Robust Skeletonization for Plant Root Structure Reconstruction from MRI
This work addresses a domain-specific problem in plant science for researchers needing accurate root analysis from MRI data, but it appears incremental as it builds on existing segmentation and skeletonization techniques.
The paper tackles the challenge of reconstructing plant root structures from low-resolution, noisy MRI scans by proposing a two-stage approach combining semantic segmentation and 3D skeletonization, achieving evaluation on 22 MRI scans compared to human expert reconstructions.
Structural reconstruction of plant roots from MRI is challenging, because of low resolution and low signal-to-noise ratio of the 3D measurements which may lead to disconnectivities and wrongly connected roots. We propose a two-stage approach for this task. The first stage is based on semantic root vs. soil segmentation and finds lowest-cost paths from any root voxel to the shoot. The second stage takes the largest fully connected component generated in the first stage and uses 3D skeletonization to extract a graph structure. We evaluate our method on 22 MRI scans and compare to human expert reconstructions.