TY - JOUR
T1 - Usiigaci
T2 - Instance-aware cell tracking in stain-free phase contrast microscopy enabled by machine learning
AU - Tsai, Hsieh Fu
AU - Gajda, Joanna
AU - Sloan, Tyler F.W.
AU - Rares, Andrei
AU - Shen, Amy Q.
N1 - Funding Information:
This work is supported by JSPS KAKENHI , Japan [Grant Number JP1700362 ]. H.-F. Tsai and A.Q. Shen also thank Okinawa Institute of Science and Technology Graduate University (OIST) , Japan for its financial support with subsidy funding from the Cabinet Office, Government of Japan. Funders had no role in study design, data collection, the decision to publish, or preparation of the manuscript. The authors acknowledge support from the Scientific Computing and Data Analysis Section, the Community Relations Section, and the Imaging Analysis Section of OIST Graduate University. The authors also thank Matterport Inc. for their Mask R-CNN implementation source code released under the MIT license for use in part of this work. The authors thank Mr. Emanuele Martini for his open-source BW_Jtrack ImageJ plugin. The authors acknowledge Ms. Tsai, Yi-Ching ( [email protected] ) and Ms. Shivani Sathish from Micro/Bio/Nanofluidics Unit at OIST for assistance in preparation of illustrations in this work. The authors thank Dr. Steven Aird, OIST’s technical editor for proofreading this article.
Publisher Copyright:
© 2019 The Authors
PY - 2019/1/1
Y1 - 2019/1/1
N2 - Stain-free, single-cell segmentation and tracking is tantamount to the holy grail of microscopic cell migration analysis. Phase contrast microscopy (PCM) images with cells at high density are notoriously difficult to segment accurately; thus, manual segmentation remains the de facto standard practice. In this work, we introduce Usiigaci, an all-in-one, semi-automated pipeline to segment, track, and visualize cell movement and morphological changes in PCM. Stain-free, instance-aware segmentation is accomplished using a mask regional convolutional neural network (Mask R-CNN). A Trackpy-based cell tracker with a graphical user interface is developed for cell tracking and data verification. The performance of Usiigaci is validated with electrotaxis of NIH/3T3 fibroblasts. Usiigaci provides highly accurate cell movement and morphological information for quantitative cell migration analysis.
AB - Stain-free, single-cell segmentation and tracking is tantamount to the holy grail of microscopic cell migration analysis. Phase contrast microscopy (PCM) images with cells at high density are notoriously difficult to segment accurately; thus, manual segmentation remains the de facto standard practice. In this work, we introduce Usiigaci, an all-in-one, semi-automated pipeline to segment, track, and visualize cell movement and morphological changes in PCM. Stain-free, instance-aware segmentation is accomplished using a mask regional convolutional neural network (Mask R-CNN). A Trackpy-based cell tracker with a graphical user interface is developed for cell tracking and data verification. The performance of Usiigaci is validated with electrotaxis of NIH/3T3 fibroblasts. Usiigaci provides highly accurate cell movement and morphological information for quantitative cell migration analysis.
KW - Convolutional neural network
KW - Instance-aware segmentation
KW - Machine learning
KW - Phase contrast microscopy
KW - Single-cell migration
KW - Stain-free cell tracking
UR - http://www.scopus.com/inward/record.url?scp=85062715158&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062715158&partnerID=8YFLogxK
U2 - 10.1016/j.softx.2019.02.007
DO - 10.1016/j.softx.2019.02.007
M3 - Article
AN - SCOPUS:85062715158
SN - 2352-7110
VL - 9
SP - 230
EP - 237
JO - SoftwareX
JF - SoftwareX
ER -