Individual Research Project 09

Clinical image processing and Big Data analysis

Martino Andrea Scarpolini – ESR 09
Big Data science refers to the massive amounts of multiple digital data sets that are captured, collected, integrated, and analysed. We intend to bring cutting edge frameworks and techniques in order to maximize Big Data potentials for knowledge discovery in Medical Digital Imaging field, with special focus on cardiovascular diseases (aortic aneurysm). Starting from a set of image repositories, populated with millions of images collected during 18 years of health care services provisioning, either for research and public health, the ESR will build an intelligent image-related features processing system, applying advanced analytics to features extracted from diagnostic and procedural imaging. Tasks related to image processing & knowledge management could be the proposal of Feature candidate, located in set of similar images, a semi-Autonomous feature classification, identification and extraction and finally compound figure separation. The goal in applying these techniques to large numbers of images in our domain is to automatically detect abnormalities, create classifications/clustering of abnormal cases, generate people segmentation based upon phenotypes, identify phenotypes in the images that can be used for automatic disease classification, foster an image-based diagnosis for “precision medicine”, predict patients at risk for disease and support evidence-based medicine. Big data analytics in imaging field is crucial and difficult due to large imaging data to manage for a single patient. In modern hospitals data is consolidated in large PACS (Picture Archive and Communication Systems) installations. Data is related to the EHR (Electronic Health Record) environment by means of standard protocols and taxonomy. Every patient can have multiple studies related to a single pathology, and studies can have hundreds or thousands of images to be analysed. The proposed system must work in parallel with the installed systems (EHR and PACS) thanks to the DICOM (Digital and Communication in Medicine) standard protocol and HL7 (Health level 7) that permit to retrieve, analyse and compare data and are compatible with PACS or VNA (Vendor Neutral Archives) archives and EHR systems. Big data analytics has the potential to transform the way healthcare providers use technologies to gain insight from their clinical and other data repositories in order to make informed decisions.

Expected Results

  • Improved clinical operations by finding out existing but currently unanalysed patient-related health and medical data.
  • Better research effectiveness in finding more clinically relevant outcomes.
  • Better ease of access to information assets for interested parties.
  • A deeper understanding of outcomes of the observed processes.
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 859836
Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google