Medical Image Analysis: a computational approach in diabetes research

Speaker:  Abbas Cheddad – Karlskrona, Sweden
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Abstract

Medical imaging is a scientific field that applies digital image processing and analysis to medical scanned images in order to address a specific medical issue. It is a multidisciplinary area that bridges applied computer science to medical/biological sciences. Needless to say, medical imaging has proven to play a major role in visualisation of medical data. Medical images are generated using different technologies (scanners). For example, optical projection tomography (OPT) has emerged as a powerful three-dimensional (3D) scanning tool for the study of small biomedical specimen. However, there are challenges related to the process of image generation using OPT technology, which are manifested in a couple of quality concerns. The commercial OPT scanners come with some functionalities to partially address some of these concerns, but unfortunately, the provided solutions are neither adequate nor practical. Besides, other concerns remain unaddressed. In this lecture, I will expose my previous research conducted in collaboration between researchers in medical sciences and computer scientists. I will give a brief overview of the mechanics surrounding the OPT scanning process and its limitations. Subsequently, I will present computational tools that I conceived to further improve OPT image acquisition and tomographic reconstructions. The lecture will demonstrate my contributions from a computer science perspective but in conjunction with research linked to diabetes. The talk will conclude with examples of some final 3D reconstructions.

About this Lecture

Number of Slides:  36
Duration:  60 minutes
Languages Available:  Arabic, English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.