3D U-Net for Segmentation of Plant Root MRI Images in Super-Resolution
This work addresses the challenge of non-invasive root system analysis for plant scientists, though it appears incremental as it builds on existing U-Net methods with modifications.
The paper tackled the problem of low resolution and high noise in plant root MRI images by segmenting scanned volumes into root and soil using a 3D U-Net in super-resolution, resulting in successful detection of most roots and identification of roots missed by human annotators.
Magnetic resonance imaging (MRI) enables plant scientists to non-invasively study root system development and root-soil interaction. Challenging recording conditions, such as low resolution and a high level of noise hamper the performance of traditional root extraction algorithms, though. We propose to increase signal-to-noise ratio and resolution by segmenting the scanned volumes into root and soil in super-resolution using a 3D U-Net. Tests on real data show that the trained network is capable to detect most roots successfully and even finds roots that were missed by human annotators. Our experiments show that the segmentation performance can be further improved with modifications of the loss function.