Development of PaaS using AWS and Terraform for medical imaging analytics

Иванова, Десислава; Borovska, Plamenka; Zahov, Stefan

doi:10.1063/1.5082133

Cited by 9 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A fim de proporcionar uma maior acessibilidade desses modelos para o usuário final, é imprescindível pensar em formas de provisionar os recursos de uma maneira performática e de baixo custo. Nesse contexto, o uso de cloud computing para o provisionamento da infraestrutura de um sistema de análise de imagens médicas já foi estudado em [Ivanova et al (2018). Neste trabalho, foi utilizado uma plataforma baseada na provedora de nuvem AWS, em conjunto da linguagem terraform para descrever a infraestrutura seguindo os princípios de IaC (Infrastructure as Code).…”

Section: Trabalhos Relacionadosunclassified

Cloud computing para deploy de modelos de deep learning para a classificação de Retinopatia Diabética

Camargo

Künas

Navaux

2023

Anais Da XXIII Escola Regional De Alto Desempenho Da Região Sul (ERAD-RS 2023)

View full text Add to dashboard Cite

A retinopatia diabética (RD) é uma doença que vem crescendo a ritmos alarmantes. A falta de mão de obra especializada para diagnóstico, essencial para o tratamento bem-sucedido da doença, traz a necessidade de estudo de alternativas para o diagnóstico via meios computacionais. Neste trabalho, avaliamos o desempenho e custo de alternativas para o deploy de modelos de Deep Learning para classificação de RD. Através da escolha da melhor arquitetura, foi possível melhorar o desempenho em até 1,71 vezes, com redução de custo de 4,17%.

show abstract

Section: Trabalhos Relacionadosunclassified

Cloud computing para deploy de modelos de deep learning para a classificação de Retinopatia Diabética

Camargo

Künas

Navaux

2023

Anais Da XXIII Escola Regional De Alto Desempenho Da Região Sul (ERAD-RS 2023)

View full text Add to dashboard Cite

show abstract

“…Although there are authors that propose hardware specific configurations based on FPGAs and GPUs [12] [16], current tendencies propose the use of cloud computing platforms, especially public offerings [13] with special examples on solutions provided directly by main industry players in cloud [1]. However, in most of the cases, the use of clouds is limited to the storage and access of medical imaging data with low processing capabilities [2] [15].…”

Section: State Of the Artmentioning

confidence: 99%

“…The HPC infrastructure is the Prometheus supercomputer [10], which is located in the 174 th position of the TOP500 list (June 2019). Prometheus cluster provides REST API to interact with SLURM called Rimrock (Robust Remote Process Controller) 13 and PLGData service 14 to interact with the file system.…”

Section: Use Case: Segmentation Of Neuroblastoma Tumoursmentioning

confidence: 99%

Seamlessly Managing HPC Workloads Through Kubernetes

López-Huguet

Segrelles

Kasztelnik

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper describes an approach to integrate the jobs management of High Performance Computing (HPC) infrastructures in cloud architectures by managing HPC workloads seamlessly from the cloud job scheduler. The paper presents hpc-connector, an open source tool that is designed for managing the full life cycle of jobs in the HPC infrastructure from the cloud job scheduler interacting with the workload manager of the HPC system. The key point is that, thanks to running hpc-connector in the cloud infrastructure, it is possible to reflect in the cloud infrastructure, the execution of a job running in the HPC infrastructure managed by hpc-connector. If the user cancels the cloud-job, as hpc-connector catches Operating System (OS) signals (for example, SIGINT), it will cancel the job in the HPC infrastructure too. Furthermore, it can retrieve logs if requested. Therefore, by using hpc-connector, the cloud job scheduler can manage the jobs in the HPC infrastructure without requiring any special privilege, as it does not need changes on the Job scheduler. Finally, we perform an experiment training a neural network for automated segmentation of Neuroblastoma tumours in the Prometheus supercomputer using hpc-connector as a batch job from a Kubernetes infrastructure.

show abstract

“…Although there are authors that propose hardware specific configurations based on FPGAs and GPUs [77] [89], current tendencies propose the use of cloud computing platforms, especially public offerings [83] with special examples on solutions provided directly by main industry players in cloud [10]. However, in most of the cases, the use of clouds is limited to the storage and access of medical imaging data with low processing capabilities [27][88].…”

Section: State Of the Artmentioning

confidence: 99%

Elastic, Interoperable and Container-based Cloud Infrastructures for High Performance Computing

Huguet¹

View full text Add to dashboard Cite

show abstract

Development of PaaS using AWS and Terraform for medical imaging analytics

Cited by 9 publications

References 0 publications

Cloud computing para deploy de modelos de deep learning para a classificação de Retinopatia Diabética

Cloud computing para deploy de modelos de deep learning para a classificação de Retinopatia Diabética

Seamlessly Managing HPC Workloads Through Kubernetes

Elastic, Interoperable and Container-based Cloud Infrastructures for High Performance Computing

Contact Info

Product

Resources

About