文献类型：期刊文献

英文题名：Development of a novel noninvasive quantitative method to monitor Siraitia grosvenorii cell growth and browning degree using an integrated computer-aided vision technology and machine learning

作者：Zhu, Xiaofeng[1,2];Mohisn, Ali[1,2];Zaman, Waqas Qamar[3];Liu, Zebo[1,2];Wang, Zejian[1,2];Yu, Zhihong[4];Tian, Xiwei[1,2];Zhuang, Yingping[1,2];Guo, Meijin[1,2];Chu, Ju[1,2]

机构：[1]East China Univ Sci & Technol, State Key Lab Bioreactor Engn, Shanghai, Peoples R China;[2]East China Univ Sci & Technol, Sch Biotechnol, Shanghai, Peoples R China;[3]Natl Univ Sci & Technol NUST, Sch Civil & Environm Engn, Inst Environm Sci & Engn, Islamabad, Pakistan;[4]East China Univ Sci & Technol, Sch Art Design & Media, Shanghai, Peoples R China

年份：2021

卷号：118

期号：10

起止页码：4092

外文期刊名：BIOTECHNOLOGY AND BIOENGINEERING

收录：;EI(收录号：20213110703697);WOS:【SCI-EXPANDED(收录号:WOS:000678120700001)】；

基金：Fundamental Research Funds for the China Central Universities, Grant/Award Numbers: No.22221818014, No.22221817014; Higher Education Discipline Innovation Project, Grant/Award Number: B18022; National Key Research and Development Program of China, Grant/Award Number: 2018YFA0900300

语种：英文

外文关键词：biomass; browning degree; computer-aided vision technology; noninvasive quantitative method; Siraitia grosvenorii

摘要：The rapid, accurate and noninvasive detection of biomass and plant cell browning can provide timely feedback on cell growth in plant cell culture. In this study, Siraitia grosvenorii suspension cells were taken as an example, a phenotype analysis platform was successfully developed to predict the biomass and the degree of cell browning based on the color changes of cells in computer-aided vision technology. First, a self-made laboratory system was established to obtain images. Then, matrices were prepared from digital images by a self-developed high-throughput image processing tool. Finally, classification models were used to judge different cell types, and then a semi-supervised classification to predict different degrees of cell browning. Meanwhile, regression models were developed to predict the plant cell mass. All models were verified with a good agreement by biological experiments. Therefore, this method can be applied for low-cost biomass estimation and browning degree quantification in plant cell culture.