Meeting Banner
Abstract #4725

Automatic Quantification of Haematoma and Surrounding Oedema in MRI of Acute Spontaneous Intracerebral Haemorrhage: Preliminary Results for the TICH-2 MRI Sub-study

Stefan Pszczolkowski1, Rebecca G. Gallagher2,3, Zhe K. Law1,4, Dewen Meng1, David J. Swienton2,5, Paul S. Morgan6, Philip M. Bath1, Nikola Sprigg1, and Robert A. Dineen1

1Division of Clinical Neuroscience, University of Nottingham, Nottingham, United Kingdom, 2Department of Neuroradiology, Nottingham University Hospitals, United Kingdom, 3Department of Radiology, Royal Derby Hospital, United Kingdom, 4Department of Medicine, National University of Malaysia, Malaysia, 5Imaging Department, Leicester Royal Infirmary, United Kingdom, 6Department of Medical Physics and Clinical Engineering, Nottingham University Hospitals, United Kingdom

In this work, we propose to take advantage of improved contrast seen on magnetic resonance (MR) images of patients with acute spontaneous intracerebral haemorrhage (SICH), and introduce an automated algorithm for haematoma and oedema segmentation from these images. To our knowledge, there is no previously proposed segmentation technique for SICH that utilises MR images directly. The method is based on k-means clustering of image intensities for haematoma segmentation and voxel-wise dynamic thresholding of hyper-intensities for oedema segmentation. Preliminary results using the Dice score metric to measure segmentation overlaps between labellings yielded by the proposed algorithm and five different expert raters show that our technique has the potential to be an effective way to automatically delineate haematoma and perihaematoma oedema extent directly from MR images.

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

Join Here