta-analysis, performed utilizing the meta library provided by the R package meta, reveals an initial significant overall effect (RR: -2.1262, 95% CI [-2.7466, -1.5059], p < 0.0001) accompanied by considerable heterogeneity among studies (I2  = 61.13%). Following analyses that specifically examined the incidence of wounds, a complex correlation was found (RR: 0.0471, 95% CI [0.0264, 0.0842], p < 0.0001), indicating that LITT has a discernible but insignificant effect on the occurrence of wounds. Although the meta-analysis emphasizes a notable decrease in wound complications subsequent to LITT treatment, additional research is warranted due to constraints in standardized reporting, data accessibility, and small sample sizes. The results of this study underscore the need for exhaustive protocols to analyse wound complications in patients with brain tumours undergoing LITT.

Radiomics-Based Prediction of TERT Promotor Mutations in Intracranial High-Grade Meningiomas

PURPOSE

In meningiomas, TERT promotor mutations are rare but qualify the diagnosis of anaplasia, directly impacting adjuvant therapy. Effective screening for patients at risk for promotor mutations could enable more targeted molecular analyses and improve diagnosis and treatment.

METHODS

Semiautomatic segmentation of intracranial grade 2/3 meningiomas was performed on preoperative magnetic resonance imaging. Discriminatory power to predict TERT promoter mutations was analyzed using a random forest algorithm with an increasing number of radiomic features. Two final models with five and eight features with both fixed and differing radiomics features were developed and adjusted to eliminate random effects and to avoid overfitting.

RESULTS

A total of 117 image sets including training (N = 94) and test data (N = 23) were analyzed. To eliminate random effects and demonstrate the robustness of our approach, data partitioning and subsequent model development and testing were repeated a total of 100 times (each time with repartitioned training and independent test data). The established five- and eight-feature models with both fixed and different radiomics features enabled the prediction of TERT with similar but excellent performance. The five-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 91.8%/94.3%, mean accuracy of 85.5%/88.9%, mean sensitivity of 88.6%/91.4%, mean specificity of 83.2%/87.0%, and a mean Cohen's Kappa of 71.0%/77.7%. The eight-feature (different/fixed) model predicted TERT promotor mutation status with a mean AUC of 92.7%/94.6%, mean accuracy of 87.3%/88.9%, mean sensitivity of 89.6%/90.6%, mean specificity of 85.5%/87.5%, and a mean Cohen's Kappa of 74.4%/77.6%. Of note, the addition of further features of up to N = 8 only slightly increased the performance.

CONCLUSIONS

Radiomics-based machine learning enables prediction of TERT promotor mutation status in meningiomas with excellent discriminatory performance. Future analyses in larger cohorts should include grade 1 lesions as well as additional molecular alterations.

[Non-invasive diagnosis of brain gliomas by histological type using neuroradiomics in standardized regions of interest: towards digital biopsy]

The future of contemporary neuroimaging does not solely lie in novel image-capturing technologies, but also in better methods for extraction of useful information from these images. Scientists see great promise in radiomics, i.e. the methodology for analysis of multiple features in medical image. However, there are certain issues in this field impairing reproducibility of results. One such issue is no standards in establishing the regions of interest.

OBJECTIVE

To introduce a standardized method for identification of regions of interest when analyzing MR images using radiomics; to test the hypothesis that this approach is effective for distinguishing different histological types of gliomas.

MATERIAL AND METHODS

We analyzed preoperative MR data in 83 adults with various gliomas (WHO classification, 2016), i.e. oligodendroglioma, anaplastic oligodendroglioma, anaplastic astrocytoma, and glioblastoma. Radiomic features were computed for T1, T1-enhanced, T2 and T2-FLAIR modalities in four standardized volumetric regions of interest by 356 voxels (46.93 mm3): 1) contrast enhancement; 2) edema-infiltration; 3) area adjacent to edema-infiltration; 4) reference area in contralateral hemisphere. Subsequently, mathematical models were trained to classify MR-images of glioma depending on histological type and quantitative features.

RESULTS

Mean accuracy of differential diagnosis of 4 histological types of gliomas in experiments with machine learning was 81.6%, mean accuracy of identification of tumor types - from 94.1% to 99.5%. The best results were obtained using support vector machines and random forest model.

CONCLUSION

In a pilot study, the proposed standardization of regions of interest demonstrated high effectiveness for MR-based differential diagnosis of oligodendroglioma, anaplastic oligodendroglioma, anaplastic astrocytoma and glioblastoma. There are grounds for applying and improving this methodology in further studies.