Search

PURPOSE Glioblastoma is extremely infiltrative with malignant cells extending beyond the enhancing rim where recurrence inevitably occurs, despite aggressive multimodal therapy. We hypothesize that important characteristics of peritumoral tissue heterogeneity captured and analyzed by multi-parametric MRI and artificial intelligence (AI) methods are generalizable in the updated multi-institutional ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium and predictive of neoplastic infiltration and future recurrence. METHODS We used the most recent update of the ReSPOND consortium to evaluate and further refine generalizability of our methods with different scanners and acquisition settings. 179 de novo glioblastoma patients with available T1, T1Gd, T2, T2-FLAIR, and ADC sequences at pre-resection baseline and after complete resection with subsequent pathology-confirmed recurrence were included. To establish generalizability of the predictive models, training and testing of the refined AI model was performed through Leave-One-Institution-Out-Cross-Validation schema. The multi-institutional cohort consisted of the Hospital of the University of Pennsylvania (UPenn, 124), Case Western Reserve University/University Hospitals (CWRU/UH, 27), New York University (NYU, 13), Ohio State University (OSU, 13), and University Hospital Río Hortega (RH, 2). Features extracted from pre-resection MRI were used to build the model predicting the spatial pattern of subsequent tumor recurrence. These predictions were evaluated against regions of pathology-confirmed post-resection recurrence. RESULTS Our model predicted the locations that later harbored tumor recurrence with overall odds ratio (99% CI)/AUC (99% CI), 12.0(11.8-12.2)/0.80(0.76-0.85), and per institute, CWRU/UH, 11.0(10.7-11.3)/0.80 (0.64-0.97); NYU, 7.0(6.7-7.3)/0.78(0.56-1.00); OSU, 18.3(17.5-19.1)/0.83(0.54-1.00); RH, 40.0(35.3-45.5)/0.93(0.00-1.00); UPenn, 8.00(7.7-8.3)/0.80(0.75-0.84). CONCLUSION This study provides extensive multi-institutional validated evidence that machine learning tools can identify peritumoral neoplastic infiltration and predict location of future recurrence, by decrypting the MRI signal heterogeneity in peritumoral tissue. Our analyses leveraged the unique dataset of the ReSPOND consortium, which aims to develop and validate AI-based biomarkers for individualized prediction and prognostication and establish generalizability in a multi-institutional setting.

Registration of longitudinal brain Magnetic Resonance Imaging (MRI) scans containing pathologies is challenging due to tissue appearance changes, and still an unsolved problem. This paper describes the first Brain Tumor Sequence Registration (BraTS-Reg) challenge, focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a brain diffuse glioma. The BraTS-Reg challenge intends to establish a public benchmark environment for deformable registration algorithms. The associated dataset comprises de-identified multi-institutional multi-parametric MRI (mpMRI) data, curated for each scan's size and resolution, according to a common anatomical template. Clinical experts have generated extensive annotations of landmarks points within the scans, descriptive of distinct anatomical locations across the temporal domain. The training data along with these ground truth annotations will be released to participants to design and develop their registration algorithms, whereas the annotations for the validation and the testing data will be withheld by the organizers and used to evaluate the containerized algorithms of the participants. Each submitted algorithm will be quantitatively evaluated using several metrics, such as the Median Absolute Error (MAE), Robustness, and the Jacobian determinant.

PURPOSE Measuring gliomas is a time-intensive process with significant inter-rater variability in post-surgical residual tumor and resection cavities. This likely contributes to the delayed assessment of progression and in-field recurrences from radiation. Automated segmentation of pre and post-treatment gliomas could reduce inter-rater variability and increase workflow efficiency for routine longitudinal radiographic assessment and treatment planning. We evaluated whether a 3D neural network is comparable to expert assessment of pre and post-treatment diffuse gliomas tissue types and resection cavities. METHODS A retrospective cohort of 647 MRIs of patients with diffuse gliomas (average 55.1 years, 45% female, 396 pre-treatment and 251 post-treatment, median 237 days post-surgery) from The Cancer Imaging Archive were stratified by operation status and tumor grade and randomly split into training (536) and testing (111) samples. T1, T1-post-contrast, T2, and FLAIR images were registered, skull-stripped, and interpolated to 1x1x1. Four classes — edema/infiltrative/post-treatment changes (ED), enhancing tissue (ET), necrotic core (NCR), and resection cavities (RC) — were manually segmented by an expert neuroradiologist. Using these segmentations and the four input image modalities, a nnU-Net, a state-of-the-art 3D U-Net convolutional neural network, was trained to predict segmentations of the four classes. RESULTS Segmentation performance in the test set for the ED, ET, and RC classes was at the level of inter-rater reliability with median Dice scores ranging from 0.85 to 1 and relative volume errors ranging from -0.05 to 0.02. There was a near-perfect correlation between manually segmented and predicted total lesion volumes (r2 values ranging from 0.95 to 0.98 among classes). CONCLUSIONS Accurate, automated volumetric quantification of diffuse glioma tissue volumes may improve response assessment in clinical trials and reduce provider burden and errors in measurement.

PURPOSE Glioblastoma, IDH-wildtype, is the most common primary malignant adult brain tumor with median overall survival (OS) of ~14 months, with little improvement over the last 20 years. We hypothesize that AI-based integration of quantitative tumor characteristics, independent of acquisition protocol and equipment, can reveal accurate generalizable prognostic stratification. We seek an AI-based OS predictor using routine clinically acquired MRI sequences, quantitatively evaluated across institutions of the ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium. METHODS We identified a retrospective cohort of 2,293 diffuse glioma (IDH-wildtype/-NOS/-NEC) patients from 22 geographically distinct institutions across 3 continents, with preoperative structural MRI scans. The entire tumor burden was automatically segmented into 3 sub-compartments, i.e., enhancing, necrotic, peritumoral T2-FLAIR abnormality. We developed our AI predictor by multivariate integration of i)patient age, ii)tumor sub-compartment volume normalized to brain volume, iii)spatial distribution characteristics (tumor location, distance to the ventricles, and laterality), and iv)morphologic descriptors (major axes’ length, axes’ ratio, extent, and number of tumors). The AI predictor returns a continuous value between 0-1, defining short-, intermediate-, and long-survivors based on thresholds on the 25th and 75th percentiles. Leave-One-Site-Out-Cross-Validation was used to assess the generalizability of our stratification. Kaplan-Meier survival curves were computed for OS analysis and evaluated by a Cox proportional hazards model for statistical significance and hazard ratios. RESULTS Survival analysis yielded a hazard ratio of 2.07 (95%CI, 2.06-2.08, p-value= 4.8e-102) for patient stratification into short-, intermediate-, and long-survivors. Pearson correlation between the predicted and actual OS yielded an R= 0.49. CONCLUSION Multivariate integration of visually quantified tumor characteristics, agnostic to acquisition protocol/equipment, yields an accurate OS surrogate index. Validation of our AI model in the largest centralized glioblastoma imaging dataset, from the ReSPOND consortium, supports its generalizability across diverse patient populations and acquisition settings, potentially contributing to equitable improvements of personalized patient care.

OBJECTIVE To identify genetic predictors of neurocognition, CMBs, brain volume, and WM changes in pediatric brain tumor survivors. METHODS Patients were selected from an existing cohort (RadART) if they had: 1) at least one neurocognitive evaluation using computer-based CogState; 2) available DNA; 3) standard imaging. Candidate gene or genome-wide genotyping was performed on all patients. CMBs were identified using a semi-automated algorithm developed in MATLAB. Volume of T2/FLAIR WM signal abnormality was measured using a semi-automated method based on a convolutional neural network. Brain volume and cortical thickness were measured using FreeSurfer volumetric analysis. Logistic and linear regression were done to compare phenotypes with candidate genotypes. Genome-wide efficient mixed-model analysis was done to compare neurocognition and CMBs. Gene set analysis was done using https://fuma.ctglab.nl/. RESULTS APOE4 was a candidate variant associated with non-lobar, larger volume CMBs (p CONCLUSION Genetic markers may be associated with neurocognition, CMBs, brain volume and WM changes in pediatric brain tumor survivors; however, larger cohorts are needed to confirm specific gene relevance.