Automatic histogram-based segmentation of white matter hyperintensities using 3D FLAIR images


Share/Save/Bookmark

Simoes, Rita and Slump, Cornelis and Mönninghoff, Christoph and Wanke, Isabel and Dlugaj, Martha and Weimar, Christian (2012) Automatic histogram-based segmentation of white matter hyperintensities using 3D FLAIR images. In: Medical Imaging 2012: Computer-Aided Diagnosis, 4-9 February 2012, San Diego, CA, USA (pp. 83153k).

[img] PDF
Restricted to UT campus only
: Request a copy
1MB
Abstract:White matter hyperintensities are known to play a role in the cognitive decline experienced by patients suffering from neurological diseases. Therefore, accurately detecting and monitoring these lesions is of importance. Automatic methods for segmenting white matter lesions typically use multimodal MRI data. Furthermore, many methods use a training set to perform a classification task or to determine necessary parameters. In this work, we describe and evaluate an unsupervised segmentation method that is based solely on the histogram of FLAIR images. It approximates the histogram by a mixture of three Gaussians in order to find an appropriate threshold for white matter hyperintensities. We use a context-sensitive Expectation-Maximization method to determine the Gaussian mixture parameters. The segmentation is subsequently corrected for false positives using the knowledge of the location of typical FLAIR artifacts. A preliminary validation with the ground truth on 6 patients revealed a Similarity Index of 0.73 ± 0.10, indicating that the method is comparable to others in the literature which require multimodal MRI and/or a preliminary training step.
Item Type:Conference or Workshop Item
Copyright:© 2012 SPIE
Faculty:
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:http://purl.utwente.nl/publications/79875
Official URL:http://dx.doi.org/10.1117/12.911327
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page