Extending SEEDS to a Supervoxel Algorithm for Medical Image Analysis
This work provides a faster and more accurate supervoxel algorithm for medical image segmentation, though it is incremental as it adapts an existing method to 3D.
The authors tackled the problem of generating supervoxels for medical image analysis by extending the 2D SEEDS superpixel algorithm to 3D volumes, resulting in 3D SEEDS, which accelerates generation by 10 times and improves the Dice score by +6.5% compared to SLIC.
In this work, we extend the SEEDS superpixel algorithm from 2D images to 3D volumes, resulting in 3D SEEDS, a faster, better, and open-source supervoxel algorithm for medical image analysis. We compare 3D SEEDS with the widely used supervoxel algorithm SLIC on 13 segmentation tasks across 10 organs. 3D SEEDS accelerates supervoxel generation by a factor of 10, improves the achievable Dice score by +6.5%, and reduces the under-segmentation error by -0.16%. The code is available at https://github.com/Zch0414/3d_seeds