CoSy seminar: "Automated analysis of medical images based on deep learning"
- Date: 20 May 2025, 12:15–13:00
- Location: Ångström Laboratory, Å4004
- Type: Seminar
- Lecturer: Anders Heyden
- Organiser: Department of Mathematics
- Contact person: Simon Wogel
Anders Heyden holds a seminar with the title "Automated analysis of medical images based on deep learning". Welcome!
Everyone is welcome and the first 40 people to register will be treated to a free lunch sandwich. If you do not want lunch, you are still welcome to join.
Register for a lunch sandwich (before Sunday 18 May).
Abstract: Machine learning and especially deep learning based on convolutional neural networks has recently gained a lot of attention in several different fields. I will talk about using deep learning for automated analysis and diagnosis in of medical images. I will present three different applications using three different imaging techniques. Firstly, I will talk about detection and grading of Prostate Cancer based on microscopic images of stained biopsies, so called digital pathology. Then, I will talk about detection of breast cancer based on ultrasound images taken by a portable (POCUS) ultrasound device. Finally, I will talk about detecting ischemia and estimating quantitative coronary angiography based on myocardial perfusion images obtained using scintigraphy. I will also talk about how to deal with the problem of not having an abundance of training data.
This is a lecture in the seminar series held by CIM (Centre for Interdisciplinary Mathematics).