Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.
No abstract
This research presents an immersive virtual laboratory for cellular study and microscopy utilizing Virtual Reality (VR) technologies. This project entails a thorough examination of the operation of a real-world microscope, followed by replicating its functionalities within a virtual environment. We strive to create an engaging and pedagogically sound learning experience by incorporating multi-modal cues and interactive activities. Our developed virtual laboratory exhibits a variety of cell types—including human, animal, and plant cells—enabling learners to visualize and manipulate these cells. Our research highlights the effectiveness of user-friendly, intuitive interfaces in enhancing cellular visualization.Additionally, the system features interactive educational activities, such as puzzles and games, designed to promote a deeper understanding and long-term retention of cellular components. We also implemented strategies to mitigate VR-induced side effects, like motion sickness, ensuring a smooth learning experience. The resulting immersive laboratory protects students from the risk of damaging physical equipment and promotes a robust understanding of the subject matter. This paper offers valuable insights into the development of a practical virtual laboratory, acting as a helpful guide for future educational VR applications.
La inteligencia de negocios y la analítica de datos como soporte para la toma de decisiones, representa en el contexto empresarial de hoy, una de las principales herramientas que dan apoyo a la gestión en sus diferentes niveles tácticos y operacionales. Por otro lado, las empresas proveedoras de servicios de envíos por courier, constituyen un importante segmento de la economía nacional, ya que su naturaleza de velocidad y servicio seguro, permiten acceder en tiempos mínimos a servicios de transporte de encomiendas a nivel nacional e internacional, lo que fomenta la productividad en todos sus escenarios de incidencia. Para cumplir con las características impuestas por su segmento de negocio, las empresas de courier deben realizar importantes inversiones económicas para ofrecer una red de cobertura propia y los mecanismos para garantizar la seguridad que implican este tipo de envíos. Asimismo, la satisfacción de los clientes, como en todo negocio, es un factor predominante a la hora de garantizar su crecimiento y competitividad. En esta investigación, se analizan enfoques teóricos y metodológicos, desde un punto de vista del análisis del modelo de negocio de las empresas de servicios por courier, para realizar la base de una propuesta tecnológica para la construcción de herramientas de analítica de información gerencial como soporte para la toma de decisiones, centradas en la segmentación de sus clientes para ofrecer servicios diferenciados y de calidad, la implementación de canales digitales de comunicación orientados a la venta, posventa y fidelización, orientadas a obtener datos de valía para analizar estrategias de crecimiento geográfico, y en general, a plantear un marco de referencia para la gestión de proyectos tecnológicos actuales y futuros. El alcance está planteado, en principio, a aquellas empresas con sede principal declarada en la provincia del Azuay.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.