Cloud-based platform for trusted big data management in medical diagnosys and therapeutical threatment follow-up
The CARPUS project is based on the presence of specific know-how in POLITECMED (Polo Ligure delle Tecnologie Medicali) and follows an approach based on two consecutive actions: (1) the analysis of solutions, results and technologies made available by research institutions, and (2) their adaptation and integration in a service platform, together with the study of technological solutions available from SMEs.
Specifically, issues related to high-performance computing will be firstly addressed. Particular attention will be paid to high-performance systems able to satisfy the constraints of low cost and independence from specific vendors, which are important features for substantial market penetration of the proposed solutions. The project will develop algorithms and computing technologies that take advantage of current graphics cards (General Purpose Graphics Processing Unit Computing) and CPU computing performance (multicore). These computational units may be used both as individual computational resources with high parallelism and for the realization of distributed computing platforms (Cloud), thus making available advanced computing capabilities to analyze the data produced by the diagnostic devices and enabling more complex and evolved usage scenarios. It will be therefore possible to implement more complex innovative algorithms and handle considerable amounts of data, allowing the medical staff to have higher performance solutions and systems, enabled by the merge of heterogeneous data and supported by aid to diagnosis (CAD) to better support diagnostic activity.
The project will also tackle the management of large data sets, through the definition of innovative interfaces for their use, with innovative solutions compared to databases commonly used. For example, the non-relational or NoSQL databases are designed to take advantage of a distributed architecture and to work without the need for predefined table designs, that is, without having to define a priori the entities you want to relate. The unstructured datasets facilitate the application of machine learning algorithms.
A consolidated research group with a renowned academic and industrial profile.
Privacy & Cookies Policy
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Any cookies that may not be particularly necessary for the website to function and is used specifically to collect user personal data via analytics, ads, other embedded contents are termed as non-necessary cookies. It is mandatory to procure user consent prior to running these cookies on your website.