Preoperative, noninvasive prediction of the meningioma grade is important because it influences the treatment strategy. The purpose of this study was to evaluate the role of radiomics features of postcontrast T1-weighted images (T1C), apparent diffusion coefficient (ADC), and fractional anisotropy (FA) maps, based on the entire tumor volume, in the differentiation of grades and histological subtypes of meningiomas.

BACKGROUND AND PURPOSE: WHO grade II gliomas are divided into three classes: isocitrate dehydrogenase (IDH)-wildtype, IDH-mutant and no 1p/19q codeletion, and IDH-mutant and 1p/19q-codeleted. Different molecular subtypes have been reported to have prognostic differences and different chemosensitivity. Our aim was to evaluate the predictive value of imaging phenotypes assessed with the Visually AcceSAble Rembrandt Images lexicon for molecular classification of lower grade gliomas. MATERIALS AND METHODS: MR imaging scans of 175 patients with lower grade gliomas with known IDH1 mutation and 1p/19q-codeletion status were included (78 grade II and 97 grade III) in the discovery set. MR imaging features were reviewed by using Visually AcceSAble Rembrandt Images (VASARI); their associations with molecular markers were assessed. The predictive power of imaging features for IDH1-wild type tumors was evaluated using the Least Absolute Shrinkage and Selection Operator. We tested the model in a validation set (40 subjects). RESULTS: Various imaging features were significantly different according to IDH1 mutation. Nonlobar location, larger proportion of enhancing tumors, multifocal/multicentric distribution, and poor definition of nonenhancing margins were independent predictors of an IDH1 wild type according to the Least Absolute Shrinkage and Selection Operator. The areas under the curve for the prediction model were 0.859 and 0.778 in the discovery and validation sets, respectively. The IDH1-mutant, 1p/19q-codeleted group frequently had mixed/restricted diffusion characteristics and showed more pial invasion compared with the IDH1-mutant, no codeletion group. CONCLUSIONS: Preoperative MR imaging phenotypes are different according to the molecular markers of lower grade gliomas, and they may be helpful in predicting the IDH1-mutation status.

The fifth edition of the World Health Organization (WHO) classification of central nervous system tumors published in 2021 advances the role of molecular diagnostics in the classification of gliomas by emphasizing integrated diagnoses based on histopathology and molecular information and grouping tumors based on genetic alterations. Importantly, molecular biomarkers that provide important prognostic information are now a parameter for establishing tumor grades in gliomas. Understanding the 2021 WHO classification is crucial for radiologists for daily imaging interpretation as well as communication with clinicians. Although imaging features are not included in the 2021 WHO classification, imaging can serve as a powerful tool to impact the clinical practice not only prior to tissue confirmation but beyond. This review represents the first of a three‐installment review series on the 2021 WHO classification for gliomas, glioneuronal tumors, and neuronal tumors and implications on imaging diagnosis. This Part 1 Review focuses on the major changes to the classification of gliomas and imaging findings on adult‐type diffuse gliomas.Evidence Level: 3.Technical Efficacy: Stage 3.

This study aims to determine how randomly splitting a dataset into training and test sets affects the estimated performance of a machine learning model and its gap from the test performance under different conditions, using real-world brain tumor radiomics data. We conducted two classification tasks of different difficulty levels with magnetic resonance imaging (MRI) radiomics features: (1) “Simple” task, glioblastomas [n = 109] vs. brain metastasis [n = 58] and (2) “difficult” task, low- [n = 163] vs. high-grade [n = 95] meningiomas. Additionally, two undersampled datasets were created by randomly sampling 50% from these datasets. We performed random training-test set splitting for each dataset repeatedly to create 1,000 different training-test set pairs. For each dataset pair, the least absolute shrinkage and selection operator model was trained and evaluated using various validation methods in the training set, and tested in the test set, using the area under the curve (AUC) as an evaluation metric. The AUCs in training and testing varied among different training-test set pairs, especially with the undersampled datasets and the difficult task. The mean (±standard deviation) AUC difference between training and testing was 0.039 (±0.032) for the simple task without undersampling and 0.092 (±0.071) for the difficult task with undersampling. In a training-test set pair with the difficult task without undersampling, for example, the AUC was high in training but much lower in testing (0.882 and 0.667, respectively); in another dataset pair with the same task, however, the AUC was low in training but much higher in testing (0.709 and 0.911, respectively). When the AUC discrepancy between training and test, or generalization gap, was large, none of the validation methods helped sufficiently reduce the generalization gap. Our results suggest that machine learning after a single random training-test set split may lead to unreliable results in radiomics studies especially with small sample sizes.

Background: Growing evidence suggests an association between imaging biomarkers of small vessel disease and future cognitive decline in Parkinson's disease (PD). Recently, magnetic resonance imaging–visible perivascular space (PVS) has been considered as an imaging biomarker of small vessel disease, but its effect on cognitive decline in PD is yet to be investigated.Objective: The objective of this study was to evaluate whether PVS can independently predict cognitive decline in PD.Methods: A total of 271 PD patients were divided into 106 patients with intact cognition (PD‐IC) and 165 patients with mild cognitive impairment (PD‐MCI). After a mean follow‐up of 5.0 ± 2.3 years, 18 PD‐IC patients showed cognitive decline to PD‐MCI and 34 PD‐MCI patients showed cognitive decline to dementia. PVS was rated in the basal ganglia (BG) and centrum semiovale using a 4‐point visual scale and then classified as high (score ≥ 2) or low (score < 2) according to severity. Lacunes and white matter hyperintensity severity were also assessed. Independent risk factors for cognitive decline were investigated using multivariable logistic regression analysis.Results: In all patients, higher BG‐PVS and white matter hyperintensity severity, higher levodopa‐equivalent dose, hypertension, and lower Mini‐Mental State Examination score were independent positive predictors of future cognitive decline. In the PD‐IC subgroup, higher BG‐PVS severity, hypertension, and more severe depressive symptoms were predictors of cognitive conversion. In the PD‐MCI subgroup, higher BG‐PVS and white matter hyperintensity severity, and lower Mini‐Mental State Examination score were predictors of cognitive decline.Conclusions: BG‐PVS may be a useful imaging marker for predicting cognitive decline in PD. © 2019 International Parkinson and Movement Disorder Society

To assess whether artificial intelligence (AI)-based decision support allows more reproducible and standardized assessment of treatment response on MRI in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden using the Response Assessment in Neuro-Oncology (RANO) criteria. A series of 30 patients (15 lower-grade gliomas, 15 glioblastoma) with availability of consecutive MRI scans was selected. The time to progression (TTP) on MRI was separately evaluated for each patient by 15 investigators over two rounds. In the first round the TTP was evaluated based on the RANO criteria, whereas in the second round the TTP was evaluated by incorporating additional information from AI-enhanced MRI sequences depicting the longitudinal changes in tumor volumes. The agreement of the TTP measurements between investigators was evaluated using concordance correlation coefficients (CCC) with confidence intervals (CI) and P-values obtained using bootstrap resampling. The CCC of TTP-measurements between investigators was 0.77 (95% CI = 0.69,0.88) with RANO alone and increased to 0.91 (95% CI = 0.82,0.95) with AI-based decision support (P = .005). This effect was significantly greater (P = .008) for patients with lower-grade gliomas (CCC = 0.70 [95% CI = 0.56,0.85] without vs. 0.90 [95% CI = 0.76,0.95] with AI-based decision support) as compared to glioblastoma (CCC = 0.83 [95% CI = 0.75,0.92] without vs. 0.86 [95% CI = 0.78,0.93] with AI-based decision support). Investigators with less years of experience judged the AI-based decision as more helpful (P = .02). AI-based decision support has the potential to yield more reproducible and standardized assessment of treatment response in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden, particularly in patients with lower-grade gliomas. A fully-functional version of this AI-based processing pipeline is provided as open-source (https://github.com/NeuroAI-HD/HD-GLIO-XNAT).