Scalable pCT Image Reconstruction Delivered as a Cloud Service - 2018


We describe a cloud-based medical image reconstruction service designed to meet a true-time and daily demand to reconstruct thousands of pictures from proton cancer treatment facilities worldwide. Rapid reconstruction of a 3-dimensional Proton Computed Tomography (pCT) image will require the transfer of a hundred GB of information and use of approximately one hundred twenty GPU-enabled compute nodes. The nature of proton therapy means that that demand for such a service is sporadic and comes from potentially hundreds of clients worldwide. We thus explore the utilization of a business cloud as a scalable and value-economical platform for pCT reconstruction. To handle the high performance requirements of this application we have a tendency to leverage Amazon Web Services' GPU-enabled cluster resources that are provisioned with high performance networks between nodes. To support episodic demand, we have a tendency to develop an on-demand multi-user provisioning service which will dynamically provision and resize clusters primarily based on image reconstruction requirements, priorities, and wait times. We compare the performance of our pCT reconstruction service running on business cloud resources with that of the identical application on dedicated local high performance computing resources. We show that we tend to will achieve scalable and on-demand reconstruction of large scale pCT pictures for simultaneous multi-client requests, processing pictures in less than ten minutes for less than $10 per image.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : On-Device Scalable Image-Based Localization via Prioritized Cascade Search and Fast One-Many RANSAC ABSTRACT: We describe a complete on-device solution for large-scale image-based urban localisation. Compact image
PROJECT TITLE :MetaFlow: A Scalable Metadata Lookup Service for Distributed File Systems in Data Centers - 2018ABSTRACT:In massive-scale distributed file systems, efficient metadata operations are vital since most file operations
PROJECT TITLE :Efficient Scalable Median Filtering Using Histogram-Based Operations - 2018ABSTRACT:Median filtering could be a smoothing technique for noise removal in pictures. Whereas there are various implementations of median
PROJECT TITLE :Scalable Distributed Nonnegative Matrix Factorization with Block-Wise Updates - 2018ABSTRACT:Nonnegative Matrix Factorization (NMF) has been applied with nice success on a big selection of applications. As NMF is
PROJECT TITLE :Scalable Content-Aware Collaborative Filtering for Location Recommendation - 2018ABSTRACT:Location recommendation plays an essential role in serving to folks realize enticing places. Though recent research has studied

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry