Human embryonic stem cell classification: random network with autoencoded feature extractor

Benjamin X Guan,Hengyue Liu,Bir Bhanu,Prue Talbot,Nikki Weng,Rajkumar Theagarajan

doi:10.1117/1.jbo.26.5.052913

Benjamin X Guan, Hengyue Liu + Show 4 more

Open Access

https://doi.org/10.1117/1.jbo.26.5.052913

Copy DOI

Abstract

.Significance: Automated understanding of human embryonic stem cell (hESC) videos is essential for the quantified analysis and classification of various states of hESCs and their health for diverse applications in regenerative medicine.Aim: This paper aims to develop an ensemble method and bagging of deep learning classifiers as a model for hESC classification on a video dataset collected using a phase contrast microscope.Approach: The paper describes a deep learning-based random network (RandNet) with an autoencoded feature extractor for the classification of hESCs into six different classes, namely, (1) cell clusters, (2) debris, (3) unattached cells, (4) attached cells, (5) dynamically blebbing cells, and (6) apoptotically blebbing cells. The approach uses unlabeled data to pre-train the autoencoder network and fine-tunes it using the available annotated data.Results: The proposed approach achieves a classification accuracy of and outperforms the state-of-the-art methods. Additionally, the approach has a very low training cost compared with the other deep-learning-based approaches, and it can be used as a tool for annotating new videos, saving enormous hours of manual labor.Conclusions: RandNet is an efficient and effective method that uses a combination of subnetworks trained using both labeled and unlabeled data to classify hESC images.

Highlights

Human embryonic stem cells are derived from the inner cell mass of developing blastocysts and possess two important properties: (1) self-renewal and (2) pluripotency.[1,2,3] Self-renewal is the ability to go through unlimited cycles of cell division, and pluripotency is the capability to differentiate into any cell type in the human body. human embryonic stem cell (hESC) are an important resource for regenerative medicine, basic research on human prenatal development, and toxicological testing of drugs and environmental chemicals
Self-renewal is the ability to go through unlimited cycles of cell division, and pluripotency is the capability to differentiate into any cell type in the human body. hESCs are an important resource for regenerative medicine, basic research on human prenatal development, and toxicological testing of drugs and environmental chemicals
It should be noted that the processing speed for our approach using all 33 subnetworks during inference is 6.25 frames per second (FPS) compared with 4.16 FPS using the approach proposed by Theagarajan et al.[19]

Summary

Introduction

Human embryonic stem cells (hESCs) are derived from the inner cell mass of developing blastocysts and possess two important properties: (1) self-renewal and (2) pluripotency.[1,2,3] Self-renewal is the ability to go through unlimited cycles of cell division, and pluripotency is the capability to differentiate into any cell type in the human body. hESCs are an important resource for regenerative medicine, basic research on human prenatal development, and toxicological testing of drugs and environmental chemicals. HESCs are an important resource for regenerative medicine, basic research on human prenatal development, and toxicological testing of drugs and environmental chemicals. Under their state of pluripotency, they can be maintained indefinitely.[4,5] hESC classification is an important task for toxicity studies. Through classification of hESCs in time-lapsed videos, biologists can analyze apoptotic behaviors in both cell clusters and individual cells under certain test chemicals. Understanding the behavior of hESCs is fundamental for medicinal and toxicological research.[5,6,7,8]

Objectives

Methods

Results

Conclusion