A Deep Learning-Based Method for Automatic Assessment of Stomatal Index in Wheat Microscopic Images of Leaf Epidermis

Chuancheng Zhu; Yusong Hu; Hude Mao; Shumin Li; Fangfang Li; Congyuan Zhao; Lin Luo; Weizhen Liu; Xiaohui Yuan

doi:10.3389/fpls.2021.716784

A Deep Learning-Based Method for Automatic Assessment of Stomatal Index in Wheat Microscopic Images of Leaf Epidermis

Front Plant Sci. 2021 Sep 3:12:716784. doi: 10.3389/fpls.2021.716784. eCollection 2021.

Authors

Chuancheng Zhu¹, Yusong Hu¹, Hude Mao², Shumin Li², Fangfang Li², Congyuan Zhao¹, Lin Luo¹, Weizhen Liu^{1

3}, Xiaohui Yuan^{1

4

5}

Affiliations

¹ School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China.
² State Key Laboratory of Crop Stress Biology for Arid Areas, College of Plant Protection, Northwest A&F University, Shaanxi, China.
³ Chongqing Research Institute, Wuhan University of Technology, Chongqing, China.
⁴ Engineering Research Centre of Chinese Ministry of Education for Edible and Medicinal Fungi, Jilin Agricultural University, Changchun, China.
⁵ Jiaxing Key Laboratory for New Germplasm Breeding of Economic Mycology, Jiaxing, China.

Abstract

The stomatal index of the leaf is the ratio of the number of stomata to the total number of stomata and epidermal cells. Comparing with the stomatal density, the stomatal index is relatively constant in environmental conditions and the age of the leaf and, therefore, of diagnostic characteristics for a given genotype or species. Traditional assessment methods involve manual counting of the number of stomata and epidermal cells in microphotographs, which is labor-intensive and time-consuming. Although several automatic measurement algorithms of stomatal density have been proposed, no stomatal index pipelines are currently available. The main aim of this research is to develop an automated stomatal index measurement pipeline. The proposed method employed Faster regions with convolutional neural networks (R-CNN) and U-Net and image-processing techniques to count stomata and epidermal cells, and subsequently calculate the stomatal index. To improve the labeling speed, a semi-automatic strategy was employed for epidermal cell annotation in each micrograph. Benchmarking the pipeline on 1,000 microscopic images of leaf epidermis in the wheat dataset (Triticum aestivum L.), the average counting accuracies of 98.03 and 95.03% for stomata and epidermal cells, respectively, and the final measurement accuracy of the stomatal index of 95.35% was achieved. R ² values between automatic and manual measurement of stomata, epidermal cells, and stomatal index were 0.995, 0.983, and 0.895, respectively. The average running time (ART) for the entire pipeline could be as short as 0.32 s per microphotograph. The proposed pipeline also achieved a good transferability on the other families of the plant using transfer learning, with the mean counting accuracies of 94.36 and 91.13% for stomata and epidermal cells and the stomatal index accuracy of 89.38% in seven families of the plant. The pipeline is an automatic, rapid, and accurate tool for the stomatal index measurement, enabling high-throughput phenotyping, and facilitating further understanding of the stomatal and epidermal development for the plant physiology community. To the best of our knowledge, this is the first deep learning-based microphotograph analysis pipeline for stomatal index assessment.

Keywords: cell counting; convolutional network; stomata detection; stomatal index; transfer learning.