Jan-Jurre Mordang The computer as an independent reader of mammograms for breast cancer detection
In the Netherlands, 1 of every 7 women develops breast cancer during her lifetime and early detection of this type of cancer can reduce breast cancer related mortality.read more
Jan-Jurre Mordang The computer as an independent reader of mammograms for breast cancer detectionIn the Netherlands, 1 of every 7 women develops breast cancer during her lifetime and early detection of this type of cancer can reduce breast cancer related mortality. Breast cancer screening programs are implemented in most developed countries, and millions of mammograms are acquired each year leading to a substantial workload for radiologists, especially in screening programs with double reading. To reduce reading time and improve detection, computer-aided detection (CAD) systems have been developed. These systems can analyze each mammographic image and localize suspicious regions.
One of the main limitations of current (commercial) CAD systems is that they show a large amount of false positive marks in each mammograms. These false positives arise because the CAD system are set to operate at a very high sensitivity such that hardly any cancers are missed, reducing its specificity. Therefore, current CAD systems should be developed further to achieve a comparable performance as radiologists. In this thesis, we have focused on the development of a stand-alone CAD system where our general goal was to optimize this system for the detection of calcifications, the earliest signs of breast cancer in mammography.
Date, time and location PhD defense
- Date: 11 December 2018
- Time: 12.30 hrs
- Location: Radboud Universiteit, Academiezaal Aula, Comeniuslaan 2
Jan-Jurre Mordang (1988) obtained in 2011 his masterdegree in Medical Engineering. He carried out the above doctoral research at the department of Radiology, within the Diagnostic Image Analysis Group. Currently, he is working at ScreenPoint Medical, a company that develops deep learning and image analysis technology for automated reading of mammograms and digital breast tomosynthesis.
- Promotor(s): Prof. N. Karssemeijer, Prof. G.J. den Heeten
- Co-promotor(s): M. Broeders, PhD