Deep learning for complex displacement field measurement

作     者：LAN ShiHai SU Yong GAO ZeRen CHEN Ye TU Han ZHANG QingChuan 

作者机构：CAS Key Laboratory of Mechanical Behavior and Design of MaterialsDepartment of Modern MechanicsUniversity of Science and Technology of ChinaHefei 230027China Fuhuang Agile DeviceInc.Hefei 230000China 

出 版 物：《Science China(Technological Sciences)》 (中国科学（技术科学英文版）)

年 卷 期：2022年第65卷第12期

页      面：3039-3056页

核心收录：

学科分类：071011[理学-生物物理学] 0710[理学-生物学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.11872354,11627803,and 12102423) the National Science and Technology Major Project(Grant No.J2019-V-0006-0100) 

主　　题：displacement recovery complex deformation measurement traction force microscopy convolutional neural network 

摘      要：Traction force microscopy(TFM)is one of the most successful and broadly-used force probing technologies to quantify the mechanical forces in living *** displacement recovery of the fluorescent beads within the gel substrate,which serve as the fiducial markers,is one of the key *** traditional methods of extracting beads displacements,such as PTV,PIV,and DIC,persistently suffer from mismatching and loss of high-frequency information while dealing with the complex deformation around the focal ***,this information is crucial for the further analysis since the cells mainly transmit the force to the extracellular surroundings through focal *** this paper,we introduced convolutional neural network(CNN)to solve the *** have generated the fluorescent images of the non-deformable fluorescent beads and the displacement fields with different spatial complexity to form the training *** the special image feature of the fluorescent images and the deformation with high complexity,we have designed a customized network architecture called U-DICNet for the feature extraction and displacement *** numerical simulation and real experiment show that U-DICNet outperforms the traditional methods(PTV,PIV,and DIC).Particularly,the proposed U-DICNet obtains a more reliable result for the analysis of the local complex deformation around the focal adhesions.