InvitedTalkBernhardKainz2019

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Invited Talk by Dr. Bernhard Kainz

Bernhard

Dr. Bernhard Kainz

Faculty of Engineering, Imperial College London

  • Date: Tuesday, November 19th, 2019
  • Time: 11 AM
  • Location: TranslaTUM auditorium, room no. 22.00.1, Ismaninger Str. 22


Population imaging++

Abstract

Artificial Narrow Intelligence (ANI) including Machine Learning (ML) has the controversial potential to replace healthcare professionals in their jobs. ANI/ML technology has already the capacity to augment, educate and democratize expertise for medical front-line personnel, freeing up their time for difficult cases while making them better at their tasks in modern precision medicine. ANI/ML can make the quality of an individual's work better, resulting in better decision making in healthcare, faster diagnosis, improved patient communication, more efficient training and less mistakes.

In this talk I will shed some light on the looming AI bubble in Healthcare, discuss the potential of ML to complement human decision making in clinical applications and will provide an outlook for selected ML applications that have the potential to survive the coming AI winter. We will explore ML methods for population screening, where lack of training and limited expertise lead to missed early treatment opportunities and a high burden on patients and the healthcare system through the 'refer if unsure' approach. Our ML methods also show promising results for complementing sparse data in a meaningful way. I will briefly discuss the impact of ML on image reconstruction tasks that go beyond human capabilities and will conclude with an outlook into the future of autonomous agents in medical imaging, which have the potential to revolutionise patient monitoring and population screening through guided image acquisition.

Bio

Dr. Bernhard Kainz is a Senior Lecturer (= Associate Professor) in the Department of Computing at Imperial College London. He heads the human-in-the-loop computing group and he is one of four academics leading the Biomedical Image Analysis, BioMedIA Collaboratory. Human-in-the-loop computing research aims to equip humans with machine-like learning and perceptual abilities. Researchers in this domain believe that machines can complement human intelligence for maximum efficiency.

Bernhard co-creates intensively with King's College London, Division of Imaging Sciences and Biomedical Engineering, St. Thomas Hospital London and the department of Bioengineering at Imperial. He is a scientific adviser for ThinkSono Ltd., Affordable Imaging stream lead for the EPSRC Centre for Doctoral Training in Smart Medical Imaging, and involved in the UKRI Centre for Doctoral Training in Artificial Intelligence for Healthcare and the Innovate UK London AI Centre for value-based healthcare.

In 2013 he moved from Graz University of Technology in Austria to Imperial College London as FP7 Marie Skłodowska-Curie Fellow, working together with Prof. Daniel Rueckert and Prof. Jo Hajnal (KCL). Since then he is pioneering Human-in-the-loop computing methods in the EPSRC/Wellcome trust project iFind.

He finished his Ph.D. in the field of medical visualization, volume graphics and GPU algorithms in the team of Prof. Dieter Schmalstieg at the Institute for Computer Graphics and Vision at Graz University of Technology in Austria. This shaped his research interests towards the interconnection of medical image data acquisition, fast hardware accelerated medical image processing and interactive real-time algorithms.

WebEventForm
Title: Invited Talk by Dr. Bernhard Kainz
Date: 19 November 2019
Location: TranslaTUM? auditorium
Abstract: Artificial Narrow Intelligence (ANI) including Machine Learning (ML) has the controversial potential to replace healthcare professionals in their jobs. ANI/ML technology has already the capacity to augment, educate and democratize expertise for medical front-line personnel, freeing up their time for difficult cases while making them better at their tasks in modern precision medicine. ANI/ML can make the quality of an individual's work better, resulting in better decision making in healthcare, faster diagnosis, improved patient communication, more efficient training and less mistakes. In this talk I will shed some light on the looming AI bubble in Healthcare, discuss the potential of ML to complement human decision making in clinical applications and will provide an outlook for selected ML applications that have the potential to survive the coming AI winter. We will explore ML methods for population screening, where lack of training and limited expertise lead to missed early treatment opportunities and a high burden on patients and the healthcare system through the 'refer if unsure' approach. Our ML methods also show promising results for complementing sparse data in a meaningful way. I will briefly discuss the impact of ML on image reconstruction tasks that go beyond human capabilities and will conclude with an outlook into the future of autonomous agents in medical imaging, which have the potential to revolutionise patient monitoring and population screening through guided image acquisition.
Imageurl: newProfile_cropSmall--tojpeg_1479141100097_x1.jpg
Type: Hot
Videourl:  
Conferencelink:  


Edit | Attach | Refresh | Diffs | More | Revision r1.2 - 18 Nov 2019 - 13:50 - MagdaPaschali

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif