maskSLIC: Regional Superpixel Generation with Application to Local Pathology Characterisation in Medical Images
This work addresses the need for more accurate local pathology characterization in medical imaging, particularly for tumour analysis, but it is incremental as it builds directly on the existing SLIC method.
The authors tackled the problem of generating supervoxels within irregular masks in medical images by introducing maskSLIC, an extension of SLIC, which overcomes SLIC's issues and achieves significantly better results on the BRATS 2013 brain tumour challenge data, outperforming SLIC on 18 out of 20 scans with p=0.001.
Supervoxel methods such as Simple Linear Iterative Clustering (SLIC) are an effective technique for partitioning an image or volume into locally similar regions, and are a common building block for the development of detection, segmentation and analysis methods. We introduce maskSLIC an extension of SLIC to create supervoxels within regions-of-interest, and demonstrate,on examples from 2-dimensions to 4-dimensions, that maskSLIC overcomes issues that affect SLIC within an irregular mask. We highlight the benefits of this method through examples, and show that it is able to better represent underlying tumour subregions and achieves significantly better results than SLIC on the BRATS 2013 brain tumour challenge data (p=0.001) - outperforming SLIC on 18/20 scans. Finally, we show an application of this method for the analysis of functional tumour subregions and demonstrate that it is more effective than voxel clustering.