Digitally Deconstructing Leaves in 3D Using X-ray Microcomputed Tomography and Machine Learning

Premise of the study: X-ray microcomputed tomography (microCT) can be used to measure 3D leaf internal anatomy, providing a holistic view of tissue organisation. Previously, the substantial time needed for segmenting multiple tissues limited this technique to small datasets, restricting its utility for phenotyping experiments and limiting our confidence in the conclusion of these studies due to low replication numbers. Methods and Results: We present a Python codebase for random-forest machine learning segmentation and 3D leaf anatomical traits quantification which dramatically reduces the time required to process leaf microCT scans. By training the model on 6 hand segmented image slices out of >1500 in the full dataset, it achieves >90% accuracy in background and tissue segmentation, including veins and bundle sheaths grouped together, but not when taken separately. Conclusion: Overall, this 3D segmentation and quantification pipeline can reduce one of the major barriers to using microCT imaging in high-throughput plant phenotyping.