Keywords: Tumors (Pre-Treatment), Machine Learning/Artificial Intelligence

Motivation: There is a need for preoperative identification of isocitrate dehydrogenase (IDH) mutation in gliomas, currently reliant on invasive procedures.

Goal(s): Identify IDH mutation status using susceptibility weighted MRI (SWI) and explainable artificial intelligence.

Approach: The SWI signal drop areas within the tumor region were compared between 98 IDH-mutant (IDH-mut) and 91 IDH wild-type (IDH-wt) gliomas using a convolutional neural network (CNN) and gradient-weighted class activation map (Grad-CAM).

Results: IDH-wt gliomas had larger SWI signal drop areas than IDH-mut. CNN resulted in an area under curve (AUC) of 0.84±0.05 for classification, and Grad-CAM highlighted the signal dropout areas.

Impact: IDH-wt gliomas had higher neovascularization on SWI than IDH-mut gliomas, potentially linked to their more aggressive nature. Grad-CAM highlighted dark areas on SWI, and a CNN architecture classified the IDH mutational subgroups with an AUC of 0.84.

Keywords: Tumors (Pre-Treatment), Brain Connectivity

Motivation: Alterations in the functional connectome may serve as new biomarkers to infer the disease profile of glioma.

Goal(s): To detect the pathological functional connectome (Patho-FCN) that characterizes the functional plasticity due to low grade glioma.

Approach: Dynamic functional connectivity-based graph convolutional network (dFC-GCN) models were constructed to distinguish patients from healthy controls. Class activation mapping was utilized to identify the top 5% salient nodes constituting the Patho-FCN, where the information flow was assessed using the time-delay and probabilistic flow estimation.

Results: The dFC-GCN model identified a contralesional Patho-FCN with altered information propagation patterns, and achieved an averaged classification accuracy of 96.1%.

Impact: The pathological functional connectome detected with the proposed methodology in this study provides a novel biomarker to characterize cerebral glioma. Theranostic scheme targeting pathological connectome may innovate the management of glioma.

Keywords: Tumors (Pre-Treatment), Cancer

Motivation: Accurate classification of multi-type brain tumours through in vivo proton magnetic resonance spectroscopy remains a significant challenge. Conventional machine learning classifiers consider all reliably observed metabolites as features and classify all brain tumours simultaneously, but their performance is limited for rare tumour types.

Goal(s): This abstract presents a novel multi-layer classification model, binary adaptive metabolite selection (BAMS), for better identifying rare tumour types.

Approach: BAMS generalises the problem by considering only one specific brain tumour type and selecting significant biomarkers in each layer iteratively and dynamically.

Results: In comparison to classic models, BAMS showed significantly improved diagnostic performance for rare brain tumour types.

Impact: A brain tumour classification method that can only work on main types and cannot determine rare types is unlikely to be useful for clinicians. This abstract introduces BAMS that can significantly improve diagnostic performance for rare brain tumour types.

Keywords: Tumors (Pre-Treatment), Brain

Motivation: Preoperative glioma classification and management is still a challenge to be solved.

Goal(s): To enhance the understanding of glioma characteristics and potentially improve patient outcomes, we analyzed 7T Magnetic Resonance Spectroscopic Imaging (MRSI) data in 36 glioma patients.

Approach: Our approach focused on k-Means clustering of 60 metabolic ratios in the tumor to identify an overlap with the WHO 2021 diagnosis. Important metabolic ratios identified include Glu+Gln/tCho and Ins/tCr ratios, highlighting their biomarker significance. 

Results: Our 7T MRSI can add metabolic profiles across the entire glioma and brain, possibly contributing to future glioma research.

Impact: We performed k-Means clustering of preoperative 7T MRSI metabolic ratios in 36 glioma patients. Correlation with histological WHO 2021 diagnosis was identified. With this approach, we could potentially enhance surgery planning and optimize glioma treatment and targeted drug  monitoring.

Keywords: Tumors (Pre-Treatment), Brain

Motivation: IDH-mutant diffuse adult type gliomas almost invariably lead to fatality. The INDIGO trial found vorasidenib significantly improving progression-free survival in non-contrast enhancing IDH mutant CNS grade 2 glioma patients.

Goal(s): The purpose of this study was to non-invasively predict both contrast enhancement and IDH mutation in glioma patients.

Approach: We employed a machine learning approach on 7T MRSI data to forecast IDH mutation status and contrast-enhancing tumor tissue in adult diffuse gliomas.

Results: Our models performed well in the training and the testing set (AUC ≥ 0.8) for both, IDH mutation and contrast enhancement prediction.

Impact: With regard to emerging IDH inhibition therapies in IDH mutant non-contrast enhancing diffuse gliomas, non-invasive prediction of IDH mutation status and contrast enhancement are of utmost importance for glioma patients. 7T MRSI can be successfully applied to this task.

Keywords: Tumors (Pre-Treatment), Tumor

Motivation: Noninvasive identification of malignant regions in glioma can help guide diagnosis and subsequent treatment planning.

Goal(s): This study aims to create models to predict and elucidate limitations in radiopathomic mapping of invasiveness in glioma using multiparametric physiologic and metabolic MRI.

Approach: A large, unique multiparametric MRI dataset with tissue is leveraged to compare various machine learning models of %ki-67 and cellularity (cells/mm²). 

Results: : The best binary model achieved a CV-AUC =0.82 and CV-AUC = 0.75 for a binarized ki-67 and cellularity. Best ki-67 continuous predictions were in the 10-fold CV SVM and 4-fold ensemble model for continuous cellularity.

Impact: Multiparametric MRI can non-invasively predict histopathology. Including physiologic and/or metabolic MRI boosts histopathological predictions, however performance is also impacted by standardization of data quality.

Keywords: Tumors (Pre-Treatment), Machine Learning/Artificial Intelligence

Motivation: Molecular markers, like neurofibromatosis type-2 (NF-2) mutations, highly impact patient outcomes in meningiomas, but they could only be assessed in excised tissue.

Goal(s): To develop a non-invasive approach for preoperatively identifying NF-2 mutations using susceptibility-weighted MRI (SWI) with radiomics and deep learning.

Approach: Preoperative SWI of 92 meningiomas with NF-2 status data were analyzed. Radiomics and deep learning were used to extract features of SWI, which were classified using traditional machine learning.

Results: Reduced tumor signal intensity, "en plaque" growth pattern, and intratumoral calcification were markers of NF2 mutation, which was identified with an accuracy of 74%.

Impact: This study employed SWI to predict NF-2 mutation through radiomics and deep learning features with 74% accuracy. Preoperative identification of NF-2 mutations might allow for personalized treatment planning resulting in better patient outcomes.

Keywords: Tumors (Pre-Treatment), Neuro, MR value, AI & Machine Learning

Motivation: Deep learning (DL)-enabled reconstruction has emerged as a promising approach to accelerate MRI exams; however, the performance of DL-accelerated 3D sequences for the detection of intracranial enhancing lesions has not been clinically investigated.
 

Goal(s): To evaluate post-contrast DL-accelerated 3D-T1-MPRAGE compared to state-of-the-art Wave-CAIPI accelerated 3D T1-MPRAGE for evaluation of intracranial enhancing lesions.

Approach: Two neuroradiologists performed head-to-head evaluation of 115 cases of post-contrast DL- vs. Wave-CAIPI-MPRAGE for visualization of dural, parenchymal, leptomeningeal, and ependymal enhancement; sharpness; noise; artifacts; and overall diagnostic quality.

Results: Highly accelerated post-contrast DL-T1-MPRAGE achieved noninferior image quality to the standard clinically validated Wave-CAIPI accelerated sequence.

Impact: Deep-learning-accelerated post-contrast 3D T1-MPRAGE demonstrates robust diagnostic quality in visualizing enhancing intracranial pathology in all compartments while maintaining similar perception of noise and artifact. DL offers a powerful approach to accelerating post-contrast 3D T1-MPRAGE for clinical and research studies.

Keywords: Tumors (Pre-Treatment), Tumor

Motivation: The usefulness of radiomics in predicting intraoperative bleeding rate remains underestimated. Our objective was to examine the potential of radiomic characteristics to predict the intraoperative bleeding rate in patients with intracranial meningiomas.

Goal(s): Как To predict intraoperative bleeding rate in patients with intracranial meningiomas using radiomics, machine learning and regression methods.

Approach: Brain 3T MRI was performed with subsequent tumor segmentation and radiomics analysis.

Results: The combination of six ADC- and ASL-based radiomics features allowed us to predict the intraoperative bleeding rate with raw residuals estimation -23 (-101; 68) (Me (1; 3 quantile)) in patients with intracranial meningiomas.

Impact: Our results provide an additional non-invasive tool for the evaluation of meningiomas, which potentially could impact the treatment tactic(for example, making a decision about performing a pre-surgicalembolization in cases with high-risk).

Keywords: Tumors (Pre-Treatment), Tumor, magnetic resonance elastography, three dimensional slip interface imaging, tumor–brain adhesion, meningioma

Motivation: The adhesion of brain tumor to brain tissue is very important to evaluate the surgical risk and prognosis of patients

Goal(s): To investigate the ability of slip interface imaging (SII), based on a recently developed technique-magnetic resonance elastography (MRE), to predict the degree of meningioma–brain adhesion

Approach: slip interface imaging (SII), based on a recently developed technique-magnetic resonance elastography (MRE)

Results: SII agreed with the intraoperative assessment of the degree of tumor adhesion (medium agreement, k=0.688, 95% CI: 0.15-1)

Impact: Preoperative non-invasive evaluation of brain tumors and the degree of adhesion around the guidance of the surgeon to assess the risk of surgery and selection of surgical methods

Keywords: Tumors (Pre-Treatment), Tumor, T2 mapping with FLAIR

Motivation: T2 mapping with FLAIR eliminates the interference of cerebrospinal fluid, depicting lesion more precise than conventional T2 mapping, but its use for grading and classifying meningiomas is scarce.

Goal(s): To investigate the value of a single-shot T2-FLAIR mapping method, inversion recovery multiple overlapping-echo detachment imaging (IR-MOLED), in distinguishing grades and subtypes of meningiomas.

Approach: IR-MOLED was applied on meningioma patients (N = 45), and histogram analysis of enhanced tumor regions was performed based on the resultant parametric maps.

Results: T2-FLAIR mapping is sensitive in determining the meningiomas grade (AUC = 0.813) and subtype (AUC = 0.971).

Impact:  IR-MOLED-based quantitative analysis is promising in differentiating high and low grades and subtypes of meningiomas, especially in patients losing body control.

Keywords: Tumors (Pre-Treatment), DSC & DCE Perfusion

Motivation: The prognostic markers of H3 K27-altered diffuse midline gliomas (DMGs) in adults have yet to be studied.

Goal(s): To investigate prognostic markers for H3 K27-altered DMGs in adults, including clinical, qualitative, quantitative imaging phenotypes, and tumor oxygenation characteristics.

Approach: Clinical, qualitative, and quantitative imaging phenotypes were analyzed in 32 adults with H3 K27-altered DMGs. Cox analyses were conducted to determine predictors of overall survival in entire patients with H3 K27-altered DMG and subgroup of contrast-enhancing (CE) tumor.

Results: The presence of LM and higher rCMRO₂ of CE tumor were independently associated with poor prognosis in adult patients with H3 K27-altered DMG.

Impact: Tumor oxygenation imaging biomarkers may provide valuable insight into the prognosis of H3 K27-altered diffuse midline gliomas, potentially reflecting higher metabolic activity in the tumor microenvironment.

Keywords: Tumors (Pre-Treatment), Quantitative Imaging

Motivation: The consistency of intracranial meningiomas is essential for determining the necessary surgical instruments and influencing the outcome of surgery. However, no specific feature of conventional MRI is reliable in predicting the meningiomas consistency.

Goal(s): To evaluate and compare the potential of various MRI perfusion and diffusion metrics in predicting the meningiomas consistency.

Approach: Histogram parameters of metrics obtained from DKI, DTI, ASL and DSC were included in logistic regression models to predict meningiomas consistency.

Results: DTI, ASL, and DSC metrics could significantly differentiate between soft and hard meningiomas. The DSC combined model yielded the highest AUC of 0.858.

Impact: The differentiation of soft and hard meningiomas was feasible by combining histogram parameters of DSC and DTI metrics.

Keywords: Tumors (Pre-Treatment), Tumor

Motivation: To investigate the efficacy of MRI features and CD8+ T cells in predicting risk stratification for meningioma recurrence.

Goal(s): To develop a reliable nomogram incorporating MRI features and CD8+ T cells to predict meningioma recurrence. 

Approach: Conventional MRI features, ADC histogram parameters, and CD8+ T cells were recorded and compared. This model was the first to combine clinical, imaging, and TME data to predict meningioma recurrence.

Results: The ADCp1 and CD8+ T cells as predictive variables for meningioma recurrence and patients with low ADCp1 or CD8+ T cell counts had higher recurrence rates than those with high ADCp1 or CD8+ T cell counts.

Impact: The findings will improve prognostic accuracy for patients with meningioma and potentially allow for targeted treatment of individuals who have the recurrent form. 

Keywords: Tumors (Pre-Treatment), Tumor

Motivation: Retrospective study

Goal(s): This study analyzed the general clinical features and preoperative MRI features of patients with Grade Ⅱ and Ⅲ intracranial solitary fibrous tumor (ISFT).

Approach: Intergroup comparison was conducted according to postoperative pathological grade. Binary logistic regression was performed to identify effective imaging indexes that could predict pathological grade. 

Results: There were differences between grades in tumor location; skull invasion; signal characteristics of T2-FLAIR and DWI images; and ADC_max, ADC_mean and ADC_min. ADC_min was the only effective imaging index that could predict pathological grade.

Impact: Retrospective analysis showed that preoperative ADCmin can effectively predict grade Ⅱ and Ⅲ tumors in patients with ISFT, which will provide an important reference basis for preoperative grading of ISFT.

Keywords: Tumors (Pre-Treatment), Diffusion/other diffusion imaging techniques, Meningioma, Embolization, IVIM

Motivation: Some studies have reported decreased tumor volume and blood flow after preoperative endovascular embolization in meningioma, but it remains unclear how the meningioma and peritumoral edema are altered after endovascular embolization, and a practical evaluation method has not been established.

Goal(s): We investigated IVIM analysis to evaluate perfusion and diffusion simultaneously before and after endovascular embolization in supratentorial meningioma.

Approach: We assessed IVIM parameters (FD*, F, D*, and D) before and after endovascular embolization in supratentorial meningioma.

Results: FD* and F were significantly lower after endovascular embolization in meningioma than those before the endovascular embolization.

Impact: The IVIM analysis makes it possible to evaluate perfusion and diffusion simultaneously after preoperative endovascular embolization in supratentorial meningiomas in a short time.