Abstract

Optical endomicroscopy (OEM) is an emerging medical imaging modality that enables real-time acquisition of in vivo and in situ optical biopsies, thereby accelerating the diagnosis of certain medical diseases. Specifically, lung diseases will be investigated in this project.

One of the diseases that this system can help manage is pneumonia, which is a leading cause of mortality among intensive care patients. A crucial aspect of treating pneumonia involves the rapid determination of both the presence and the gram status (quantity) of pathogenic bacteria in the distal lungs. The bacteria can be labeled with SmartProbes that emit fluorescence at predetermined wavelengths, causing the bacteria to appear as bright dots in the images. These images can assist medical practitioners in effectively identifying bacteria. However, these systems generate a substantial amount of data, necessitating a labor-intensive manual analysis process that can hinder real-time image analysis. To address this, machine learning approaches can be employed to analyze the images and detect bacteria in the distal lungs much more quickly than human practitioners, thereby reducing potential human errors and enabling real-time analysis.

In this presentation, I will outline some of my recent research into the development of novel machine-learning techniques for detecting bacteria in OEM images.

Biography

Mehmet Demirel received the M.Eng. degree in electrical and electronic engineering from The University of Manchester, Manchester, U.K., in 2021. He is currently pursuing a Ph.D. degree with the School of Engineering, The University of Edinburgh, Edinburgh, U.K. His research interests include machine learning and medical image processing. He is a member of the Institute for Imaging, Data, and Communications within the School.