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

Deep learning models for semantic segmentation of images require large amounts of data. In the medical imaging domain, acquiring sufficient data is a significant challenge. Labeling medical image data requires expert knowledge. Collaboration between institutions could address this challenge, but sharing medical data to a centralized location faces various legal, privacy, technical, and data-ownership challenges, especially among international institutions. In this study, we introduce the first use of federated learning for multi-institutional collaboration, enabling deep learning modeling without sharing patient data. Our quantitative results demonstrate that the performance of federated semantic segmentation models (Dice=0.852) on multimodal brain scans is similar to that of models trained by sharing data (Dice=0.862). We compare federated learning with two alternative collaborative learning methods and find that they fail to match the performance of federated learning.

Single-unit activity in area M1 was recorded in awake, behaving monkeys during a three-dimensional (3D) reaching task performed in a virtual reality environment. This study compares motor cortical discharge rate to both the hand's velocity and the arm's joint angular velocities. Hand velocity is considered a parameter of extrinsic space because it is measured in the Cartesian coordinate system of the monkey's workspace. Joint angular velocity is considered a parameter of intrinsic space because it is measured relative to adjacent arm/body segments. In the initial analysis, velocity was measured as the difference in hand position or joint posture between the beginning and ending of the reach. Cortical discharge rate was taken as the mean activity between these two times. This discharge rate was compared through a regression analysis to either an extrinsic-coordinate model based on the three components of hand velocity or to an intrinsic-coordinate model based on seven joint angular velocities. The model showed that velocities about four degrees-of-freedom (elbow flexion/extension, shoulder flexion/extension, shoulder internal/external rotation, and shoulder adduction/abduction) were those best represented in the sampled population of recorded activity. Patterns of activity recorded across the cortical population at each point in time throughout the task were used in a second analysis to predict the temporal profiles of joint angular velocity and hand velocity. The population of cortical units from area M1 matched the hand velocity and three of the four major joint angular velocities. However, shoulder adduction/abduction could not be predicted even though individual cells showed good correlation to movement on this axis. This was also the only major degree-of-freedom not well correlated to hand velocity, suggesting that the other apparent relations between joint angular velocity and neuronal activity may be due to intrinsic-extrinsic correlations inherent in reaching movements.

Chronic heart failure (CHF) may impair lung gas diffusion, an effect that contributes to exercise limitation. We investigated whether diffusion improvement is a mechanism whereby physical training increases aerobic efficiency in CHF. Patients with CHF (n = 16) were trained (40 min of stationary cycling, 4 times/wk) for 8 wk; similar sedentary patients (n = 15) were used as controls. Training increased lung diffusion (DlCO, +25%), alveolar-capillary conductance (DM, +15%), pulmonary capillary blood volume (VC, +10%), peak exercise O2 uptake (peak VO2, +13%), and VO2 at anaerobic threshold (AT, +20%) and decreased the slope of exercise ventilation to CO2 output (VE/VCO2, -14%). It also improved the flow-mediated brachial artery dilation (BAD, from 4.8 +/- 0.4 to 8.2 +/- 0.4%). These changes were significant compared with baseline and controls. Hemodynamics were obtained in the last 10 patients in each group. Training did not affect hemodynamics at rest and enhanced the increase of cardiac output (+226 vs. +187%) and stroke volume (+59 vs. +49%) and the decrease of pulmonary arteriolar resistance (-28 vs. -13%) at peak exercise. Hemodynamics were unchanged in controls after 8 wk. Increases in DlCO and DM correlated with increases in peak VO2 (r = 0.58, P = 0.019 and r = 0.51, P = 0.04, respectively) and in BAD (r = 0.57, P < 0.021 and r = 0.50, P = 0.04, respectively). After detraining (8 wk), DlCO, DM, VC, peak VO2, VO2 at AT, VE/VCO2 slope, cardiac output, stroke volume, pulmonary arteriolar resistance at peak exercise, and BAD reverted to levels similar to baseline and to levels similar to controls. Results document, for the first time, that training improves DlCO in CHF, and this effect may contribute to enhancement of exercise performance.

No abstract