Despite advancements in molecular and histopathologic characterization of pediatric low-grade gliomas (pLGGs), there remains significant phenotypic heterogeneity among tumors with similar ...categorizations. We hypothesized that an unsupervised machine learning approach based on radiomic features may reveal distinct pLGG imaging subtypes.
Multi-parametric MR images (T1 pre- and post-contrast, T2, and T2 FLAIR) from 157 patients with pLGGs were collected and 881 quantitative radiomic features were extracted from tumorous region. Clustering was performed using K-means after applying principal component analysis (PCA) for feature dimensionality reduction. Molecular and demographic data was obtained from the PedCBioportal and compared between imaging subtypes.
K-means identified three distinct imaging-based subtypes. Subtypes differed in mutational frequencies of BRAF (p < 0.05) as well as the gene expression of BRAF (p<0.05). It was also found that age (p < 0.05), tumor location (p < 0.01), and tumor histology (p < 0.0001) differed significantly between the imaging subtypes.
In this exploratory work, it was found that clustering of pLGGs based on radiomic features identifies distinct, imaging-based subtypes that correlate with important molecular markers and demographic details. This finding supports the notion that incorporation of radiomic data could augment our ability to better characterize pLGGs.
Purpose
This study assessed the ability of the LACE + Length of stay, Acuity of admission, Charlson Comorbidity Index (CCI) score, and Emergency department visits in the past 6 months index to ...predict adverse outcomes after urologic surgery.
Methods
LACE + scores were retrospectively calculated for all consecutive patients (
n
= 9824) who received urologic surgery at one multi-center health system over 2 years (2016–2018). Coarsened exact matching was employed to sort patient data before analysis; matching criteria included duration of surgery, BMI, and race among others. Outcomes including unplanned hospital readmission, emergency room visits, and reoperation were compared for patients with different LACE + quartiles.
Results
722 patients were matched between Q1 and Q4; 1120 patients were matched between Q2 and Q4; 2550 patients were matched between Q3 and Q4. Higher LACE + score significantly predicted readmission within 90 days (90D) of discharge for Q1 vs Q4 and Q2 vs Q4. Increased LACE + score also significantly predicted 90D emergency room visits for Q1 vs Q4, Q2 vs Q4, and Q3 vs Q4. LACE + score was also significantly predictive of 90D reoperation for Q1 vs Q4. LACE + score did not predict 90D reoperation for Q2 vs Q4 or Q3 vs Q4 or 90D readmission for Q3 vs. Q4.
Conclusion
These results suggest that LACE + may be a suitable prediction model for important patient outcomes after urologic surgery.
Increasing evidence suggests that besides mutational and molecular alterations, the immune component of the tumor microenvironment also substantially impacts tumor behavior and complicates treatment ...response, particularly to immunotherapies. Although the standard method for characterizing tumor immune profile is through performing integrated genomic analysis on tissue biopsies, the dynamic change in the immune composition of the tumor microenvironment makes this approach not feasible, especially for brain tumors. Radiomics is a rapidly growing field that uses advanced imaging techniques and computational algorithms to extract numerous quantitative features from medical images. Recent advances in machine learning methods are facilitating biological validation of radiomic signatures and allowing them to "mine" for a variety of significant correlates, including genetic, immunologic, and histologic data. Radiomics has the potential to be used as a non-invasive approach to predict the presence and density of immune cells within the microenvironment, as well as to assess the expression of immune-related genes and pathways. This information can be essential for patient stratification, informing treatment decisions and predicting patients' response to immunotherapies. This is particularly important for tumors with difficult surgical access such as gliomas. In this review, we provide an overview of the glioma microenvironment, describe novel approaches for clustering patients based on their tumor immune profile, and discuss the latest progress on utilization of radiomics for immune profiling of glioma based on current literature.
Highlights • Mild traumatic brain injury activates TGF-β1. • Oxidative stress has a significant role in the activation of TGF-β1. • Phosphorylation of R-Smads involves in inflammatory and apoptotic ...role of TGF-β1. • Inhibition of TGF-βRI or TGF-β1 diminishes neuroinflammation and apoptosis. • Excess TGF-β1 may contribute to neuronal dysfunction and cognitive impairment in mTBI.
INTRODUCTION: Pathomics is an emerging data science technique that may be used to extract intricate, sub-visual histopathologic features using high-throughput digital image analysis. METHODS: Using ...the Children’s Brain Tumor Network database, pediatric medulloblastoma patients were evaluated for inclusion in the study. After tumor segmentation, 49 quantitative pathomic features were extracted using a digital pathology software package (Qupath). LASSO cox proportional hazard model with stratified 5-fold cross-validation was used to identify high-performing features and create a predictive survival model by identifying low-, medium- and high-risk OS cohorts. A classification model was developed using histogram gradient boosting classifier to perform binary classification of Group3/4 vs. SHH/WNT with leave-one-subject-out cross validation. RESULTS: 84 patients with median age at diagnosis of 8.61 years (range 0.31-21.72), and median OS of 45.6 months (range 0.76-195.87) were included in the study. A survival model built using only clinical features yielded a concordance index (c-index) of 0.76 compared to actual outcomes (stratification: p < 0.001). However, a survival model built by combining clinical and high-performing pathomic features yielded the best performance, showing disparate outcomes between low-, medium- and high-risk groups (p < 0.001) with resultant c-index of 0.85. Furthermore, pathomic features classified subjects into Group 3/4 or SHH/WNT with classification accuracy of 71% (SEM = 0.06), and t-test against stratified chance accuracy (57%) showed significantly above-chance performance (p = .019). CONCLUSIONS: This study represents the largest pathomic-based machine learning analysis for predicting survival and molecular subtypes in medulloblastoma. The results demonstrate success in pathomic analysis using machine learning-based modeling to predict survival and molecular subtypes for patients with medulloblastoma. Further work will aim to perform our analysis on an external validation dataset to enhance model performance and improve its clinical applicability.
Abstract
BACKGROUND
Pediatric brain tumors (PBTs) are the leading cause of cancer-related death in children. Currently, based on the RAPNO guidelines, two-dimensional (2D) measurements are used to ...detect progression. However, due to the complex radiographic appearance of many PBTs, 2D measurements may not accurately reflect tumor growth. Here, we compared 3D, 2D, and qualitative radiologists’ interpretations in a group of PBTs to determine tumor progression.
METHODS
Six PBT patients (5 low-grade glioma, 1 ependymoma, age range at the time of baseline scan: 23-191 months) with an average of 5 imaging time points who had at least one episode of progression with subsequent surgery were included. Segmentation was performed on either T1 post-contrast or FLAIR, whichever that best identified the tumor. For 2D measurements, the two largest perpendicular diameters in a section that included the largest tumor component were measured. For the volumetric assessment, the tumors were manually segmented, and the volume was computed using the ITK-SNAP software. In multifocal tumors, only the tumor component that showed progression and underwent resection was included. A 25% and 41% increase in tumor size was considered as progression on 2D and 3D measurements, respectively. The time to progression (TTP) based on 2D vs 3D assessment as well as the official pediatric neuroradiologist interpretation based on the electronic health record report was compared.
RESULTS
In three of six patients, volumetric segmentation detected tumor progression at an earlier time point compared to 2D measurements and radiologists’ interpretation (median TTP: 134 compared to 503 for 2D and radiologist interpretation). For these three patients, the TTP based on 3D vs 2D assessment was: 252 vs 1299 days, 134 vs 503 days, and 80 vs 255 days.
CONCLUSION
Volumetric measurements can determine tumor progression earlier than the current standard method of 2D measurements and qualitative interpretation of radiologists in PBTs.
Abstract
Characterization of pediatric low-grade glioma (pLGG) remains a significant challenge in the field of neuro-oncology, with a need for more effective precision diagnostics. Multi-modal ...analysis, which incorporates data from varied sources, has the potential to provide a comprehensive understanding of the underlying biology of pediatric brain tumors. Despite its potential, the utilization of true multi-modality clustering remains limited in pediatric brain tumor research. In this study, we aimed to address this gap by using a clustering model that incorporated genomics, radiomics, and clinical variables (age, sex, and tumor location) to group patients into distinct clusters. 103 patients with pLGGs were included. Mutations data was derived from whole genome sequencing obtained through the PedCBioportal. Radiomic data was obtained from MR imaging through the Children’s Brain Tumor Network and included features from pre- and post-contrast T1, T2, FLAIR, and ADC sequences. Categorical variables included sex (male vs female), genetic mutation status for 10 selected genes (BRAF, FGFR1, TSC1, TSC2, NF1, MYB, EGFR, ALK, IDH1, and RB1) that are known to play a role in the pathogenesis of pLGG (mutated vs non-mutated), and tumor location (9 categories). Continuous variables included age (days) and radiomic features. All numerical variables were normalized and reduced into principal components that captured 90% of the variance in the data prior to clustering. Various clustering iterations were performed incorporating combinations of radiomic, genomic, and clinical data. Our models identified two distinct clusters and the PFS differences between clusters approached statistical significance with the integration of information from all modalities when compared to any combination of subsets of data, highlighting the complementary value of these modalities in providing a comprehensive characterization of pLGG. This study provides preliminary evidence for the utility of multi-modality data clustering in improving our understanding of pLGG and supports further investigation into this approach.
Abstract BACKGROUND Accurate radiographic diagnosis of pediatric brain tumors (PBTs) that originate in the brainstem and posterior fossa, including medulloblastoma (MB), pilocytic astrocytoma (PA), ...ependymoma (EPN), atypical teratoid/rhabdoid tumor (ATRT), and diffuse intrinsic pontine glioma (DIPG), is crucial for optimizing surgical approaches and enhancing neoadjuvant therapies. Existing research on the radiographic differential diagnosis of posterior fossa tumors has limitations, including small sample sizes, lack of inclusion of certain histologies especially rarer tumors such as ATRTs, and incomplete analysis of the whole tumor, including peritumoral edema. In this study, we aimed to perform a comprehensive analysis using radiomics and machine learning to differentiate among the common posterior fossa and brainstem tumors. METHODS We employed 927 radiomic features extracted from whole tumor regions within treatment-naïve, standard multiparametric MRI sequences (pre-/post-contrast T1-weighted, T2-weighted, FLAIR) of 264 patients (106 MBs, 78 PAs, 28 EPNs, 27 ATRTs, and 25 DIPGs), collected from the Children’s Brain Tumor Network (CBTN). We adopted a one-versus-rest classification strategy, employing Support Vector Machines combined with the Least Absolute Shrinkage and Selection Operator (LASSO) for feature selection, and implementing nested cross-validation for robustness. RESULTS The performances of the classifiers were evaluated using the Area Under the Receiver Operating Characteristic Curve, yielding values of 0.84 for MBs, 0.84 for PAs, 0.70 for EPNs, 0.75 for ATRTs, and 0.71 for DIPGs. CONCLUSIONS Our method effectively differentiates between various tumor types in the posterior fossa and brainstem, paving the path towards the development of comprehensive diagnostic and prognostic AI tools for pre-treatment histological diagnosis of these tumors. These AI tools can lead to more tailored, risk-adjusted treatments for PBTs, reducing morbidities and improving patient outcomes. Based on our promising initial results, we will expand our dataset to include more samples and incorporate rarer tumor types, as well as piloting in different molecular subclassifications.
