A deep learning-integrated micro-CT image analysis pipeline for quantifying rice lodging resistance-related traits

TY - JOUR

T1 - A deep learning-integrated micro-CT image analysis pipeline for quantifying rice lodging resistance-related traits

AU - Wu, Di

AU - Wu, Dan

AU - Feng, Hui

AU - Duan, Lingfeng

AU - Dai, Guoxing

AU - Liu, Xiao

AU - Wang, Kang

AU - Yang, Peng

AU - Chen, Guoxing

AU - Gay, Alan P.

AU - Doonan, John H.

AU - Niu, Zhiyou

AU - Xiong, Lizhong

AU - Yang, Wanneng

N1 - Funding Information: This work was supported by grants from the National Key Research and Development Program ( 2020YFD1000904-1-3 ), the National Natural Science Foundation of China ( 31770397 ), the Fundamental Research Funds for the Central Universities ( 2662020ZKPY017 ), and UK grants supported by the Biotechnology and Biological Sciences Research Council ( BB/J004464/1 , BB/CAP1730/1 , BB/CSP1730/1 , and BB/R02118X/1 ). Publisher Copyright: © 2021 The Author(s)

PY - 2021/1/29

Y1 - 2021/1/29

N2 - Lodging is a common problem in rice, reducing its yield and mechanical harvesting efficiency. Rice architecture is a key aspect of its domestication and a major factor that limits its high productivity. The ideal rice culm structure, including major_axis_culm, minor axis_culm, and wall thickness_culm, is critical for improving lodging resistance. However, the traditional method of measuring rice culms is destructive, time consuming, and labor intensive. In this study, we used a high-throughput micro-CT-RGB imaging system and deep learning (SegNet) to develop a high-throughput micro-CT image analysis pipeline that can extract 24 rice culm morphological traits and lodging resistance-related traits. When manual and automatic measurements were compared at the mature stage, the mean absolute percentage errors for major_axis_culm, minor_axis_culm, and wall_thickness_culm in 104 indica rice accessions were 6.03%, 5.60%, and 9.85%, respectively, and the R2 values were 0.799, 0.818, and 0.623. We also built models of bending stress using culm traits at the mature and tillering stages, and the R2 values were 0.722 and 0.544, respectively. The modeling results indicated that this method can quantify lodging resistance nondestructively, even at an early growth stage. In addition, we also evaluated the relationships of bending stress to shoot dry weight, culm density, and drought-related traits and found that plants with greater resistance to bending stress had slightly higher biomass, culm density, and culm area but poorer drought resistance. In conclusion, we developed a deep learning-integrated micro-CT image analysis pipeline to accurately quantify the phenotypic traits of rice culms in ∼4.6 min per plant; this pipeline will assist in future high-throughput screening of large rice populations for lodging resistance. This study reports a deep learning-integrated micro-CT image analysis pipeline to rapidly (4.6 min per plant) and accurately quantify 24 phenotypic traits of rice culms and to visualize the 3D bending stress distribution of the culms. This approach will enable future high-throughput screening of large rice populations for lodging resistance.

AB - Lodging is a common problem in rice, reducing its yield and mechanical harvesting efficiency. Rice architecture is a key aspect of its domestication and a major factor that limits its high productivity. The ideal rice culm structure, including major_axis_culm, minor axis_culm, and wall thickness_culm, is critical for improving lodging resistance. However, the traditional method of measuring rice culms is destructive, time consuming, and labor intensive. In this study, we used a high-throughput micro-CT-RGB imaging system and deep learning (SegNet) to develop a high-throughput micro-CT image analysis pipeline that can extract 24 rice culm morphological traits and lodging resistance-related traits. When manual and automatic measurements were compared at the mature stage, the mean absolute percentage errors for major_axis_culm, minor_axis_culm, and wall_thickness_culm in 104 indica rice accessions were 6.03%, 5.60%, and 9.85%, respectively, and the R2 values were 0.799, 0.818, and 0.623. We also built models of bending stress using culm traits at the mature and tillering stages, and the R2 values were 0.722 and 0.544, respectively. The modeling results indicated that this method can quantify lodging resistance nondestructively, even at an early growth stage. In addition, we also evaluated the relationships of bending stress to shoot dry weight, culm density, and drought-related traits and found that plants with greater resistance to bending stress had slightly higher biomass, culm density, and culm area but poorer drought resistance. In conclusion, we developed a deep learning-integrated micro-CT image analysis pipeline to accurately quantify the phenotypic traits of rice culms in ∼4.6 min per plant; this pipeline will assist in future high-throughput screening of large rice populations for lodging resistance. This study reports a deep learning-integrated micro-CT image analysis pipeline to rapidly (4.6 min per plant) and accurately quantify 24 phenotypic traits of rice culms and to visualize the 3D bending stress distribution of the culms. This approach will enable future high-throughput screening of large rice populations for lodging resistance.

KW - deep learning

KW - high-throughput

KW - lodging resistance

KW - micro-CT

KW - rice culm

KW - SegNet

UR - http://www.scopus.com/inward/record.url?scp=85101291445&partnerID=8YFLogxK

U2 - 10.1016/j.xplc.2021.100165

DO - 10.1016/j.xplc.2021.100165

M3 - Article

C2 - 33898978

AN - SCOPUS:85101291445

JO - Plant Communications

JF - Plant Communications

SN - 2590-3462

M1 - 100165

ER -