Diffusion kurtosis imaging combined with dynamic susceptibility contrast-enhanced MRI in differentiating high-grade glioma recurrence from pseudoprogression

BTK Expression Level Prediction and the High-Grade Glioma Prognosis Using Radiomic Machine Learning Models

We aimed to study whether the Bruton's tyrosine kinase (BTK) expression is correlated with the prognosis of patients with high-grade gliomas (HGGs) and predict its expression level prior to surgery, by constructing radiomic models. Clinical and gene expression data of 310 patients from The Cancer Genome Atlas (TCGA) were included for gene-based prognostic analysis. Among them, contrast-enhanced T1-weighted imaging (T1WI + C) from The Cancer Imaging Archive (TCIA) with genomic data was selected from 82 patients for radiomic models, including support vector machine (SVM) and logistic regression (LR) models. Furthermore, the nomogram incorporating radiomic signatures was constructed to evaluate its clinical efficacy. BTK was identified as an independent risk factor for HGGs through univariate and multivariate Cox regression analyses. Three radiomic features were selected to construct the SVM and LR models, and the validation set showed area under curve (AUCs) values of 0.711 (95% CI, 0.598-0.824) and 0.736 (95% CI, 0.627-0.844), respectively. The median survival times of the high Rad_score and low-Rad_score groups based on LR model were 15.53 and 23.03 months, respectively. In addition, the total risk score of each patient was used to construct a predictive nomogram, and the AUCs calculated from the corresponding time-dependent ROC curves were 0.533, 0.659, and 0.767 for 1, 3, and 5 years, respectively. BTK is an independent risk factor associated with poor prognosis in patients, and the radiomic model constructed in this study can effectively and non-invasively predict preoperative BTK expression levels and patient prognosis based on T1WI + C.

CFINet: Cross-Modality MRI Feature Interaction Network for Pseudoprogression Prediction of Glioblastoma

Pseudoprogression (PSP) is a related reaction of glioblastoma treatment, and misdiagnosis can lead to unnecessary intervention. Magnetic resonance imaging (MRI) provides cross-modality images for PSP prediction studies. However, how to effectively use the complementary information between the cross-modality MRI to improve PSP prediction is still a challenging task. To address this challenge, we propose a cross-modality feature interaction network for PSP prediction. Firstly, we propose a triple-branch multi-scale module to extract low-order feature representations and a skip-connection multi-scale module to extract high-order feature representations. Then, a cross-modality interaction module based on attention mechanism is designed to make the complementary information between cross-modality MRI fully interact. Finally, the high-order cross-modality interaction information is fed into a multi-layer perceptron to achieve the PSP prediction task. We evaluate the proposed network on a private dataset with 52 subjects from Hunan Cancer Hospital and validate it on a private dataset with 30 subjects from Xiangya Hospital. The accuracy of our proposed network on the datasets is 0.954 and 0.929, respectively, which is better than most typical convolutional neural network and interaction methods.

MR-Based Radiomics Predicts CDK6 Expression and Prognostic Value in High-grade Glioma

RATIONALE AND OBJECTIVES

This study aims to assess the prognostic value of Cyclin-dependent kinases 6 (CDK6) expression levels and establish a machine learning-based radiomics model for predicting the expression levels of CDK6 in high-grade gliomas (HGG).

MATERIALS AND METHODS

Clinical parameters and genomic data were extracted from 310 HGG patients in the Cancer Genome Atlas (TCGA) database and 27 patients in the Repository of Molecular Brain Neoplasia Data (REMBRANDT) database. Univariate and multivariate Cox regression, as well as Kaplan-Meier analysis, were performed for prognosis analysis. The correlation between immune cell Infiltration with CDK6 was assessed using spearman correlation analysis. Radiomic features were extracted from contrast-enhanced magnetic resonance imaging (CE-MRI) in the Cancer Imaging Archive (TCIA) database (n = 82) and REMBRANDT database (n = 27). Logistic regression (LR) and support vector machine (SVM) were employed to establish the radiomics model for predicting CDK6 expression. Receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) were utilized to assess the predictive performance of the radiomics model. Generate radiomic scores (RS) based on the LR model. An RS-based nomogram was constructed to predict the prognosis of HGG.

RESULTS

CDK6 was significantly overexpressed in HGG tissues and was related to lower overall survival. A significant elevation in infiltrating M0 macrophages was observed in the CDK6 high group (P < 0.001). The LR radiomics model for the prediction of CDK6 expression levels (AUC=0.810 in the training cohort, AUC = 0.784 after cross-validation, AUC=0.750 in the testing cohort) was established utilizing three radiomic features. The predictive efficiencies of the RS-based nomogram, as measured by AUC, were 0.769 for 1-year, 0.815 for 3-year, and 0.780 for 5-year, respectively.

CONCLUSION

The expression level of CDK6 can impact the prognosis of patients with HGG. The expression level of HGG can be noninvasively prognosticated utilizing a radiomics model.

Dynamic Susceptibility Contrast-Enhanced Perfusion-Weighted Imaging in Differentiation Between Recurrence and Pseudoprogression in High-Grade Glioma: A Meta-analysis

INTRODUCTION

In glioma patients that have undergone surgical tumor resection, the ability to reliably distinguish between pseudoprogression (PsP) and a recurrent tumor (RT) is of key clinical importance. Accordingly, this meta-analysis evaluated the utility of dynamic susceptibility contrast-enhanced perfusion-weighted imaging as a means of distinguishing between PsP and RT when analyzing patients with high-grade glioma.

MATERIALS AND METHODS

The PubMed, Web of Science, and Wanfang databases were searched for relevant studies. Pooled analyses of sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) values were conducted, after which the area under the curve (AUC) for summary receiver operating characteristic curves was computed.

RESULTS

This meta-analysis ultimately included 21 studies enrolling 879 patients with 888 lesions. Cerebral blood volume-associated diagnostic results were reported in 20 of the analyzed studies, and the respective pooled sensitivity, specificity, PLR, and NLR values were 86% (95% confidence interval [CI], 0.81-0.89), 83% (95% CI, 0.77-0.87), 4.94 (95% CI, 3.61-6.75), and 0.18 (95% CI, 0.13-0.23) for these 20 studies. The corresponding AUC value was 0.91 (95% CI, 0.88-0.93), and the publication bias risk was low ( P = 0.976). Cerebral blood flow-related diagnostic results were additionally reported in 6 of the analyzed studies, with respective pooled sensitivity, specificity, PLR, and NLR values of 85% (95% CI, 0.78-0.90), 85% (95% CI, 0.76-0.91), 5.54 (95% CI, 3.40-9.01), and 0.18 (95% CI, 0.12-0.26). The corresponding AUC value was 0.92 (95% CI, 0.89-0.94), and the publication bias risk was low ( P = 0.373).

CONCLUSIONS

The present meta-analysis results suggest that dynamic susceptibility contrast-enhanced perfusion-weighted imaging represents an effective diagnostic approach to distinguishing between PsP and RT in high-grade glioma patients.

MR Perfusion Imaging for Gliomas

Accurate diagnosis and treatment evaluation of patients with gliomas is imperative to make clinical decisions. Multiparametric MR perfusion imaging reveals physiologic features of gliomas that can help classify them according to their histologic and molecular features as well as distinguish them from other neoplastic and nonneoplastic entities. It is also helpful in distinguishing tumor recurrence or progression from radiation necrosis, pseudoprogression, and pseudoresponse, which is difficult with conventional MR imaging. This review provides an update on MR perfusion imaging for the diagnosis and treatment monitoring of patients with gliomas following standard-of-care chemoradiation therapy and other treatment regimens such as immunotherapy.

Tumor Progression and Treatment-Related Changes: Radiological Diagnosis Challenges for the Evaluation of Post Treated Glioma

Simple Summary

Glioma is the most common primary malignant tumor of the adult central nervous system. Despite aggressive multimodal treatment, its prognosis remains poor. During follow-up, it remains challenging to distinguish treatment-related changes from tumor progression in treated patients with gliomas due to both share clinical symptoms and morphological imaging characteristics (with new and/or increasing enhancing mass lesions). The early effective identification of tumor progression and treatment-related changes is of great significance for the prognosis and treatment of gliomas. We believe that advanced neuroimaging techniques can provide additional information for distinguishing both at an early stage. In this article, we focus on the research of magnetic resonance imaging technology and artificial intelligence in tumor progression and treatment-related changes. Finally, it provides new ideas and insights for clinical diagnosis.

Abstract

As the most common neuro-epithelial tumors of the central nervous system in adults, gliomas are highly malignant and easy to recurrence, with a dismal prognosis. Imaging studies are indispensable for tracking tumor progression (TP) or treatment-related changes (TRCs). During follow-up, distinguishing TRCs from TP in treated patients with gliomas remains challenging as both share similar clinical symptoms and morphological imaging characteristics (with new and/or increasing enhancing mass lesions) and fulfill criteria for progression. Thus, the early identification of TP and TRCs is of great significance for determining the prognosis and treatment. Histopathological biopsy is currently the gold standard for TP and TRC diagnosis. However, the invasive nature of this technique limits its clinical application. Advanced imaging methods (e.g., diffusion magnetic resonance imaging (MRI), perfusion MRI, magnetic resonance spectroscopy (MRS), positron emission tomography (PET), amide proton transfer (APT) and artificial intelligence (AI)) provide a non-invasive and feasible technical means for identifying of TP and TRCs at an early stage, which have recently become research hotspots. This paper reviews the current research on using the abovementioned advanced imaging methods to identify TP and TRCs of gliomas. First, the review focuses on the pathological changes of the two entities to establish a theoretical basis for imaging identification. Then, it elaborates on the application of different imaging techniques and AI in identifying the two entities. Finally, the current challenges and future prospects of these techniques and methods are discussed.

Discriminators of pseudoprogression and true progression in high-grade gliomas: A systematic review and meta-analysis

High-grade gliomas remain the most common primary brain tumour with limited treatments options and early recurrence rates following adjuvant treatments. However, differentiating true tumour progression (TTP) from treatment-related effects or pseudoprogression (PsP), may critically influence subsequent management options. Structural MRI is routinely employed to evaluate treatment responses, but misdiagnosis of TTP or PsP may lead to continuation of ineffective or premature cessation of effective treatments, respectively. A systematic review and meta-analysis were conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses method. Embase, MEDLINE, Web of Science and Google Scholar were searched for methods applied to differentiate PsP and TTP, and studies were selected using pre-specified eligibility criteria. The sensitivity and specificity of included studies were summarised. Three of the identified methods were compared in a separate subgroup meta-analysis. Thirty studies assessing seven distinct neuroimaging methods in 1372 patients were included in the systematic review. The highest performing methods in the subgroup analysis were DWI (AUC = 0.93 [0.91-0.95]) and DSC-MRI (AUC = 0.93 [0.90-0.95]), compared to DCE-MRI (AUC = 0.90 [0.87-0.93]). 18F-fluoroethyltyrosine PET (18F-FET PET) and amide proton transfer-weighted MRI (APTw-MRI) also showed high diagnostic accuracy, but results were based on few low-powered studies. Both DWI and DSC-MRI performed with high sensitivity and specificity for differentiating PsP from TTP. Considering the technical parameters and feasibility of each identified method, the authors suggested that, at present, DSC-MRI technique holds the most clinical potential.

Effect of 3D Slicer Preoperative Planning and Intraoperative Guidance with Mobile Phone Virtual Reality Technology on Brain Glioma Surgery

Objective

To explore the effect of 3D Slicer preoperative planning and intraoperative guidance with mobile phone virtual reality (VR) technology on brain glioma surgery.

Methods

By means of retrospective study, the data of 77 brain glioma patients treated in the neurosurgery departments at The Second Affiliated Hospital of Wannan Medical College and Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine from January 2015 to January 2022 were analyzed, and the patients were divided into the experimental group (EG, n = 38) and the control group (CG, n = 39) according to the surgical modalities. Before surgery, all patients received positron emission tomography-computed tomography (PET/CT) scanning and magnetic resonance imaging (MRI) examination. For patients in EG, the DICOM format images acquired from PET-CT and MRI examinations were imported with the 3D Slicer software for 3D visual fusion reconstruction, acquiring VR images, and developing detailed preoperative planning. Then, the reconstructed images were imported into the Sina software on a mobile phone, and the surgery was performed with the assistance of VR technology; for patients in CG, traditional 2D images were used for tumor contour drawing by the subjective visual method, and the craniotomy was performed under a traditional microscope. Patients' surgery indicators and Karnofsky Performance Scale (KPS) scores were compared between the two groups.

Results

The number of cases with total resection, rate of total resection, hospital stay after surgery, and surgery time were significantly better in EG than in CG (P < 0.05); after treatment, the KPS score was significantly higher in EG than in CG (75.66 ± 4.01 vs 65.36 ± 5.23, P < 0.001).

Conclusion

Combining 3D Slicer preoperative planning with intraoperative mobile phone VR technology can promote the accuracy of brain glioma surgery, which is conducive to effectively removing tumors while protecting patients' neural function.