Breast cancer is the most common cancer in women worldwide: more than 1.6 Mio. cancers are diagnosed per year according to WHO cancer statistics. At Karlsruhe Institute of Technology an automated method for multimodal image registration is developed. The registration allows localizing suspicious tissue structures in all modalities at a glance. Using this approach the advantages of modalities may be combined. Our method therefore contributes to computer aided multimodal diagnosis of breast cancer. The challenges for the im-age registration are the severe differences in patient positioning and compression state of the breast during examination. In order to overcome these challenges we apply sophisticated patient-specific biomechanical models of the breast to simulate the tissue deformation when subject to compression.
Digital breast tomosynthesis (DBT) is an emerging technology which provides 3D information of the com-pressed breast anatomy. In a joint HEiKA research project (https://www.heika-research.de/) in collaboration with the Medical Faculty Mannheim of the University Heidelberg, we apply this new modality to gain a deeper knowledge of the complex breast deformation and raise the accuracy of image registration methods to a new clinically applicable level.
The tasks of the student assistant include developing methods for data exchange and ground truth annota-tion by radiologists. Furthermore he/she supports the development of the fundamental algorithms of the proposed image registration methods, e.g. by developing and evaluating an automated image segmentation and build up patient-specific biomechanical models of the breast.
• Development of data exchange and annotation methods for clinical datasets.
• Development of image registration method involving 3D image processing and segmentation, ex-tension of biomechanical model and simulation environment, optimization and development of appropriate evaluation methods for clinical datasets.
- Programming skills in MATLAB required
- Interest in medical imaging and medical image processing, in particular image segmentation and im-age registration
- Basic knowledge in (bio-)mechanical simulations / Finite Element simulations beneficial.
According to prior agreement, up to 40 hours/month
Torsten Hopp, torsten hoppAty5∂kit edu