University of Heidelberg
Faculty of Medicine Mannheim
University Hospital Mannheim
CKM receives DFG funding for Project "Prädiktion von Therapieansprechen und Outcome beim lokal fortgeschrittenen Rektum-Karzinom mittels Radiomics und Deep Learning: eine beispielhafte Anwendung für eine allgemein verwendbare, Deep Learning basierte Prozessierungs-Pipeline für die Bild-Klassifikation" read more.
Alena-Kathrin Schnurr presented on our research on AI in medical imaging @ Research Plus forum
read more
Dr. Mathias Davids wins the I. I. Rabi Award of the International Society for Magnetic Resonance in Medicine (ISMRM),
read more, article in local newspaper (Mannheimer Morgen)

If you have questions concerning a specific publication please use this form with subject 'information about publications' and giving the full citation in the message body.

Home > Publications > Abstract >

Quantitaive Assessment of Kidney Function using Dynamic Contrast Enhanced MRI - Steps towards an integrated software prototype

A. Anderlik, A. Munthe-Kaas, O. Oye, E. Eikefjord, J. Rorvik, D. Ulvang, F. Zöllner and A. Lundervold

Proceedings of the 6th International Symposium on Image and Signal Processing and Analysis,, pp.575-581

Renal diseases, caused by e.g. diabetes mellitus, hypertension or multiple cyst formations, can lead to kidney failure that requires renal replacement therapy (RRT). Early detection and treatment can delay or prevent this progression towards end-stage renal disease (ESRD). Worldwide an increasing number of people will in the near future suffer from ESRD, with dialysis or kidney transplantation as the costly therapeutic alternatives. In a clinical setting, the detection of renal failure (i.e. reduction in glomerular filtration rate, GFR) is a challenge, and today's methods (e.g. elevated serum creatinine and urine analysis) are very crude and cannot even differentiate between left and right kidney function. Magnetic resonance imaging methods such as DCE-MRI have proven to be a very promising tool for (semi)quantitative and localized assessment of renal function, representing a non-invasive procedure that most patients can tolerate. In order to fully realize the potential of data from such methods, a series of image processing and analysis steps are required, including image registration, segmentation, kidney compartment modeling and visualization. We present here methods and results from these steps, and describes how the processing pipeline has been integrated as a software prototype.

Contact: Prof. Dr. Frank Zöllner last modified: 01.07.2020
to top of page