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. Abbreviations CDS Collaborative data sharing FL Federated learning IIL Institutional incremental learning CIIL Cyclic institutional incremental learning IID Independent and identically distributed BraTS Brain tumor segmentation

† People involved in the organization of the challenge. ‡ People contributing data from their institutions.§ Equal senior authors.

The identifying or sensitive anatomical features in MR and CT images used in research raise patient privacy concerns when such data are shared. In order to protect human subject privacy, we developed a method of anatomical surface modification and investigated the effects of such modification on image statistics and common neuroimaging processing tools. Common approaches to obscuring facial features typically remove large portions of the voxels. The approach described here focuses on blurring the anatomical surface instead, to avoid impinging on areas of interest and hard edges that can confuse processing tools. The algorithm proceeds by extracting a thin boundary layer containing surface anatomy from a region of interest. This layer is then “stretched” and “flattened” to fit into a thin “box” volume. After smoothing along a plane roughly parallel to anatomy surface, this volume is transformed back onto the boundary layer of the original data. The above method, named normalized anterior filtering, was coded in MATLAB and applied on a number of high resolution MR and CT scans. To test its effect on automated tools, we compared the output of selected common skull stripping and MR gain field correction methods used on unmodified and obscured data. With this paper, we hope to improve the understanding of the effect of surface deformation approaches on the quality of de-identified data and to provide a useful de-identification tool for MR and CT acquisitions.

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 approach 1 obtains accurate results, providing a generic and practical tool for brain extraction on scans with brain tumors.

Synopsis The goal of this article is to compare resting state fMRI with task fMRI as a tool for presurgical functional mapping of the sensorimotor (SM) region. Prior to tumor resection, 38 patients were scanned using both methods. The SM area was anatomically defined using two different software tools. Overlap of anatomical regions of interest with task activation maps and resting state networks was measured in the SM region. A paired t-test showed higher overlap between resting state maps and anatomical references as compared to task activation when using a maximal overlap criterion. Resting state derived maps are more comprehensive than those derived from task fMRI.