Visualization of heterogeneity and regional grading of gliomas by multiple features using magnetic resonance-based clustered images

Voxel-based clustered imaging by multiparameter diffusion tensor images for predicting the grade and proliferative activity of meningioma

INTRODUCTION

Meningiomas are the most common primary central nervous system tumors. Predicting the grade and proliferative activity of meningiomas would influence therapeutic strategies. We aimed to apply the multiple parameters from preoperative diffusion tensor images for predicting meningioma grade and proliferative activity.

METHODS

Nineteen patients with low-grade meningiomas and eight with high-grade meningiomas were included. For the prediction of proliferative activity, the patients were divided into two groups: Ki-67 monoclonal antibody labeling index (MIB-1 LI) < 5% (lower MIB-1 LI group; n = 18) and MIB-1 LI ≥ 5% (higher MIB-1 LI group; n = 9). Six features, diffusion-weighted imaging, fractional anisotropy, mean, axial, and radial diffusivities, and raw T2 signal with no diffusion weighting, were extracted as multiple parameters from diffusion tensor imaging. The two-level clustering approach for a self-organizing map followed by the K-means algorithm was applied to cluster a large number of input vectors with the six features. We also validated whether the diffusion tensor-based clustered image (DTcI) was helpful for predicting preoperative meningioma grade or proliferative activity.

RESULTS

The sensitivity, specificity, accuracy, and area under the curve of receiver operating characteristic curves from the 16-class DTcIs for differentiating high- and low-grade meningiomas were 0.870, 0.901, 0.891, and 0.959, and those from the 10-class DTcIs for differentiating higher and lower MIB-1 LIs were 0.508, 0.770, 0.683, and 0.694, respectively. The log-ratio values of class numbers 13, 14, 15, and 16 were significantly higher in high-grade meningiomas than in low-grade meningiomas (p < .001). With regard to MIB-1 LIs, the log-ratio values of class numbers 8, 9, and 10 were higher in meningiomas with higher MIB-1 groups (p < .05).

CONCLUSION

The multiple diffusion tensor imaging-based parameters from the voxel-based DTcIs can help differentiate between low- and high-grade meningiomas and between lower and higher proliferative activities.

Quantitative susceptibility mapping evaluation of glioma

OBJECTIVES

To comprehensively evaluate the glioma using quantitative susceptibility mapping (QSM).

MATERIALS AND METHODS

Forty-two patients (18 women; mean age, 45 years) with pathologically confirmed gliomas were retrospectively included. All the patients underwent conventional and advanced MRI examinations (QSM, DWI, MRS, etc.). Five patients underwent paired QSM (pre- and post-enhancement). Four Visually Accessible Rembrandt Image (VASARI) features and intratumoural susceptibility signal (ITSS) were observed. Three ROIs each were manually drawn separately in the tumour parenchyma with relatively high and low magnetic susceptibility. The association between the tumour's magnetic susceptibility and other MRI parameters was also analysed.

RESULTS

Morphologically, gliomas with heterogeneous ITSS were more similar to high-grade gliomas (p = 0.006, AUC: 0.72, sensitivity: 70%, and specificity: 73%). Heterogeneous ITSS was significantly associated with tumour haemorrhage, necrosis, diffusion restriction, and avid enhancement but did not change between pre- and post-enhanced QSM. Quantitatively, tumour parenchyma magnetic susceptibility had limited value in grading gliomas and identifying IDH mutation status, whereas the relatively low magnetic susceptibility of the tumour parenchyma helped identify oligodendrogliomas in IDH mutated gliomas (AUC = 0.78) with high specificity (100%). The relatively high tumour magnetic susceptibility significantly increased after enhancement (p = 0.039). Additionally, we found that the magnetic susceptibility of the tumour parenchyma was significantly correlated with ADC (r = 0.61) and Cho/NAA (r = 0.40).

CONCLUSIONS

QSM is a promising candidate for the comprehensive evaluation of gliomas, except for IDH mutation status. The magnetic susceptibility of tumour parenchyma may be affected by tumour cell proliferation.

KEY POINTS

• Morphologically, gliomas with a heterogeneous intratumoural susceptibility signal (ITSS) are more similar to high-grade gliomas (p = 0.006; AUC, 0.72; sensitivity, 70%; and specificity, 73%). Heterogeneous ITSS was significantly associated with tumour haemorrhage, necrosis, diffusion restriction, and avid enhancement but did not change between pre- and post-enhanced QSM. • Tumour parenchyma's relatively low magnetic susceptibility helped identify oligodendroglioma with high specificity. • Tumour parenchyma magnetic susceptibility was significantly correlated with ADC (r = 0.61) and Cho/NAA (r = 0.40).

Visualization of tumor heterogeneity and prediction of isocitrate dehydrogenase mutation status for human gliomas using multiparametric physiologic and metabolic MRI

This study aimed to differentiate isocitrate dehydrogenase (IDH) mutation status with the voxel-wise clustering method of multiparametric magnetic resonance imaging (MRI) and to discover biological underpinnings of the clusters. A total of 69 patients with treatment-naïve diffuse glioma were scanned with pH-sensitive amine chemical exchange saturation transfer MRI, diffusion-weighted imaging, fluid-attenuated inversion recovery, and contrast-enhanced T1-weighted imaging at 3 T. An unsupervised two-level clustering approach was used for feature extraction from acquired images. The logarithmic ratio of the labels in each class within tumor regions was applied to a support vector machine to differentiate IDH status. The highest performance to predict IDH mutation status was found for 10-class clustering, with a mean area under the curve, accuracy, sensitivity, and specificity of 0.94, 0.91, 0.90, and 0.91, respectively. Targeted biopsies revealed that the tissues with labels 7-10 showed high expression levels of hypoxia-inducible factor 1-alpha, glucose transporter 3, and hexokinase 2, which are typical of IDH wild-type glioma, whereas those with labels 1 showed low expression of these proteins. In conclusion, A machine learning model successfully predicted the IDH mutation status of gliomas, and the resulting clusters properly reflected the metabolic status of the tumors.

Differentiating IDH status in human gliomas using machine learning and multiparametric MR/PET

Background

The purpose of this study was to develop a voxel-wise clustering method of multiparametric magnetic resonance imaging (MRI) and 3,4-dihydroxy-6-[¹⁸F]-fluoro-L-phenylalanine (FDOPA) positron emission tomography (PET) images using an unsupervised, two-level clustering approach followed by support vector machine in order to classify the isocitrate dehydrogenase (IDH) status of gliomas.

Methods

Sixty-two treatment-naïve glioma patients who underwent FDOPA PET and MRI were retrospectively included. Contrast enhanced T1-weighted images, T2-weighted images, fluid-attenuated inversion recovery images, apparent diffusion coefficient maps, and relative cerebral blood volume maps, and FDOPA PET images were used for voxel-wise feature extraction. An unsupervised two-level clustering approach, including a self-organizing map followed by the K-means algorithm was used, and each class label was applied to the original images. The logarithmic ratio of labels in each class within tumor regions was applied to a support vector machine to differentiate IDH mutation status. The area under the curve (AUC) of receiver operating characteristic curves, accuracy, and F1-socore were calculated and used as metrics for performance.

Results

The associations of multiparametric imaging values in each cluster were successfully visualized. Multiparametric images with 16-class clustering revealed the highest classification performance to differentiate IDH status with the AUC, accuracy, and F1-score of 0.81, 0.76, and 0.76, respectively.

Conclusions

Machine learning using an unsupervised two-level clustering approach followed by a support vector machine classified the IDH mutation status of gliomas, and visualized voxel-wise features from multiparametric MRI and FDOPA PET images. Unsupervised clustered features may improve the understanding of prioritizing multiparametric imaging for classifying IDH status.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-021-00396-5.

Tumor Heterogeneity in Glioblastomas: From Light Microscopy to Molecular Pathology

One of the main reasons for the aggressive behavior of glioblastoma (GBM) is its intrinsic intra-tumor heterogeneity, characterized by the presence of clonal and subclonal differentiated tumor cell populations, glioma stem cells, and components of the tumor microenvironment, which affect multiple hallmark cellular functions in cancer. "Tumor Heterogeneity" usually encompasses both inter-tumor heterogeneity (population-level differences); and intra-tumor heterogeneity (differences within individual tumors). Tumor heterogeneity may be assessed in a single time point (spatial heterogeneity) or along the clinical evolution of GBM (longitudinal heterogeneity). Molecular methods may detect clonal and subclonal alterations to describe tumor evolution, even when samples from multiple areas are collected in the same time point (spatial-temporal heterogeneity). In GBM, although the inter-tumor mutational landscape is relatively homogeneous, intra-tumor heterogeneity is a striking feature of this tumor. In this review, we will address briefly the inter-tumor heterogeneity of the CNS tumors that yielded the current glioma classification. Next, we will take a deeper dive in the intra-tumor heterogeneity of GBMs, which directly affects prognosis and response to treatment. Our approach aims to follow technological developments, allowing for characterization of intra-tumor heterogeneity, beginning with differences on histomorphology of GBM and ending with molecular alterations observed at single-cell level.

Multi-parametric MR Imaging Biomarkers Associated to Clinical Outcomes in Gliomas: A Systematic Review

PURPOSE

To systematically review evidence regarding the association of multiparametric biomarkers with clinical outcomes and their capacity to explain relevant subcompartments of gliomas.

MATERIALS AND METHODS

Scopus database was searched for original journal papers from January 1st, 2007 to February 20th, 2017 according to PRISMA. Four hundred forty-nine abstracts of papers were reviewed and scored independently by two out of six authors. Based on those papers we analyzed associations between biomarkers, subcompartments within the tumor lesion, and clinical outcomes. From all the articles analyzed, the twenty-seven papers with the highest scores were highlighted to represent the evidence about MR imaging biomarkers associated with clinical outcomes. Similarly, eighteen studies defining subcompartments within the tumor region were also highlighted to represent the evidence of MR imaging biomarkers. Their reports were critically appraised according to the QUADAS-2 criteria.

RESULTS

It has been demonstrated that multi-parametric biomarkers are prepared for surrogating diagnosis, grading, segmentation, overall survival, progression-free survival, recurrence, molecular profiling and response to treatment in gliomas. Quantifications and radiomics features obtained from morphological exams (T1, T2, FLAIR, T1c), PWI (including DSC and DCE), diffusion (DWI, DTI) and chemical shift imaging (CSI) are the preferred MR biomarkers associated to clinical outcomes. Subcompartments relative to the peritumoral region, invasion, infiltration, proliferation, mass effect and pseudo flush, relapse compartments, gross tumor volumes, and highrisk regions have been defined to characterize the heterogeneity. For the majority of pairwise cooccurrences, we found no evidence to assert that observed co-occurrences were significantly different from their expected co-occurrences (Binomial test with False Discovery Rate correction, α=0.05). The co-occurrence among terms in the studied papers was found to be driven by their individual prevalence and trends in the literature.

CONCLUSION

Combinations of MR imaging biomarkers from morphological, PWI, DWI and CSI exams have demonstrated their capability to predict clinical outcomes in different management moments of gliomas. Whereas morphologic-derived compartments have been mostly studied during the last ten years, new multi-parametric MRI approaches have also been proposed to discover specific subcompartments of the tumors. MR biomarkers from those subcompartments show the local behavior within the heterogeneous tumor and may quantify the prognosis and response to treatment of gliomas.

Lower Grade Gliomas: Relationships Between Metabolic and Structural Imaging with Grading and Molecular Factors

BACKGROUND

Positron emission tomography (PET) is a valuable tool for the characterization of brain tumors in vivo. However, few studies have investigated the correlation between carbon-11-methionine (11C-METH) PET metrics and the clinical, radiological, histological, and molecular features of patients affected by lower grade gliomas (LGGs). The present observational study evaluated the relationships between 11C-METH PET metrics and structural magnetic resonance imaging (MRI) findings with the histomolecular biomarkers in patients with LGGs who were candidates for surgery.

METHODS

We enrolled 96 patients with pathologically proven LGG (51 men, 45 women; age 44.1 ± 13.7 years; 45 with grade II, 51 with grade III), who had been referred from March 2012 to January 2015 for tumor resection and had undergone preoperative 11C-METH PET. The semiquantitative metrics for 11C-METH PET included maximum standardized uptake value (SUVmax), SUV ratio to normal brain, and metabolic tumor burden (MTB). The PET semiquantitative metrics were analyzed and compared with the MRI features, histological diagnosis, isocitrate dehydrogenase-1/2 status, and 1p/19q codeletion.

RESULTS

Histological grade was associated with SUVmax (P = 0.002), SUV ratio (P = 0.011), and MTB (P = 0.001), with grade III lesions showing higher values. Among the nonenhancing lesions on MRI, SUVmax (P = 0.001), SUV ratio (P = 0.003) and MTB (P < 0.001) were significantly different statistically for grade II versus grade III. The MRI lesion volume correlated poorly with MTB (r² = 0.13). The SUVmax and SUV ratio were greater (P < 0.05) in isocitrate dehydrogenase-1/2 wild-type lesions, and the SUV ratio was associated with the presence of the 1p19q codeletion.

CONCLUSIONS

The 11C-METH PET metrics correlated significantly with histological grade and the molecular profile. Semiquantitative PET metrics can improve the preoperative evaluation of LGGs and thus support clinical decision-making.

A review and outlook on visual analytics for uncertainties in functional magnetic resonance imaging

Analysis of functional magnetic resonance imaging (fMRI) plays a pivotal role in uncovering an understanding of the brain. fMRI data contain both spatial volume and temporal signal information, which provide a depiction of brain activity. The analysis pipeline, however, is hampered by numerous uncertainties in many of the steps; often seen as one of the last hurdles for the domain. In this review, we categorise fMRI research into three pipeline phases: (i) image acquisition and processing; (ii) image analysis; and (iii) visualisation and human interpretation, to explore the uncertainties that arise in each phase, including the compound effects due to the inter-dependence of steps. Attempts at mitigating uncertainties rely on providing interactive visual analytics that aid users in understanding the effects of the uncertainties and adjusting their analyses. This impetus for visual analytics comes in light of considerable research investigating uncertainty throughout the pipeline. However, to the best of our knowledge, there is yet to be a comprehensive review on the importance and utility of uncertainty visual analytics (UVA) in addressing fMRI concerns, which we term fMRI-UVA. Such techniques have been broadly implemented in related biomedical fields, and its potential for fMRI has recently been explored; however, these attempts are limited in their scope and utility, primarily focussing on addressing small parts of single pipeline phases. Our comprehensive review of the fMRI uncertainties from the perspective of visual analytics addresses the three identified phases in the pipeline. We also discuss the two interrelated approaches for future research opportunities for fMRI-UVA.

Clustering approach to identify intratumour heterogeneity combining FDG PET and diffusion-weighted MRI in lung adenocarcinoma

OBJECTIVES

Malignant tumours consist of biologically heterogeneous components; identifying and stratifying those various subregions is an important research topic. We aimed to show the effectiveness of an intratumour partitioning method using clustering to identify highly aggressive tumour subregions, determining prognosis based on pre-treatment PET and DWI in stage IV lung adenocarcinoma.

METHODS

Eighteen patients who underwent both baseline PET and DWI were recruited. Pre-treatment imaging of SUV and ADC values were used to form intensity vectors within manually specified ROIs. We applied k-means clustering to intensity vectors to yield distinct subregions, then chose the subregion that best matched the criteria for high SUV and low ADC to identify tumour subregions with high aggressiveness. We stratified patients into high- and low-risk groups based on subregion volume with high aggressiveness and conducted survival analyses. This approach is referred to as the partitioning approach. For comparison, we computed tumour subregions with high aggressiveness without clustering and repeated the described procedure; this is referred to as the voxel-wise approach.

RESULTS

The partitioning approach led to high-risk (median SUVmax = 14.25 and median ADC = 1.26x10^-3 mm²/s) and low-risk (median SUVmax = 14.64 and median ADC = 1.09x10^-3 mm²/s) subgroups. Our partitioning approach identified significant differences in survival between high- and low-risk subgroups (hazard ratio, 4.062, 95% confidence interval, 1.21 - 13.58, p-value: 0.035). The voxel-wise approach did not identify significant differences in survival between high- and low-risk subgroups (p-value: 0.325).

CONCLUSION

Our partitioning approach identified intratumour subregions that were predictors of survival.

KEY POINTS

• Multimodal imaging of PET and DWI is useful for assessing intratumour heterogeneity. • Data-driven clustering identified subregions which might be highly aggressive for lung adenocarcinoma. • The data-driven partitioning results might be predictors of survival.

Imaging in neuro-oncology

Imaging plays several key roles in managing brain tumors, including diagnosis, prognosis, and treatment response assessment. Ongoing challenges remain as new therapies emerge and there are urgent needs to find accurate and clinically feasible methods to noninvasively evaluate brain tumors before and after treatment. This review aims to provide an overview of several advanced imaging modalities including magnetic resonance imaging and positron emission tomography (PET), including advances in new PET agents, and summarize several key areas of their applications, including improving the accuracy of diagnosis and addressing the challenging clinical problems such as evaluation of pseudoprogression and anti-angiogenic therapy, and rising challenges of imaging with immunotherapy.

An Update on the Approach to the Imaging of Brain Tumors

PURPOSE OF REVIEW

Neuroimaging plays a critical role in diagnosis of brain tumors and in assessment of response to therapy. However, challenges remain, including accurately and reproducibly assessing response to therapy, defining endpoints for neuro-oncology trials, providing prognostic information, and differentiating progressive disease from post-therapeutic changes particularly in the setting of antiangiogenic and other novel therapies.

RECENT FINDINGS

Recent advances in the imaging of brain tumors include application of advanced MRI imaging techniques to assess tumor response to therapy and analysis of imaging features correlating to molecular markers, grade, and prognosis. This review aims to summarize recent advances in imaging as applied to current diagnostic and therapeutic neuro-oncologic challenges.

Distinct Patterns of Cerebral Cortical Thinning in Schizophrenia: A Neuroimaging Data-Driven Approach

Schizophrenia is an etiologically and clinically heterogeneous disorder. Although neuroimaging studies have revealed brain alterations in schizophrenia, most studies have assumed that the disorder is a single entity, neglecting the diversity of alterations observed in the disorder. The current study sought to explore the distinct patterns of altered cortical thickness in patients with schizophrenia and healthy individuals using a data-driven approach. Unsupervised clustering using self-organizing maps followed by a K-means algorithm was applied to regional cortical thickness data in 108 schizophrenia patients and 121 healthy controls. After clustering, the clinical characteristics and cortical thickness patterns of each cluster were assessed. Unsupervised clustering revealed that a 6-cluster solution was the most appropriate in this sample. There was substantial overlap between the patterns of cortical thickness in schizophrenia patients and healthy controls, although the distributions of the patients and controls differed across the clusters. The patterns of altered cortical thickness in schizophrenia exhibited cluster-specific features; patients within a cluster exhibited the most extensive cortical thinning, particularly in the medial prefrontal and temporal regions, while those in other clusters exhibited reduced cortical thickness in the medial frontal region or temporal lobe. Furthermore, in the schizophrenia group, extensive cortical thinning was correlated with a higher dosage of antipsychotic medication, while preserved cortical thickness appeared to be linked to less negative symptoms. This data-driven neuroimaging approach revealed distinct patterns of cortical thinning in schizophrenia, possibly reflecting the etiological heterogeneity of the disorder.