Docent lecture – Improved detection and characterisation of breast cancer using multi-modal magnetic resonance imaging and novel computer-aided detection/diagnosis (CAD) techniques

Andrew Mehnert’s research focuses on the development of medical image analysis methods for clinical imaging applications. He has both academic and commercial research experience in the areas of optical microscopy (automated cytology), MRI (breast cancer, musculoskeletal sports injuries), and x-ray CT (forensic identification of human dental remains). His present research focus is on the development of computer-aided detection/diagnosis (CAD) tools for both optical microscopy (cervical cancer screening) and MRI (breast lesion detection and characterisation). In this talk Andrew will present an overview of the latter.

CAD systems for breast MRI presently fall short of automatically locating and classifying malignant lesions. Instead they automate many of the image processing and analysis functions that would otherwise have to be performed manually and visualise the data to aid interpretation. A recent meta-study concluded that “CAD in breast MRI has little influence on the sensitivity and specificity of experienced radiologists and therefore their interpretation remains essential”. A recent review concluded that breast MRI CAD needs to be based on “quantitative features extracted preferably from the automatically segmented 3D lesion” and a more comprehensive assessment of lesions based on features “derived from MR multi-parametric acquisitions”.

To this end Chalmers S2 and MedTech West are collaborating with MedTeQ at the University of Queensland, CBA at Uppsala University, and Queensland X-Ray to develop novel CAD techniques to improve the sensitivity and specificity of breast MRI, and concomitantly its clinical utility.

Our approach is based on combining multi-modal MRI with multi-parametric and multi-dimensional image analysis techniques. In particular we are developing methods to quantitatively characterise tissue morphology, microvasculature, and microstructure from spatially aligned multi-modal MR images including anatomical T1- and T2-weighted images, as well as images acquired using dynamic contrast-enhanced MRI, and diffusion-weighted imaging. We are also developing image analysis methods to automatically extract these features, segment (delineate) suspicious tissue, and classify the tissue as benign or malignant.

Results to date include a novel registration evaluation framework based on a biomechanical breast model that permits realistic simulation of tissue deformation, new spatiotemporal features for improved discrimination of benign and malignant lesions in dynamic contrast-enhanced MRI, and most recently the first fully automatic method for breast lesion detection and delineation. Our results suggest that improvements in the accuracy of breast MRI CAD are possible using multi-modal MRI coupled with multi-parametric and multi-dimensional image analysis techniques.

 (1) McClymont, D., Mehnert, A., Trakic, A., Kennedy, D., and Crozier, S. Journal of Magnetic Resonance Imaging, 39(4): 795-804, 2014

(2) Gal, Y., Mehnert, A., Bradley, A., Kennedy, D., and Crozier, S. Journal of Computer Assisted Tomography, 35(5):645-652, 2011

(3) Mehnert, A., Wildermoth, M., Crozier, S., Bengtsson, E., & Kennedy, D. Proceedings ISMRM 2011

 

 

Presented by Andrew Mehnert

 

Date:  Tuesday, June 3rd

 

Time: 11.00-12.00 pm

 

Location:  EB-salen, Hörsalsvägen 11, Chalmers