Automatic 3D cell segmentation of fruit parenchyma tissue from X-ray micro CT images using deep learning

BACKGROUND

High quality 3D information of the microscopic plant tissue morphology-the spatial organization of cells and intercellular spaces in tissues-helps in understanding physiological processes in a wide variety of plants and tissues. X-ray micro-CT is a valuable tool that is becoming increasingly available in plant research to obtain 3D microstructural information of the intercellular pore space and individual pore sizes and shapes of tissues. However, individual cell morphology is difficult to retrieve from micro-CT as cells cannot be segmented properly due to negligible density differences at cell-to-cell interfaces. To address this, deep learning-based models were trained and tested to segment individual cells using X-ray micro-CT images of parenchyma tissue samples from apple and pear fruit with different cell and porosity characteristics.

RESULTS

The best segmentation model achieved an Aggregated Jaccard Index (AJI) of 0.86 and 0.73 for apple and pear tissue, respectively, which is an improvement over the current benchmark method that achieved AJIs of 0.73 and 0.67. Furthermore, the neural network was able to detect other plant tissue structures such as vascular bundles and stone cell clusters (brachysclereids), of which the latter were shown to strongly influence the spatial organization of pear cells. Based on the AJIs, apple tissue was found to be easier to segment, as the porosity and specific surface area of the pore space are higher and lower, respectively, compared to pear tissue. Moreover, samples with lower pore network connectivity, proved very difficult to segment.

CONCLUSIONS

The proposed method can be used to automatically quantify 3D cell morphology of plant tissue from micro-CT instead of opting for laborious manual annotations or less accurate segmentation approaches. In case fruit tissue porosity or pore network connectivity is too low or the specific surface area of the pore space too high, native X-ray micro-CT is unable to provide proper marker points of cell outlines, and one should rely on more elaborate contrast-enhancing scan protocols.

Reconstruction of plant microstructure using distance weighted tessellation algorithm optimized by virtual segmentation

The accurate reconstruction model of plant microstructure is important for obtaining the mechanical properties of plant tissues. In this paper, a virtual segmentation technique is proposed to optimize Delaunay triangulation. Based on the optimized Delaunay triangulation, an Optimized Distance Weighted Tessellation (ODWT) algorithm is developed. Two different structures, namely carrot and retting maize vascular bundles, were reconstructed via the ODWT algorithm. The accuracy of ODWT is evaluated statistically by comparing with Centroid-based Voronoi Tessellation (CVT) and Area Weighted Tessellation (AWT). The results show that ODWT has distinct advantages over CVT and AWT. It is worth mentioning that ODWT has better performance than CVT when there exists large diversity in adjacent cell area. It is found that CVT and AWT fail to reconstruct cells with elongated and concave shapes, while ODWT shows excellent feasibility and reliability. Furthermore, ODWT is capable of establishing finite tissue boundary, which CVT and AWT have failed to realize. The purpose of this work is to develop an algorithm with higher accuracy to implement the preprocessing for further numerical study of plants properties. The comparison results of the simulated values of the longitudinal tensile modulus with the experimental value show that ODWT algorithm can improve the prediction accuracy of multi-scale models on mechanical properties.