scholarly journals Machine Learning Approach to Automated Quality Identification of Human Induced Pluripotent Stem Cell Colony Images

2016 ◽  
Vol 2016 ◽  
pp. 1-15 ◽  
Author(s):  
Henry Joutsijoki ◽  
Markus Haponen ◽  
Jyrki Rasku ◽  
Katriina Aalto-Setälä ◽  
Martti Juhola

The focus of this research is on automated identification of the quality of human induced pluripotent stem cell (iPSC) colony images. iPS cell technology is a contemporary method by which the patient’s cells are reprogrammed back to stem cells and are differentiated to any cell type wanted. iPS cell technology will be used in future to patient specific drug screening, disease modeling, and tissue repairing, for instance. However, there are technical challenges before iPS cell technology can be used in practice and one of them is quality control of growing iPSC colonies which is currently done manually but is unfeasible solution in large-scale cultures. The monitoring problem returns to image analysis and classification problem. In this paper, we tackle this problem using machine learning methods such as multiclass Support Vector Machines and several baseline methods together with Scaled Invariant Feature Transformation based features. We perform over 80 test arrangements and do a thorough parameter value search. The best accuracy (62.4%) for classification was obtained by using ak-NN classifier showing improved accuracy compared to earlier studies.

2020 ◽  
Vol 21 (19) ◽  
pp. 6997 ◽  
Author(s):  
Davide Rovina ◽  
Elisa Castiglioni ◽  
Francesco Niro ◽  
Sara Mallia ◽  
Giulio Pompilio ◽  
...  

The ultimate goal of precision disease modeling is to artificially recreate the disease of affected people in a highly controllable and adaptable external environment. This field has rapidly advanced which is evident from the application of patient-specific pluripotent stem-cell-derived precision therapies in numerous clinical trials aimed at a diverse set of diseases such as macular degeneration, heart disease, spinal cord injury, graft-versus-host disease, and muscular dystrophy. Despite the existence of semi-adequate treatments for tempering skeletal muscle degeneration in dystrophic patients, nonischemic cardiomyopathy remains one of the primary causes of death. Therefore, cardiovascular cells derived from muscular dystrophy patients’ induced pluripotent stem cells are well suited to mimic dystrophin-associated cardiomyopathy and hold great promise for the development of future fully effective therapies. The purpose of this article is to convey the realities of employing precision disease models of dystrophin-associated cardiomyopathy. This is achieved by discussing, as suggested in the title echoing William Shakespeare’s words, the settlements (or “leagues”) made by researchers to manage the constraints (“betwixt mine eye and heart”) distancing them from achieving a perfect precision disease model.


2020 ◽  
Vol 7 (4) ◽  
pp. 133
Author(s):  
Xiufang Guo ◽  
Agnes Badu-Mensah ◽  
Michael C. Thomas ◽  
Christopher W. McAleer ◽  
James J. Hickman

In vitro generation of functional neuromuscular junctions (NMJs) utilizing the same induced pluripotent stem cell (iPSC) source for muscle and motoneurons would be of great value for disease modeling and tissue engineering. Although, differentiation and characterization of iPSC-derived motoneurons are well established, and iPSC-derived skeletal muscle (iPSC-SKM) has been reported, there is a general lack of systemic and functional characterization of the iPSC-SKM. This study performed a systematic characterization of iPSC-SKM differentiated using a serum-free, small molecule-directed protocol. Morphologically, the iPSC-SKM demonstrated the expression and appropriate distribution of acetylcholine, ryanodine and dihydropyridine receptors. Fiber type analysis revealed a mixture of human fast (Type IIX, IIA) and slow (Type I) muscle types and the absence of animal Type IIB fibers. Functionally, the iPSC-SKMs contracted synchronously upon electrical stimulation, with the contraction force comparable to myofibers derived from primary myoblasts. Most importantly, when co-cultured with human iPSC-derived motoneurons from the same iPSC source, the myofibers contracted in response to motoneuron stimulation indicating the formation of functional NMJs. By demonstrating comparable structural and functional capacity to primary myoblast-derived myofibers, this defined, iPSC-SKM system, as well as the personal NMJ system, has applications for patient-specific drug testing and investigation of muscle physiology and disease.


2016 ◽  
Vol 2016 ◽  
pp. 1-17 ◽  
Author(s):  
Daniel R. Bayzigitov ◽  
Sergey P. Medvedev ◽  
Elena V. Dementyeva ◽  
Sevda A. Bayramova ◽  
Evgeny A. Pokushalov ◽  
...  

Fundamental studies of molecular and cellular mechanisms of cardiovascular disease pathogenesis are required to create more effective and safer methods of their therapy. The studies can be carried out only when model systems that fully recapitulate pathological phenotype seen in patients are used. Application of laboratory animals for cardiovascular disease modeling is limited because of physiological differences with humans. Since discovery of induced pluripotency generating induced pluripotent stem cells has become a breakthrough technology in human disease modeling. In this review, we discuss a progress that has been made in modeling inherited arrhythmias and cardiomyopathies, studying molecular mechanisms of the diseases, and searching for and testing drug compounds using patient-specific induced pluripotent stem cell-derived cardiomyocytes.


2017 ◽  
Vol 37 (11) ◽  
pp. 2014-2025 ◽  
Author(s):  
Yang Lin ◽  
Chang-Hyun Gil ◽  
Mervin C. Yoder

The emergence of induced pluripotent stem cell (iPSC) technology paves the way to generate large numbers of patient-specific endothelial cells (ECs) that can be potentially delivered for regenerative medicine in patients with cardiovascular disease. In the last decade, numerous protocols that differentiate EC from iPSC have been developed by many groups. In this review, we will discuss several common strategies that have been optimized for human iPSC-EC differentiation and subsequent studies that have evaluated the potential of human iPSC-EC as a cell therapy or as a tool in disease modeling. In addition, we will emphasize the importance of using in vivo vessel-forming ability and in vitro clonogenic colony–forming potential as a gold standard with which to evaluate the quality of human iPSC-EC derived from various protocols.


2021 ◽  
Vol 33 (3) ◽  
pp. 221-227
Author(s):  
Karolina Plössl ◽  
Andrea Milenkovic ◽  
Bernhard H. F. Weber

Abstract The human retina is a highly structured and complex neurosensory tissue central to perceiving and processing visual signals. In a healthy individual, the close interplay between the neuronal retina, the adjacent retinal pigment epithelium and the underlying blood supply, the choriocapillaris, is critical for maintaining eyesight over a lifetime. An impairment of this delicate and metabolically highly active system, caused by genetic alteration, environmental impact or both, results in a multitude of pathological phenotypes of the retina. Understanding and treating these disease processes are motivated by a marked medical need in young as well as in older patients. While naturally occurring or gene-manipulated animal models have been used successfully in ophthalmological research for many years, recent advances in induced pluripotent stem cell technology have opened up new avenues to generate patient-derived retinal model systems. Here, we explore to what extent these cellular models can be useful to mirror human pathologies in vitro ultimately allowing to analyze disease mechanisms and testing treatment options in the cell type of interest on an individual patient-specific genetic background.


Sign in / Sign up

Export Citation Format

Share Document