Seminar October 17TH, 2023
Hours: 16:30 - 18:00
Stefan Pszczolkowski, PhD
Title: Clinical applications of Medical Image Analysis in Intracerebral Haemorrhage and Ataxia Telangiectasia
Abstract: The analysis of medical images is an integral part of healthcare engineering research and has the potential to inform clinical practice. In this talk, I will describe applications of medical image analysis in the context of a phase III international multi-centre clinical trial of intracerebral haemorrhage and a large imaging study investigating cross-sectional features of Ataxia Telangectasia.
Bio: Stefan Pszczolkowski obtained his Computer Engineering and MSc. degree from the Pontifical Catholic University of Chile in 2007, where he was part of the GRIMA group (now IALab). In 2015, he obtained his Ph.D. in Medical Image Analysis from the Department of Computing at Imperial College London. Then, from December of that year, he is a Postdoctoral Researcher at the School of Medicine, University of Nottingham. Stefan has ample experience in healthcare engineering research using medical images in a number of conditions such as Stroke, Ataxia Telangectasia, Depression and Parkinson's Disease.
Pamela Romero
Title: Skin Lesion Recognition with skin images from Chile
Abstract: Currently, skin cancer is one of the most common cancers in the world. The World Health Organization establishes that one third of diagnosed cancer corresponds to skin cancer. This research corresponds to an interdisciplinary work between engineering and medicine. It aims to classify skin lesions using images from a Chilean dataset (the first skin lesions dataset of Chile). The research works with Federated Learning and different Deep Learning tools are used and developed such as: Convolutional Neural Networks, Pre-trained Models, Transformer, etc.
Bio: Pamela Romero, master's student in Computer Science at Pontificia Universidad Católica de Chile. She studied electrical engineering at Pontificia Universidad Católica de Chile. Currently, Pamela works in the area of Deep Learning applied to medical images.
