Abstract #2860

Automatic Brain MR Sequence Classification for Quality Control using Support Vector Machines and Convolutional Neural Networks

Luis A. Souto Maior Neto^1,2, Heather Charette^3,4, Marina Salluzzi^4,5, Mariana Bento^4,5, and Richard Frayne^1,2,4,5

¹Biomedical Engineering Graduate Program, University of Calgary, Calgary, AB, Canada, ²Seaman Family MR Research Centre, University of Calgary, Calgary, AB, Canada, ³Schulich School of Engineering, University of Calgary, Calgary, AB, Canada, ⁴Calgary Image Processing and Analysis Centre, Calgary, AB, Canada, ⁵Radiology, and Clinical Neurosciences, Hotchkiss Brain Institute, Calgary, AB, Canada

Medical imaging core lab centres face increasing quality control (QC) challenges as studies/trials become larger and more complex. Many QC processes are performed manually by experts, a time-consuming process. Most of the work on automated medical image QC in the literature focuses on text-based metadata correction, thus automated QC algorithms that are able to detect inconsistencies with image data only are needed. We propose two different methods for classification of anonymized MR images by acquisition method (T1-w, T2-w, T1 post contrast, or FLAIR). The classifiers were trained on the MICCAI-BRATS 2016 dataset and achieved accuracies of 85.7% and 93.8%.

This abstract and the presentation materials are available to members only; a login is required.

Join Here