Quantitative Medical Image Analysis Group

Ivana Išgum
Ivana Išgum

Associate Professor
Group Leader

Welcome to the page of the Quantitative Medical Image Analysis (QIA) group at the Image Sciences Institute, UMC Utrecht.
My group is focusing on the development of algorithms for quantitative analysis of medical images to enable automatic patient risk profiling and prognosis using techniques from the fields of image processing and machine learning. We currently have two areas of application: automatic cardiovascular risk assessment in CT scans, and MRI-based analysis of the developing neonatal brain. We collaborate closely with researchers and radiologists from the Department of Radiology and Medical Genetics on determination of cardiovascular risk, and with neonatologists from the Department of Neonatology on analysis of the neonatal brain.


Special session at ISBI 2018: Image Analysis of the Developing Brain


We are co-organizing a Special session on Image Analysis of the Developing Brain at IEEE ISBI, April 4-7, 2018 in Washington D.C. For details please follow this link.

MIDL conference


We are co-organizing Medical Imaging with Deep Learning (MIDL) conference in Amsterdam, July 4-6, 2018. More information is available on the conference website. We look forward to seeing you there!

New paper on deep learning analysis of the myocardium in CCTA for identification of functionally significant coronary artery stenosis


Our paper “Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis” has been published in Medical Image Analysis. The paper can be found here and here (Arxiv).

RSNA 2017 Magna Cum Laude award


Our educational exhibit on Deep Learning in Medical Image Analysis: What’s Next? has received a prestigious Magna Cum Laude award at the annual meeting of the Radiological Society of North America (RSNA) in Chicago. The exhibit can be viewed via this link.

New paper on automatic calcium scoring in lung cancer screening CT

Our paper “Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions” has been published in the IEEE Transactions on Medical Imaging. The paper can be found on IEEExplore and arXiv.