BACKGROUND:Glioblastoma (GBM) is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification. METHODS:We developed a highly reproducible, personalized prognostication, and clinical subgrouping system using machine learning (ML) on routine clinical data, magnetic resonance imaging (MRI), and molecular measures from 2838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, and III) using Kaplan-Meier analysis (Cox proportional model and hazard ratios [HR]). RESULTS:The ML model stratified patients into distinct prognostic subgroups with HRs between subgroups I-II and I-III of 1.62 (95% CI: 1.43-1.84, P < .001) and 3.48 (95% CI: 2.94-4.11, P < .001), respectively. Analysis of imaging features revealed several tumor properties contributing unique prognostic value, supporting the feasibility of a generalizable prognostic classification system in a diverse cohort. CONCLUSIONS:Our ML model demonstrates extensive reproducibility and online accessibility, utilizing routine imaging data rather than complex imaging protocols. This platform offers a unique approach to personalized patient management and clinical trial stratification in GBM.

Automated brain tumor segmentation methods have become well-established and reached performance levels offering clear clinical utility. These methods typically rely on four input magnetic resonance imaging (MRI) modalities: T1-weighted images with and without contrast enhancement, T2-weighted images, and FLAIR images. However, some sequences are often missing in clinical practice due to time constraints or image artifacts, such as patient motion. Consequently, the ability to substitute missing modalities and gain segmentation performance is highly desirable and necessary for the broader adoption of these algorithms in the clinical routine. In this work, we present the establishment of the Brain MR Image Synthesis Benchmark (BraSyn) in conjunction with the Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2023. The primary objective of this challenge is to evaluate image synthesis methods that can realistically generate missing MRI modalities when multiple available images are provided. The ultimate aim is to facilitate automated brain tumor segmentation pipelines. The image dataset used in the benchmark is diverse and multi-modal, created through collaboration with various hospitals and research institutions.

Background: Resting-state fMRI is increasingly used to study the effects of gliomas on the functional organization of the brain. A variety of preprocessing techniques and functional connectivity analyses are represented in the literature. However, there so far has been no systematic comparison of how alternative methods impact observed results.New method: We first surveyed current literature and identified alternative analytical approaches commonly used in the field. Following, we systematically compared alternative approaches to atlas registration, parcellation scheme, and choice of graph-theoretical measure as regards differentiating glioma patients (N = 59) from age-matched reference subjects (N = 163).Results: Our results suggest that non-linear, as opposed to affine registration, improves structural match to an atlas, as well as measures of functional connectivity. Functionally-as opposed to anatomically-derived parcel-lation schemes maximized the contrast between glioma patients and reference subjects. We also demonstrate that graph-theoretic measures strongly depend on parcellation granularity, parcellation scheme, and graph density. Comparison with existing methods and conclusions: Our current work primarily focuses on technical optimization of rs-fMRI analysis in glioma patients and, therefore, is fundamentally different from the bulk of papers discussing glioma-induced functional network changes. We report that the evaluation of glioma-induced alterations in the functional connectome strongly depends on analytical approaches including atlas registration, choice of par-cellation scheme, and graph-theoretical measures.

BACKGROUND AND OBJECTIVES: Surgical planning is critical to achieve optimal outcome in deep brain stimulation (DBS). The relationship between clinical outcomes and DBS electrode position relative to subthalamic nucleus (STN) is well investigated, but the role of surgical trajectory remains unclear. We sought to determine whether preoperatively planned DBS lead trajectory relates to adequate motor outcome in STN-DBS for Parkinson's disease (PD). METHODS: In 49 participants who underwent bilateral STN-DBS for PD using a Leksell® frame, we coregistered the frame and participant MRI images to obtain participant-specific anatomical planes. We evaluated relationships between clinical data and planned trajectories relative to their midsagittal and axial planes. We computed percent change in Unified PD Rating Scale subsection 3 (Unified Parkinson's Disease Rating Scale, part III) scores before and after DBS, and performed binary logistic regression to determine whether planned trajectories affect adequate (>30% Unified Parkinson's Disease Rating Scale, part III improvement) motor outcome. RESULTS: Preoperatively planned left lead trajectory relative to midsagittal plane predicted likelihood of adequate right body motor outcomes (odds ratio = 0.69, P = .024), even when controlling for ventricular width through Evans index. This effect reflects that increasingly lateral angle of approach reduced odds of adequate motor outcome. Right lead trajectory lacked a similar trend. CONCLUSION: Left DBS lead trajectory predicts adequate right-body motor outcome after bilateral STN-DBS. Greater planned trajectory angle relative to midsagittal plane reduces motor outcomes, independent of patients' ventricular width. These data may guide patient selection, inform risk/benefit discussions, optimize surgical planning, or support evidence-based evaluation of the methodologies used to select the approach trajectory, with careful consideration of the angle of approach relative to target.

A myriad of algorithms for the automatic analysis of brain MR images is available to support clinicians in their decision-making. For brain tumor patients, the image acquisition time series typically starts with an already pathological scan. This poses problems, as many algorithms are designed to analyze healthy brains and provide no guarantee for images featuring lesions. Examples include, but are not limited to, algorithms for brain anatomy parcellation, tissue segmentation, and brain extraction. To solve this dilemma, we introduce the BraTS inpainting challenge. Here, the participants explore inpainting techniques to synthesize healthy brain scans from lesioned ones. The following manuscript contains the task formulation, dataset, and submission procedure. Later, it will be updated to summarize the findings of the challenge. The challenge is organized as part of the ASNR-BraTS MICCAI challenge.

Vestibular schwannoma (VS) is a benign, slow growing tumor that may affect hearing and balance. It accounts for 7-8% of all primary brain tumors. Gamma knife radiosurgery (GKRS) is a common treatment option for VS. Magnetic resonance imaging (MRI) is employed for diagnosis, surgery planning, and follow-up of VS. Long-term follow-up determines efficacy of VS treatment. Identifying MRI-derived markers to improve management of VS is challenging. This study describes MRI processing pipeline that automatically segments VS and investigates stability and outcome predictive power of radiomic MRI features.We first preprocessed and segmented available pre-GKRS T1-weighted post-contrast MRI images in VS patients, using a Convolutional Neural Network (CNN) developed on DeepMedic framework. Then, we compared CNN and manual segmentations, extracted radiomic features from both manual and CNN segmentations of VS, and, finally, evaluated robustness of extracted features and clinical outcome analyses based thereof.We found that homogeneity, robust maximum intensity and sphericity were the most robust across segmentations. We also found that maximum and minimum intensities were most predictive of tumor growth across all segmentation methods and subject cohorts. We used retrospective post-GK SRS data collected in our institution to build the processing pipeline for unsupervised segmenting of VS. This pipeline is released as a Docker image integrated with XNAT (extensible neuroimaging archive toolkit), an established open research imaging database platform[15][1]. Generated segmentations can be viewed and edited in the XNAT-based online OHIF (Open Health Imaging Foundation) viewer[16][2] in real time.### Competing Interest StatementAlbert Kim is a consultant for Monteris Medical.### Funding StatementThis work was partially funded by NCI grant U24CA204854 aimed at developing data and knowledge management platforms to support the collection, analysis, and sharing of imaging and related data for use in cancer research.### Author DeclarationsI confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.YesThe details of the IRB/oversight body that provided approval or exemption for the research described are given below:IRB of Washington University in Saint Louis gave ethical approval for this work.I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.YesI understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).YesI have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.YesAll data produced in the present study are available upon reasonable request to the authors* VS : Vestibular Schwannoma MGA : Multimodal Glioma Analysis GK : Gamma Knife QC : Quality Control NCR : necrosis ENH : enhancement ROI : region of interest FOV : field of view nogt-63 : no gamma knife contour CNN : convolutional neural network gt : gamma knife DM : DeepMedic [1]: #ref-15 [2]: #ref-16

Abstract Using resting-state fMRI is a challenge in patients with large tumors owing to mass effect and potentially altered representation of function, i.e., remapping. The best approach to atlas registration in tumor patients remains uncertain. In this work, we investigated the effects of alternative approaches to atlas registration on resting-state fMRI functional connectivity in glioblastoma (GBM) patients and studied the impact of GBM on functional brain organization. We analyzed data representing 59 GBM patients and 161 age-matched healthy subjects and systemically investigated affine vs. non-linear atlas registration and two associated masking options. Outcomes were assessed both in terms of structural data match to an atlas template as well as functional connectivity (FC) match to a reference dataset. Next, we evaluated the impact of GBMs on the organization of brain networks accounting for the hierarchical organization of resting state networks. Our results demonstrate that non-linear atlas registration with tumor masking optimizes both structural normalization and FC mapping. The aberrancy map results, obtained with fine parcellations, are consistent with prior findings showing that FC abnormalities induced by focal lesions are widely distributed. However, the results obtained with coarse parcellations indicate that functional architecture is grossly normal in tumor patients.

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at: https://github.com/RagMeh11/QU-BraTS.

Abstract PURPOSE Multi-parametric MRI and artificial intelligence (AI) methods were previously used to predict peritumoral neoplastic cell infiltration and risk of future recurrence in glioblastoma, in single-institution studies. We hypothesize that important characteristics of peritumoral tissue heterogeneity captured, engineered/selected, and quantified by these methods relate to predictions generalizable in the multi-institutional ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium. METHODS To support further development, generalization, and clinical translation of our proposed method, we trained the AI model on a retrospective cohort of 29 de novo glioblastoma patients from the Hospital of the University of Pennsylvania (UPenn) (Male/Female:20/9, age:22-78 years) followed by evaluation on a prospective multi-institutional cohort of 84 glioblastoma patients (Male/Female:51/33, age:34-89 years) from Case Western Reserve University/University Hospitals (CWRU/UH, 25), New York University (NYU, 13), Ohio State University (OSU, 13), University Hospital Río Hortega (RH, 2), and UPenn (31). Features extracted from pre-resection MRI (T1, T1-Gd, T2, T2-FLAIR, ADC) were used to build our 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 sensitivity 83%, AUC 0.83 (99% CI, 0.73-0.93), and odds ratio 7.23 (99% CI, 7.09-7.37) in the prospective cohort. Odds ratio (99% CI)/AUC(99% CI) per institute were: CWRU/UH, 7.8(7.6-8.1)/0.82(0.75-0.89); NYU, 3.5(3.3-3.6)/0.84(074-0.93); OSU, 7.9(7.6-8.3)/0.8(0.67-0.94); RH, 22.7(20-25.1)/0.94(0.27-1); UPenn, 7.1(6.8-7.3)/0.83(0.76-0.91). CONCLUSION This is the first study that provides relatively extensive multi-institutional validated evidence that AI can provide good predictions of peritumoral neoplastic cell infiltration and future recurrence, by dissecting the MRI signal heterogeneity in peritumoral tissue. Our analyses leveraged the unique dataset of the ReSPOND consortium, which aims to develop and evaluate AI-based biomarkers for individualized prediction and prognostication, by moving from single-institution studies to generalizable, well-validated multi-institutional predictive biomarkers.

Abstract PURPOSE Multi-parametric MRI based radiomic signatures have highlighted the promise of artificial intelligence (AI) in neuro-oncology. However, inter-institution heterogeneity hinders generalization to data from unseen clinical institutions. To this end, we formulated the ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium for glioblastoma. Here, we seek non-invasive generalizable radiomic signatures from routine clinically-acquired MRI for prognostic stratification of glioblastoma patients. METHODS We identified a retrospective cohort of 606 patients with near/gross total tumor resection ( >90%), from 13 geographically-diverse institutions. All pre-operative structural MRI scans (T1,T1-Gd,T2,T2-FLAIR) were aligned to a common anatomical atlas. An automatic algorithm segmented the whole tumors (WTs) into 3 sub-compartments, i.e., enhancing (ET), necrotic core (NC), and peritumoral T2-FLAIR signal abnormality (ED). The combination of ET+NC defines the tumor core (TC). Quantitative radiomic features were extracted to generate our AI model to stratify patients into short- (< 14mts) and long-survivors ( >14mts). The model trained on 276 patients from a single institution was independently validated on 330 unseen patients from 12 left-out institutions, using the area-under-the-receiver-operating-characteristic-curve (AUC). RESULTS Each feature individually offered certain (limited but reproducible) value for identifying short-survivors: 1) TC closer to lateral ventricles (AUC=0.62); 2) larger ET/brain (AUC=0.61); 3) larger TC/brain (AUC=0.59); 4) larger WT/brain (AUC=0.55); 5) larger ET/WT (AUC=0.59); 6) smaller ED/WT (AUC=0.57); 7) larger ventricle deformations (AUC=0.6). Integrating all features and age, through a multivariate AI model, resulted in higher accuracy (AUC=0.7; 95% C.I.,0.64-0.77). CONCLUSION Prognostic stratification using basic radiomic features is highly reproducible across diverse institutions and patient populations. Multivariate integration yields relatively more accurate and generalizable radiomic signatures, across institutions. Our results offer promise for generalizable non-invasive in vivo signatures of survival prediction in patients with glioblastoma. Extracted features from clinically-acquired imaging, renders these signatures easier for clinical translation. Large-scale evaluation could contribute to improving patient management and treatment planning. *Indicates equal authorship.

PurposeTo develop an algorithm to classify postcontrast T1-weighted MRI scans by tumor classes (high-grade glioma, low-grade glioma [LGG], brain metastasis, meningioma, pituitary adenoma, and acoustic neuroma) and a healthy tissue (HLTH) class.Materials and MethodsIn this retrospective study, preoperative postcontrast T1-weighted MR scans from four publicly available datasets-the Brain Tumor Image Segmentation dataset (n = 378), the LGG-1p19q dataset (n = 145), The Cancer Genome Atlas Glioblastoma Multiforme dataset (n = 141), and The Cancer Genome Atlas Low Grade Glioma dataset (n = 68)-and an internal clinical dataset (n = 1373) were used. In all, a total of 2105 images were split into a training dataset (n = 1396), an internal test set (n = 361), and an external test dataset (n = 348). A convolutional neural network was trained to classify the tumor type and to discriminate between images depicting HLTH and images depicting tumors. The performance of the model was evaluated by using cross-validation, internal testing, and external testing. Feature maps were plotted to visualize network attention. The accuracy, positive predictive value (PPV), negative predictive value, sensitivity, specificity, F1 score, area under the receiver operating characteristic curve (AUC), and area under the precision-recall curve (AUPRC) were calculated.ResultsOn the internal test dataset, across the seven different classes, the sensitivities, PPVs, AUCs, and AUPRCs ranged from 87% to 100%, 85% to 100%, 0.98 to 1.00, and 0.91 to 1.00, respectively. On the external data, they ranged from 91% to 97%, 73% to 99%, 0.97 to 0.98, and 0.9 to 1.0, respectively.ConclusionThe developed model was capable of classifying postcontrast T1-weighted MRI scans of different intracranial tumor types and discriminating images depicting pathologic conditions from images depicting HLTH.Keywords MR-Imaging, CNS, Brain/Brain Stem, Diagnosis/Classification/Application Domain, Supervised Learning, Convolutional Neural Network, Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2021.

The BraTS 2021 challenge celebrates its 10th anniversary and is jointly organized by the Radiological Society of North America (RSNA), the American Society of Neuroradiology (ASNR), and the Medical Image Computing and Computer Assisted Interventions (MICCAI) society. Since its inception, BraTS has been focusing on being a common benchmarking venue for brain glioma segmentation algorithms, with well-curated multi-institutional multi-parametric magnetic resonance imaging (mpMRI) data. Gliomas are the most common primary malignancies of the central nervous system, with varying degrees of aggressiveness and prognosis. The RSNA-ASNR-MICCAI BraTS 2021 challenge targets the evaluation of computational algorithms assessing the same tumor compartmentalization, as well as the underlying tumor's molecular characterization, in pre-operative baseline mpMRI data from 2,040 patients. Specifically, the two tasks that BraTS 2021 focuses on are: a) the segmentation of the histologically distinct brain tumor sub-regions, and b) the classification of the tumor's O[6]-methylguanine-DNA methyltransferase (MGMT) promoter methylation status. The performance evaluation of all participating algorithms in BraTS 2021 will be conducted through the Sage Bionetworks Synapse platform (Task 1) and Kaggle (Task 2), concluding in distributing to the top ranked participants monetary awards of 60,000 collectively.

ABSTRACT Background Deep brain stimulation of the subthalamic nucleus is a widely used adjunctive therapy for motor symptoms of Parkinson's disease, but with variable motor response. Predicting motor response remains difficult, and novel approaches may improve surgical outcomes as well as the understanding of pathophysiological mechanisms. The objective of this study was to determine whether preoperative resting‐state functional connectivity MRI predicts motor response from deep brain stimulation of the subthalamic nucleus. Methods We collected preoperative resting‐state functional MRI from 70 participants undergoing subthalamic nucleus deep brain stimulation. For this cohort, we analyzed the strength of STN functional connectivity with seeds determined by stimulation‐induced (ON/OFF) 15 O H 2 O PET regional cerebral blood flow differences in a partially overlapping group (n = 42). We correlated STN‐seed functional connectivity strength with postoperative motor outcomes and applied linear regression to predict motor outcomes. Results Preoperative functional connectivity between the left subthalamic nucleus and the ipsilateral internal globus pallidus correlated with postsurgical motor outcomes ( r = −0.39, P = 0.0007), with stronger preoperative functional connectivity relating to greater improvement. Left pallidal‐subthalamic nucleus connectivity also predicted motor response to DBS after controlling for covariates. Discussion Preoperative pallidal‐subthalamic nucleus resting‐state functional connectivity predicts motor benefit from deep brain stimulation, although this should be validated prospectively before clinical application. These observations suggest that integrity of pallidal‐subthalamic nucleus circuits may be critical to motor benefits from deep brain stimulation. © 2020 International Parkinson and Movement Disorder Society

Surface rendering of MRI brain scans may lead to identification of the participant through facial characteristics. In this study, we evaluate three methods that overwrite voxels containing privacy-sensitive information: Face Masking, FreeSurfer defacing, and FSL defacing. We included structural T1-weighted MRI scans of children, young adults and older adults. For the young adults, test-retest data were included with a 1-week interval. The effects of the de-identification methods were quantified using different statistics to capture random variation and systematic noise in measures obtained through the FreeSurfer processing pipeline. Face Masking and FSL defacing impacted brain voxels in some scans especially in younger participants. FreeSurfer defacing left brain tissue intact in all cases. FSL defacing and FreeSurfer defacing preserved identifiable characteristics around the eyes or mouth in some scans. For all de-identification methods regional brain measures of subcortical volume, cortical volume, cortical surface area, and cortical thickness were on average highly replicable when derived from original versus de-identified scans with average regional correlations >.90 for children, young adults, and older adults. Small systematic biases were found that incidentally resulted in significantly different brain measures after de-identification, depending on the studied subsample, de-identification method, and brain metric. In young adults, test-retest intraclass correlation coefficients (ICCs) were comparable for original scans and de-identified scans with average regional ICCs >.90 for (sub)cortical volume and cortical surface area and ICCs >.80 for cortical thickness. We conclude that apparent visual differences between de-identification methods minimally impact reliability of brain measures, although small systematic biases can occur.

Detection and segmentation of primary and secondary brain tumors are crucial in Radiation Oncology. Significant efforts have been dedicated to devising deep learning models for this purpose. However, development of a unified model for the segmentation of multiple types of tumors is nontrivial due to high heterogeneity across different pathologies. In this work, we propose BrainTumorNet, a multi-task learning (MTL) scheme for the joint segmentation of high-grade gliomas (HGG) and brain metastases (METS) from multimodal magnetic resonance imaging (MRI) scans. We augment the state-of-the-art DeepMedic1 architecture using this scheme and evaluate its performance on a highly unbalanced hybrid dataset comprising 259 HGG and 58 METS patient-cases. For the HGG segmentation task, the network produces a Dice score of 86.74% for whole tumor segmentation, which is comparable to 87.35% and 87.19% by the task-specific and single-task joint training baselines, respectively. For the METS segmentation task, BrainTumorNet produces an average Dice score of 62.60% thus outperforming the scores of 19.85%, 57.99%, 59.74%, and 44.17% by the two transfer-learned, task-specific, and single-task joint training baseline models, respectively. The trained network retains knowledge across segmentation tasks by exploiting the underlying correlation between pathologies. At the same time, it is discriminative enough to produce competitive segmentations for each task. The hard parameter sharing in the network reduces the computational overhead compared to training task-specific models for multiple tumor types. To our knowledge, this is the first attempt towards developing a single overarching model for the segmentation of different types of brain tumors.

BACKGROUND:To explore if early perfusion-weighted magnetic resonance imaging (PWI) may be a promising imaging biomarker to predict local recurrence (LR) of brain metastases after stereotactic radiosurgery (SRS). METHODS:This is a prospective pilot study of adult brain metastasis patients who were treated with SRS and imaged with PWI before and 1 week later. Relative cerebral blood volume (rCBV) parameter maps were calculated by normalizing to the mean value of the contralateral white matter on PWI. Cox regression was conducted to explore factors associated with time to LR, with Bonferroni adjusted p<0.0006 for multiple testing correction. LR rates were estimated with the Kaplan-Meier method and compared using the log-rank test. RESULTS:Twenty-three patients were enrolled from 2013 through 2016, with 22 evaluable lesions from 16 patients. After a median follow-up of 13.1 months (range: 3.0-53.7), 5 lesions (21%) developed LR after a median of 3.4 months (range: 2.3-5.7). On univariable analysis, larger tumor volume (HR 1.48, 95% CI 1.02-2.15, p = 0.04), lower SRS dose (HR 0.45, 95% CI 0.21-0.97, p = 0.04), and higher rCBV at week 1 (HR 1.07, 95% CI 1.003-1.14, p = 0.04) had borderline association with shorter time to LR. Tumors >2.0cm3 had significantly higher LR than if ≤2.0cm3: 54% vs 0% at 1 year, respectively, p = 0.008. A future study to confirm the association of early PWI and LR of the high-risk cohort of lesions >2.0cm3 is estimated to require 258 patients. CONCLUSIONS:PWI at week 1 after SRS may have borderline association with LR. Tumors <2.0cm3 have low risk of LR after SRS and may be low-yield for predictive biomarker studies. Information regarding sample size and potential challenges for future imaging biomarker studies may be gleaned from this pilot study.

Retrospective neuro-oncology imaging research relies on standardization of large, heterogeneous sets of clinical images. In particular, many tumor segmentation algorithms require pre- and post- Gadolinium (Gd) T1-weighted MRI scans. Since the presence of contrast agent cannot be reliably inferred from image metadata, we propose an automatic imagebased classifier for this purpose. We proceed with aligning a T1-weighted MR image to a standard atlas space, by selecting one of eight affine transforms produced using different registration parameters and atlases. After resampling to the standard space, we normalize the intensity distribution and compute intensity characteristics inside a pre-built binary mask of likely enhancement. Using a labeled set of 1892 scans, we evaluated logistic regressions with mean, standard deviation, and 95th percentile as possible factors. A univariable logistic regression with standard deviation as factor was most accurate at 98.9% on testing data. The slope coefficient was highly robust with p<1e-6 and Cramer-Rao bound on variance of 1%. The resulting classification script is completely unsupervised. Accuracy on two validation datasets from different sources (totaling 1328 scans) was over 99% on scans with isotropic sampling. Accuracy was lower on highly anisotropic or otherwise lower quality scans. To our knowledge, this is the first attempt to build an automated Gd enhancement classifier for big data applications. We plan to integrate it into XNAT platform for automatic labeling, to enable Gd enhanced image search. The proposed detector performed well on a wide variety of acquisition parameters. Image anisotropy and acquisition artifacts may interfere with accurate detection.

Brain extraction, or skull-stripping, is an essential pre-processing step in neuro-imaging that has a direct impact on the quality of all subsequent processing and analyses steps. It is also a key requirement in multi-institutional collaborations to comply with privacy-preserving regulations. Existing automated methods, including Deep Learning (DL) based methods that have obtained state-of-the-art results in recent years, have primarily targeted brain extraction without considering pathologically-affected brains. Accordingly, they perform sub-optimally when applied on magnetic resonance imaging (MRI) brain scans with apparent pathologies such as brain tumors. Furthermore, existing methods focus on using only T1-weighted MRI scans, even though multi-parametric MRI (mpMRI) scans are routinely acquired for patients with suspected brain tumors. In this study, we present a comprehensive performance evaluation of recent deep learning architectures for brain extraction, training models on mpMRI scans of pathologically-affected brains, with a particular focus on seeking a practically-applicable, low computational footprint approach, generalizable across multiple institutions, further facilitating collaborations. We identified a large retrospective multi-institutional dataset of n=3340 mpMRI brain tumor scans, with manually-inspected and approved gold-standard segmentations, acquired during standard clinical practice under varying acquisition protocols, both from private institutional data and public (TCIA) collections. To facilitate optimal utilization of rich mpMRI data, we further introduce and evaluate a novel ''modality-agnostic training'' technique that can be applied using any available modality, without need for model retraining. Our results indicate that the modality-agnostic approach1 obtains accurate results, providing a generic and practical tool for brain extraction on scans with brain tumors.

Several studies underscore the potential of deep learning in identifying complex patterns, leading to diagnostic and prognostic biomarkers. Identifying sufficiently large and diverse datasets, required for training, is a significant challenge in medicine and can rarely be found in individual institutions. Multi-institutional collaborations based on centrally-shared patient data face privacy and ownership challenges. Federated learning is a novel paradigm for data-private multi-institutional collaborations, where model-learning leverages all available data without sharing data between institutions, by distributing the model-training to the data-owners and aggregating their results. We show that federated learning among 10 institutions results in models reaching 99% of the model quality achieved with centralized data, and evaluate generalizability on data from institutions outside the federation. We further investigate the effects of data distribution across collaborating institutions on model quality and learning patterns, indicating that increased access to data through data private multi-institutional collaborations can benefit model quality more than the errors introduced by the collaborative method. Finally, we compare with other collaborative-learning approaches demonstrating the superiority of federated learning, and discuss practical implementation considerations. Clinical adoption of federated learning is expected to lead to models trained on datasets of unprecedented size, hence have a catalytic impact towards precision/personalized medicine.

Background Use of functional MRI (fMRI) in pre-surgical planning is a non-invasive method for pre-operative functional mapping for patients with brain tumors, especially tumors located near eloquent cortex. Currently, this practice predominantly involves task-based fMRI (T-fMRI). Resting state fMRI (RS-fMRI) offers an alternative with several methodological advantages. Here, we compare group-level analyses of RS-fMRI vs. T-fMRI as methods for language localization. Purpose To contrast RS-fMRI vs. T-fMRI as techniques for localization of language function. Methods We analyzed data obtained in 35 patients who had both T-fMRI and RS-fMRI scans during the course of pre-surgical evaluation. The RS-fMRI data were analyzed using a previously trained resting-state network classifier. The T-fMRI data were analyzed using conventional techniques. Group-level results obtained by both methods were evaluated in terms of two outcome measures: (1) inter-subject variability of response magnitude and (2) sensitivity/specificity analysis of response topography, taking as ground truth previously reported maps of the language system based on intraoperative cortical mapping as well as meta-analytic maps of language task fMRI responses. Results Both fMRI methods localized major components of the language system (areas of Broca and Wernicke) although not with equal inter-subject consistency. Word-stem completion T-fMRI strongly activated Broca's area but also several task-general areas not specific to language. RS-fMRI provided a more specific representation of the language system. Conclusion We demonstrate several advantages of classifier-based mapping of language representation in the brain. Language T-fMRI activated task-general (i.e., not language-specific) functional systems in addition to areas of Broca and Wernicke. In contrast, classifier-based analysis of RS-fMRI data generated maps confined to language-specific regions of the brain.