Volume 11, Issue 12 e201800146
FULL ARTICLE

Segmentation of Drosophila heart in optical coherence microscopy images using convolutional neural networks

Lian Duan

Lian Duan

Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, Pennsylvania

Search for more papers by this author
Xi Qin

Xi Qin

Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, Pennsylvania

Search for more papers by this author
Yuanhao He

Yuanhao He

Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, Pennsylvania

Search for more papers by this author
Xialin Sang

Xialin Sang

Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, Pennsylvania

Department of Electrical Engineering and Computer Science, Hainan University, Haikou, China

Search for more papers by this author
Jinda Pan

Jinda Pan

School of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin, China

Search for more papers by this author
Tao Xu

Tao Xu

Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, Pennsylvania

State Key Laboratory of Software Engineering, Wuhan University, Wuhan, China

Search for more papers by this author
Jing Men

Jing Men

Department of Bioengineering, Lehigh University, Bethlehem, Pennsylvania

Search for more papers by this author
Rudolph E. Tanzi

Rudolph E. Tanzi

Genetics and Aging Research Unit, Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts

Search for more papers by this author
Airong Li

Airong Li

Genetics and Aging Research Unit, Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts

Search for more papers by this author
Yutao Ma

Yutao Ma

State Key Laboratory of Software Engineering, Wuhan University, Wuhan, China

Search for more papers by this author
Chao Zhou

Corresponding Author

Chao Zhou

Department of Electrical and Computer Engineering, Lehigh University, Bethlehem, Pennsylvania

Department of Bioengineering, Lehigh University, Bethlehem, Pennsylvania

Correspondence

Chao Zhou, Department of Electrical and Computer Engineering, Lehigh University, 19 Memorial Drive West, 18015, Bethlehem, Pennsylvania.

Email: [email protected]

Search for more papers by this author
First published: 10 July 2018
Citations: 11
Funding information Lehigh University, Grant/Award Number: Start-Up Fund; National Institutes of Health, Grant/Award Numbers: K99/R00-EB010071, R15-EB019704, R21- EY026380, R01-EB025209; National Key Basic Research Program of China, Grant/Award Number: 20014CB340404; National Science Foundation, Grant/Award Number: DBI-1455613

Abstract

Convolutional neural networks (CNNs) are powerful tools for image segmentation and classification. Here, we use this method to identify and mark the heart region of Drosophila at different developmental stages in the cross-sectional images acquired by a custom optical coherence microscopy (OCM) system. With our well-trained CNN model, the heart regions through multiple heartbeat cycles can be marked with an intersection over union of ~86%. Various morphological and dynamical cardiac parameters can be quantified accurately with automatically segmented heart regions. This study demonstrates an efficient heart segmentation method to analyze OCM images of the beating heart in Drosophila.

image

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.