Diagnosis and prognostication in medical imaging using AI

Presenter: Ida Häggström, Associate Professor at the unit of Computer Vision and Medical Image Analysis, dept. of Electrical Engineering at Chalmers University of Technology.

Abstract: The field of medical image analysis is makinggreat strides in the era of deep learning (DL), with a wide range of problemsbeing addressed using such techniques. Two considerable limitations to the useof DL in medical imaging is the lack of annotated data needed for supervisedlearning, and the oftentimes low level of explainability and missinguncertainty estimation of DL predictions. In my presentation, I will talk aboutthe use of weakly labeled data for cancer diagnosis and prognostication, and waysto improve prognostication with new survival modelling approaches. Furthermore,I will talk about the combination of DL and rule-based approaches forexplainability and uncertainty estimation in the detection of bone structuresin medical images.

‍

In compliance with GDPR consent requirements, presentations given in a Visual Intelligence context may be recorded with the consent of the speaker. All recordings are edited to remove all faces, names and voices of other participants. Questions and comments by the audience will hence be removed and will not appear in the recording.  With the freely given consent from the speaker, recorded presentation may be posted on the Visual Intelligence YouTube channel.

‍