Improved CAD for breast and prostate MRI

Computer-assisted detection/diagnosis for breast and prostate MRI

In Sweden the most frequently diagnosed cancer and the leading cause of cancer death in women is breast cancer whilst in men it is prostate cancer. This picture holds more generally for the developed world except that prostate cancer is the third leading cause of cancer death in men*. Magnetic resonance imaging (MRI) is being increasingly used clinically as a supplemental tool in the detection and characterisation of both cancers. In particular it is used for assessing the degree of progression, determining the most appropriate treatment, and for patient follow-up after cancer treatment. The clinical utility of prostate MRI is presently limited by the relatively low sensitivity (ability to detect cancer) and specificity (certainty that what was detected is cancer) of the traditionally used T2-weighted images. Similarly the clinical utility of breast MRI is presently limited by the poor to moderate specificity of the traditionally used dynamic contrast-enhanced (DCE) MRI.

MedTech West is a partner in developing novel CAD techniques to improve the sensitivity and specificity of MRI, and concomitantly its clinical utility, for both breast and prostate cancers.

Our approach

Our approach is based on combining multimodal magnetic resonance imaging with novel multiparametric and multidimensional image analysis techniques. In particular we are developing methods to quantitatively characterise tissue morphology, microvasculature, microstructure, and metabolism from spatially aligned multimodal MR images including anatomical T1- and T2-weighted images, as well as images acquired using DCE-MRI (perfusion imaging), diffusion-weighted imaging (DWI), susceptibility weighted imaging (SWI), and spectroscopic imaging (MRSI). We are also developing image analysis methods to automatically extract these features, segment (delineate) suspicious tissue, and classify the tissue as benign or malignant. The broad outcome from this project will be a collection of CAD tools for multimodal MRI that will permit more accurate detection and characterisation of both breast and prostate cancers. This technology not only has the potential to reduce the mortality from these diseases but also to improve morbidity through enhanced clinical management.

Research team

MedTech West partner

Dr. Andrew Mehnert, Department of Signals and Systems, Chalmers University of Technology.

Technical research partners

Prof. Mikael Persson, Department of Signals and Systems, Chalmers University of Technology.

Prof. Stuart Crozier, School of ITEE, The University of Queensland, Australia.

Prof. Ewert Bengtsson, Centre for Image Analysis, Uppsala University.

Clinical partners

Prof. Mikael Hellström, Department of Radiology, Sahlgrenska University Hospital.

Dominic Kennedy, Queensland X-Ray, Greenslopes Private Hospital, Australia.

Contact

For more information on this project, contact Henrik Mindedal at henrik.mindedal@medtechwest.se