A5037424460- Software-Defined Networks and 5G
- Advanced MIMO Systems Optimization
- Telecommunications and Broadcasting Technologies
- Caching and Content Delivery
- Glioma Diagnosis and Treatment
- Software System Performance and Reliability
- Radiomics and Machine Learning in Medical Imaging
- Meningioma and schwannoma management
- IoT and Edge/Fog Computing
- IoT Networks and Protocols
- Image and Video Quality Assessment
- Artificial Intelligence in Healthcare and Education
- Service-Oriented Architecture and Web Services
- Medical Imaging and Analysis
- Energy Harvesting in Wireless Networks
- Distributed systems and fault tolerance
- Anesthesia and Pain Management
- AI in cancer detection
- Spine and Intervertebral Disc Pathology
- Traumatic Brain Injury and Neurovascular Disturbances
- Smart Grid Security and Resilience
- Multimedia Communication and Technology
- graph theory and CDMA systems
- Brain Tumor Detection and Classification
- Advanced Wireless Communication Technologies
Washington University in St. Louis
2024-2025
Samsung (United Kingdom)
2019-2025
University of Illinois Urbana-Champaign
2024
Samsung (United States)
2020-2021
We describe the design and results from BraTS 2023 Intracranial Meningioma Segmentation Challenge. The Challenge differed prior Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic anatomical presentation a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data largest multi-institutional systematically expert annotated multilabel multi-sequence...
Abstract Meningiomas are the most common primary intracranial tumors and can be associated with significant morbidity mortality. Radiologists, neurosurgeons, neuro-oncologists, radiation oncologists rely on brain MRI for diagnosis, treatment planning, longitudinal monitoring. However, automated, objective, quantitative tools non-invasive assessment of meningiomas multi-sequence MR images not available. Here we present BraTS Pre-operative Meningioma Dataset, as largest multi-institutional...
We describe the design and results from BraTS 2023 Intracranial Meningioma Segmentation Challenge. The Challenge differed prior Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic anatomical presentation a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data largest multi-institutional systematically expert annotated multilabel multi-sequence...
The 5G-VINNI testbed infrastructure project provides 5G facilities for pan-European services. Within the project, UK site is one of that targets developing a flexible and dynamic test environment which can be adapted to meet requirements from H2020 funded projects as well external trials, enable vertical industries assess networks in context advanced digital use cases. In this paper, we present full overview developed at facility, including backhaul, edge, slicing, interworking validation....
Developing a 5G end-to-end facility that can demonstrate the key network KPIs be met, and accessed used by vertical industries, is one of focus areas Phase 3 PPP. This paper presents guidelines to implement such facility.
We state a position on addressing the problem of Zero Downtime Edge Application Mobility (ZeroDEAM) for ultra-low latency 5G streaming services. define and use an network gaming case as paradigm investigating solution to contemporary emerging cases characterized by high mobility latency, which require zero downtime after handover. As thesis, we pose conceptual architecture leveraging Machine Learning (ML) potential at network's Edge, where distributed intelligent models in proximity mobile...
Ultra-reliable low-latency communication (URLLC) services are intrinsically challenging to deliver, with many 5G and future services, including mobile game streaming, adding further complexity by demanding zero service downtime in high-mobility scenarios. Solving these challenges is essential must be addressed beyond gaming realise a multitude of current like eX-tended/Virtual Reality(XR/VR) or holoportation Multi-access Edge Computing (MEC) brings "closer" user consumption evident...
Next-generation mobile core networks are required to be scalable and capable of efficiently utilizing heterogeneous bare metal resources that may include edge servers. To this end, microservice-based solutions where control plane procedures deconstructed in their fundamental building blocks gaining momentum. This letter proposes an optimization framework delivering the partitioning mapping large-scale microservice graphs onto deployments while minimizing total network traffic among An...
Deep learning techniques, despite their potential, often suffer from a lack of reproducibility and generalizability, impeding clinical adoption. Image segmentation is one the critical tasks in medical image analysis, which or several regions/volumes interest should be annotated. This paper introduces RIDGE checklist, framework for assessing Reproducibility, Integrity, Dependability, Generalizability, Efficiency deep learning-based models. The checklist serves as guide researchers to enhance...
Next-generation mobile core networks are required to be scalable and capable of efficiently utilizing heterogeneous bare metal resources that may include edge servers. To this end, microservice-based solutions where control plane procedures deconstructed in their fundamental building blocks gaining momentum. This letter proposes an optimization framework delivering the partitioning mapping large-scale microservice graphs onto deployments while minimizing total network traffic among An...
Abstract Deep learning techniques hold immense promise for advancing medical image analysis, particularly in tasks like segmentation, where precise annotation of regions or volumes interest within images is crucial but manually laborious and prone to interobserver intraobserver biases. As such, deep approaches could provide automated solutions such applications. However, the potential these often undermined by challenges reproducibility generalizability, which are key barriers their clinical...
The 5G VINNI testbed infrastructure project provides facilities for pan-European services. Within the project, UK site is one of 5G-VINNI that targets developing a flexible and dynamic test environment which can be adapted to meet requirements from H2020 funded projects as well external trials, enable vertical industries assess networks in context advanced digital use cases. In this paper, we present full overview developed at facility, including backhaul, edge, slicing, interworking...
With mobile networks expected to support services with stringent reliability, availability, latency and throughput metrics, resulting in a more complex concept of Quality Service (QoS), the ability predict QoS variation adapt flow traffic accordingly has become critical requirement for some use cases. For example Connected Automated Mobility applications could prediction reduce speed an autonomous vehicle if network performance is going deteriorate, information needs be conveyed. Current...
Ultra-Reliable Low Latency 5G applications require Edge implementation deep in access networks, resulting the need for inter-Edge Server application mobility. This paper identifies methodology zero-downtime
Network slicing as a key feature of 5G is supported by 5G-VINNI end-to-end Facility to validate the performance services and use cases operating trials required Verticals. This document contains architecture supporting systems for Sites be able implement with Slicing. Slicing design are mainly based on 3GPP specifications, but also taking into consideration work in other standardization bodies (SDOs) vertical requirements evolutions. The enhancements learned during implementation Verticals...