Citations

Abstract Nerve conduction F-wave studies contain crucial information about subclinical motor dysfunction that can be used to diagnose patients with amyotrophic lateral sclerosis (ALS). However, F-wave responses are highly variable in morphology, making waveform interpretation challenging. Artificial intelligence techniques can extract time–frequency features to provide new insights into ALS diagnosis and prognosis. A retrospective analysis was performed on F-wave responses from 46 802 patients. Discrete wavelet transforms were applied to time-series waveform responses after stimulating ulnar, median, fibular and tibial nerves. Wavelet coefficient statistics, onset age, sex and body mass index were features for training a Gradient Boosting Machine model on 40 095 patients (5329 diagnosed with motor neuron disease). Model performance was tested on responses from 689 ALS patients meeting Gold Coast criteria and 689 age- and sex-matched controls. An exploratory analysis examined model performance on cohorts of patients with inclusion body myositis, cervical radiculopathy, lumbar radiculopathy or peripheral neuropathy, which can mimic ALS symptoms. Factors affecting survival were estimated through Cox proportional hazards regression. The model trained using wavelet features on the full waveform had 90% recall, 87% precision and 88% accuracy. Similar model performance was measured using features from only the M-wave or F-wave. Classification probabilities for ALS patients were statistically different from the diagnoses mimicking ALS symptoms (P < 0.001, ANOVA, Tukey’s post hoc test). Higher model classification probabilities of ALS, older age at onset, and family history of ALS alone or with frontotemporal dementia were factors decreasing survival. Longer diagnostic delay and upper limb onset site were factors increasing survival. Model scores two standard deviations below the mean had 4 months increased survival (two standard deviations below had 3 months decreased survival). Artificial intelligence techniques extracted important information from F-wave responses to estimate a patient’s likelihood of ALS and their survival risks. Although the model can make predictions at a specific decision threshold as presented here, the true strength of such a model lies in its ability to provide probabilities about whether a patient is likely to have ALS in comparison to other mimicking diagnoses, such as inclusion body myositis, cervical or lumbar radiculopathy or peripheral neuropathy. These probabilities provide clinicians with additional information that they can use to make the final diagnosis with greater confidence and precision. Integrating such a model into the clinical workflow could help clinicians to diagnose ALS sooner and manage treatment based on estimated survival, which might improve outcomes and the quality of life of patients.

Abstract Background Despite advances in our understanding of the molecular underpinnings of meningioma progression and innovations in systemic and local treatments, recurrent meningiomas remain a substantial therapeutic challenge. The objective of this systematic review and meta-analysis is to provide a historical baseline, contemporary analysis, and propose a “rate of probable interest” to inform future clinical trial design and development on behalf of the Response Assessment in Neuro-Oncology meningioma group. Methods PubMed, ClinicalTrials.gov, and ASCOpubs databases were screened for clinical trials evaluating the activity of systemic therapies for adults with recurrent meningiomas. The pooled progression-free survival at 6-months and 1-year (PFS-6 and PFS-1 year) values were calculated using the random effects technique with I2 indices. Results The pooled PFS-6 and PFS-1 year rates for recurrent WHO grade 1 meningiomas were 43.6% (95% CI: 22.7-67.0%, I2 = 80%) and 21.7% (95% CI: 6.2-53.9%, I2 = 76%), and for grades 2-3 meningiomas, the PFS-6 was 38.0% (95% CI: 28.3-48.8%, I2 = 68%). In the targeted therapy group, PFS-6 and PFS-1 year rates stood at 62.0% (I2 = 58%) and 49.0% (I2 = 63%) for grade 1, while for grades 2-3 tumors, the PFS-6 rates with targeted therapy and immunotherapy were 42.1% (I² = 60%) and 46.0% (I² = 0%), respectively. The benchmarks were set at 67% and 54% for PFS-6 and PFS-1 year for grade 1 tumors, and PFS-6 of 49% for grades 2-3 tumors. Conclusions Several studies have reported outcomes in patients with recurrent meningiomas testing a variety of agents with modest, but variable and progressively increasing activity. In this context, we recommend new benchmarks for future trials to define efficacy of future investigational therapies.

AbstractBackgroundMany proposed clinical decision support systems (CDSS) require multiple disparate data elements as input, which makes implementation difficult, and furthermore have a black‐box nature leading to low interpretability. Fluorodeoxyglucose Positron Emission Tomography (FDG‐PET) is an established modality for the diagnosis of dementia, and a CDSS that uses only an FDG‐PET image to produce a reliable and understandable result would ease both of these challenges to clinical application.MethodA deep variational autoencoder (VAE) was used to extract a latent representation of each image through prior training from FDG‐PET brain images (n=2000). This unsupervised VAE has a novel graph convolutional architecture that makes it applicable to masked template space images. A logistic regression model was used to classify each image. A parametric study of the latent space revealed the imaging features that were used in the logistic regression model to differentiate each class. A separate dataset of participants labeled with their clinical diagnosis (n=1239) was used to assess the logistic regression model’s diagnostic accuracy of cognitively unimpaired (CU) (n=679) and between common dementia subtypes: Alzheimer’s disease (AD) (n=310), Lewy body dementia (DLB) (n=151), and behavioral variant frontotemporal dementia (bvFTD) (n=99). The logistic regression classifier was evaluated using receiver‐operator characteristic (ROC‐AUC) curves.ResultROC‐AUC curves for CU and each dementia subtype are illustrated in Figure 1a. A k nearest neighbors model was used to develop a graphical representation of the latent space where nodes are images and edges are drawn between nearest neighbors, illustrated in Figure 1b. The graph of the latent space demonstrates a comparison between dementia subtypes and CU images.ConclusionIn this study, we developed a proof‐of‐concept VAE that can achieve differential diagnosis with 84.8% balanced accuracy. The model architecture provides visual interpretability, and shows that the hippocampi, parietal lobes, and cerebellum, were useful for distinguishing AD, the frontal lobe, posterior cingulate cortex, and hippocampi were useful for distinguishing DLB, and prefrontal pole, subcortical structures, and occipital lobe were useful for distinguishing bvFTD. These regions of metabolism align with clinical pathology and metabolic patterns.

Abstract Background Many proposed clinical decision support systems (CDSS) require multiple disparate data elements as input, which makes implementation difficult, and furthermore have a black‐box nature leading to low interpretability. Fluorodeoxyglucose Positron Emission Tomography (FDG‐PET) is an established modality for the diagnosis of dementia, and a CDSS that uses only an FDG‐PET image to produce a reliable and understandable result would ease both of these challenges to clinical application. Method A deep variational autoencoder (VAE) was used to extract a latent representation of each image through prior training from FDG‐PET brain images (n=2000). This unsupervised VAE has a novel graph convolutional architecture that makes it applicable to masked template space images. A logistic regression model was used to classify each image. A parametric study of the latent space revealed the imaging features that were used in the logistic regression model to differentiate each class. A separate dataset of participants labeled with their clinical diagnosis (n=1239) was used to assess the logistic regression model’s diagnostic accuracy of cognitively unimpaired (CU) (n=679) and between common dementia subtypes: Alzheimer’s disease (AD) (n=310), Lewy body dementia (DLB) (n=151), and behavioral variant frontotemporal dementia (bvFTD) (n=99). The logistic regression classifier was evaluated using receiver‐operator characteristic (ROC‐AUC) curves. Result ROC‐AUC curves for CU and each dementia subtype are illustrated in Figure 1a. A k nearest neighbors model was used to develop a graphical representation of the latent space where nodes are images and edges are drawn between nearest neighbors, illustrated in Figure 1b. The graph of the latent space demonstrates a comparison between dementia subtypes and CU images. Conclusion In this study, we developed a proof‐of‐concept VAE that can achieve differential diagnosis with 84.8% balanced accuracy. The model architecture provides visual interpretability, and shows that the hippocampi, parietal lobes, and cerebellum, were useful for distinguishing AD, the frontal lobe, posterior cingulate cortex, and hippocampi were useful for distinguishing DLB, and prefrontal pole, subcortical structures, and occipital lobe were useful for distinguishing bvFTD. These regions of metabolism align with clinical pathology and metabolic patterns.

The Quantitative Imaging Biomarkers Alliance Profile for dynamic susceptibility contrast (DSC) MRI and its longitudinal claims for the precision of a DSC MRI–derived quantitative imaging biomarker to assess the relative cerebral blood volume changes in gliomas are summarized.

Abstract BACKGROUND Standard of care surgery for high grade glioma (HGG) employs Magnetic Resonance Imaging to identify the contrast enhancing (CE) core for resection, leaving a non-enhancing (NE) invasive rim of tumor which contributes to recurrence. Multi-parametric MRI (mpMRI) has recently been used to map regional biological heterogeneity of neuronal and immune signatures in HGG, and continues to offer a promising strategy for non-invasive surveillance of tumor progression. Here, we present a graph network analysis relating mpMRI to biological signatures in the NE tumor rim and show the utility of communities of imaging features for discriminating tumor phenotypes. METHODS 53 mpMRI features across 101 spatially-localized RNA-sequenced biopsy samples from 64 patients with IDH-wt HGG were represented as nodes within a Neo4j graph network. Modularity optimization was used to identify communities of densely connected nodes. Communities of nodes representing high proportions of NE samples (one-tailed test) were kept for further analysis. Gene set enrichment analysis (GSEA) on samples within selected imaging communities was analyzed for biological process enrichment using clusterProfiler. Single sample GSEA (ssGSEA) using ssGSEA2 was used to annotate neuronal and immune cell states across samples within selected communities. mpMRI feature selection within each community identified the most relevant imaging features for isolating samples classified into neuronal and immune cell states. RESULTS 11 imaging communities gathered a high proportion of NE samples. Three NE communities showed significant enrichment of neuronal signatures, while one showed significant enrichment of immune pathways. One neuronal-predominant community showed unique upregulation of 14 pathways related to neuronal migration/astrocyte projection. CONCLUSION Network imaging communities can identify clusters of NE glioma samples showing contrasting neuronal and immune signatures, including distinct upregulation of migration and projection pathways. Mapping these imaging feature communities to specific biological processes implicated in glioma progression may aid treatment planning and prognostication for glioma patients.

Abstract The intra- and inter-patient heterogeneity in high-grade glioma (HGG) continues to contribute to its poor prognosis. Clinical biopsies are often harvested from limited regions and typically are not image localized. Thus, they fail to capture the diversity within tumor regions, immune expression or normal cell abundances that play key roles in tumor development. It is important to gain an understanding of these subpopulation ecologies, their spatial resolution, and interactions between them that may then be exploited for future therapeutic benefit. Further, these may differ by patient characteristics such as sex, age at diagnosis and treatment status. Using an ongoing image-localized biopsy collection protocol, we have so far evaluated the bulk transcriptomics of 202 multi-regional biopsies from 58 patients to characterize HGG heterogeneity. These samples were processed through Monocle, a reverse graph embedding algorithm that groups samples into states and orders them along developmental trajectories. Deconvolution methods were previously used to predict relative abundances of 7 normal, 6 glioma, and 5 immune cell subpopulations for each sample, which we have now overlaid on the Monocle graph. Monocle classified HGG into 4 main states along a three-pronged trajectory. These states reveal distinct population ecologies with associated enriched gene pathways. We also note significant immune pathway enrichments that differ between state and patient-reported sex. Together, these algorithms reveal a simple transcriptomic trajectory that helps us understand the development and evolution of HGG. Characterizing the in vivo diversity within and between high grade gliomas is important for understanding prognosis, stratifying future treatments and ultimately improving patient outcome.

Abstract Diffuse gliomas represent the most common type of primary adult malignant brain tumor historically diagnosed and graded from histologic criteria alone. Gliomas harboring isocitrate dehydrogenase (IDH) 1 or 2 mutations are associated with lower grade tumors and portend a favorable prognosis relative to IDH-wildtype glioma. However, the loss of CDKN2A/B in IDH-mutant astrocytoma confers an aggressive high grade phenotype and is the strongest implicated molecular alteration associated poor clinical survival, thus is now sufficient to define a grade 4 tumor regardless of histologic grade. However, there remains no effective therapies targeted at molecular subgroups in aggressive gliomas to date. Here, we sought to elucidate the biologic pathways and functional outcomes associated with the acquisition of high-grade behavior under loss of CDKN2A/B in IDH-mutant astrocytoma to inform future therapeutic strategies. We analyzed a cohort of patient IDH-mutant astrocytomas with RNA sequencing data and found the increased expression of regulators of embryonic nervous system development and signaling concurrent with CDKN2A/B loss. Using grade 4 IDH-mutant astrocytoma patient-derived (PDX) and cell-lines harboring CDKN2A/B homozygous deletion, we stably re-expressed p14ARF, p15INK4B, and p16INK4A using a Tet-inducible system. IDH-mutant cell lines with re-expression of p14, p15, or p16 displayed differential transcription factor activation, impaired neurosphere capability, decreased colony formation, and lower neurosphere proliferation. Intriguingly, RNA-seq data revealed CUX2, a transcription factor known to control neuronal precursor behavior, as the likely candidate regulating the differential expression profile across CDKN2A/B status. We observed increased CUX2 expression in cell lines stably re-expressing p14, p15, and p16. We validated the CUX2 signature across publicly available datasets of IDH-mutant astrocytoma where CUX2 expression negatively correlated with loss of CDKN2A/B in patient tumors. Together our work suggests CUX2 deficiency in IDH-mutant astrocytoma with CDKN2A/B deletion enables an increased neuronal stem-like phenotype in these grade 4 tumors.

Abstract BACKGROUND High-grade glioma (HGG) is the most common and aggressive form of primary brain cancer. Standard of care surgery employs Magnetic Resonance Imaging to identify the contrast enhancing (CE) core for resection, leaving a non-enhancing (NE) invasive rim of tumor which contributes to recurrence. The hypoxic tumor microenvironment is thought to drive invasion into healthy brain, and understanding cellular responses to hypoxia may provide insight into combatting recurrence. Here, we apply a graph network to integrate regionally heterogeneous data from a unique dataset of spatially-localized CE and NE biopsies from a large cohort of patients with HGG to identify gene networks regulating hypoxia response and invasion. METHODS RNA-sequencing of 1159 differentially expressed genes across 159 IDH-wt biopsies (74 patients) from NE/CE regions were represented as nodes in a Neo4j graph network. Candidate genes for network random walks occurred exclusively within NE communities detected by modularity optimization and were localized by cell-type using single-cell RNA-sequencing (scRNAseq). CSF2RA was selected as source (walk length = 5; 10,000 walks/source node). Frequently occurring genes (one-tailed test) in walks were ranked by correlation with CSF2RA expression in NE samples and analyzed by gene set enrichment analysis for biological processes (clusterProfiler). CSF2RA and hypoxia gene expression were visualized with DoHeatmap in composite NE/CE scRNAseq profiles. RESULTS CSF2RA, an immune receptor, was upregulated (logFC = 0.789) in NE samples, scRNAseq myeloid populations, and Glycolytic/Plurimetabolic glioma subtype. CSF2RA random walk genes (n=46) enriched metabolic/proliferative signatures. CSF2RA expression correlated negatively with hypoxia genes globally and regionally (NE/CE), while NE/CE scRNAseq revealed distinct cellular expression patterns of CSF2RA and hypoxia response genes. CONCLUSION CSF2RA expression may prime NE glioma cells for invasion by altering hypoxia response. The genetic network bridging CSF2RA and hypoxia response may be a targetable mechanism of tumor recurrence.