Quality Control of Human Pluripotent Stem Cell Colonies by Computational Image Analysis Using Convolutional Neural Networks
Human pluripotent stem cells are promising for a wide range of research and therapeutic purposes. Their maintenance in culture requires the deep control of their pluripotent and clonal status. A non-invasive method for such control involves day-to-day observation of the morphological changes, along...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/24/1/140 |
| _version_ | 1797625707463966720 |
|---|---|
| author | Anastasiya Mamaeva Olga Krasnova Irina Khvorova Konstantin Kozlov Vitaly Gursky Maria Samsonova Olga Tikhonova Irina Neganova |
| author_facet | Anastasiya Mamaeva Olga Krasnova Irina Khvorova Konstantin Kozlov Vitaly Gursky Maria Samsonova Olga Tikhonova Irina Neganova |
| author_sort | Anastasiya Mamaeva |
| collection | DOAJ |
| description | Human pluripotent stem cells are promising for a wide range of research and therapeutic purposes. Their maintenance in culture requires the deep control of their pluripotent and clonal status. A non-invasive method for such control involves day-to-day observation of the morphological changes, along with imaging colonies, with the subsequent automatic assessment of colony phenotype using image analysis by machine learning methods. We developed a classifier using a convolutional neural network and applied it to discriminate between images of human embryonic stem cell (hESC) colonies with “good” and “bad” morphological phenotypes associated with a high and low potential for pluripotency and clonality maintenance, respectively. The training dataset included the phase-contrast images of hESC line H9, in which the morphological phenotype of each colony was assessed through visual analysis. The classifier showed a high level of accuracy (89%) in phenotype prediction. By training the classifier on cropped images of various sizes, we showed that the spatial scale of ~144 μm was the most informative in terms of classification quality, which was an intermediate size between the characteristic diameters of a single cell (~15 μm) and the entire colony (~540 μm). We additionally performed a proteomic analysis of several H9 cell samples used in the computational analysis and showed that cells of different phenotypes differentiated at the molecular level. Our results indicated that the proposed approach could be used as an effective method of non-invasive automated analysis to identify undesirable developmental anomalies during the propagation of pluripotent stem cells. |
| first_indexed | 2024-03-11T10:00:07Z |
| format | Article |
| id | doaj.art-aa65f796e8f84af3acccadaef3a2aaea |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-11T10:00:07Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-aa65f796e8f84af3acccadaef3a2aaea2023-11-16T15:29:57ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-12-0124114010.3390/ijms24010140Quality Control of Human Pluripotent Stem Cell Colonies by Computational Image Analysis Using Convolutional Neural NetworksAnastasiya Mamaeva0Olga Krasnova1Irina Khvorova2Konstantin Kozlov3Vitaly Gursky4Maria Samsonova5Olga Tikhonova6Irina Neganova7Mathematical Biology and Bioinformatics Lab, Peter the Great St. Petersburg Polytechnic University, 195251 Saint Petersburg, RussiaInstitute of Cytology, 194064 Saint Petersburg, RussiaFaculty of Biology, Saint-Petersburg State University, 199034 Saint Petersburg, RussiaMathematical Biology and Bioinformatics Lab, Peter the Great St. Petersburg Polytechnic University, 195251 Saint Petersburg, RussiaIoffe Institute, 194021 Saint Petersburg, RussiaMathematical Biology and Bioinformatics Lab, Peter the Great St. Petersburg Polytechnic University, 195251 Saint Petersburg, RussiaInstitute of Biomedical Chemistry, 119121 Moscow, RussiaInstitute of Cytology, 194064 Saint Petersburg, RussiaHuman pluripotent stem cells are promising for a wide range of research and therapeutic purposes. Their maintenance in culture requires the deep control of their pluripotent and clonal status. A non-invasive method for such control involves day-to-day observation of the morphological changes, along with imaging colonies, with the subsequent automatic assessment of colony phenotype using image analysis by machine learning methods. We developed a classifier using a convolutional neural network and applied it to discriminate between images of human embryonic stem cell (hESC) colonies with “good” and “bad” morphological phenotypes associated with a high and low potential for pluripotency and clonality maintenance, respectively. The training dataset included the phase-contrast images of hESC line H9, in which the morphological phenotype of each colony was assessed through visual analysis. The classifier showed a high level of accuracy (89%) in phenotype prediction. By training the classifier on cropped images of various sizes, we showed that the spatial scale of ~144 μm was the most informative in terms of classification quality, which was an intermediate size between the characteristic diameters of a single cell (~15 μm) and the entire colony (~540 μm). We additionally performed a proteomic analysis of several H9 cell samples used in the computational analysis and showed that cells of different phenotypes differentiated at the molecular level. Our results indicated that the proposed approach could be used as an effective method of non-invasive automated analysis to identify undesirable developmental anomalies during the propagation of pluripotent stem cells.https://www.mdpi.com/1422-0067/24/1/140human pluripotent stem cellspluripotencydeep learningconvolutional neural networksimage processing |
| spellingShingle | Anastasiya Mamaeva Olga Krasnova Irina Khvorova Konstantin Kozlov Vitaly Gursky Maria Samsonova Olga Tikhonova Irina Neganova Quality Control of Human Pluripotent Stem Cell Colonies by Computational Image Analysis Using Convolutional Neural Networks International Journal of Molecular Sciences human pluripotent stem cells pluripotency deep learning convolutional neural networks image processing |
| title | Quality Control of Human Pluripotent Stem Cell Colonies by Computational Image Analysis Using Convolutional Neural Networks |
| title_full | Quality Control of Human Pluripotent Stem Cell Colonies by Computational Image Analysis Using Convolutional Neural Networks |
| title_fullStr | Quality Control of Human Pluripotent Stem Cell Colonies by Computational Image Analysis Using Convolutional Neural Networks |
| title_full_unstemmed | Quality Control of Human Pluripotent Stem Cell Colonies by Computational Image Analysis Using Convolutional Neural Networks |
| title_short | Quality Control of Human Pluripotent Stem Cell Colonies by Computational Image Analysis Using Convolutional Neural Networks |
| title_sort | quality control of human pluripotent stem cell colonies by computational image analysis using convolutional neural networks |
| topic | human pluripotent stem cells pluripotency deep learning convolutional neural networks image processing |
| url | https://www.mdpi.com/1422-0067/24/1/140 |
| work_keys_str_mv | AT anastasiyamamaeva qualitycontrolofhumanpluripotentstemcellcoloniesbycomputationalimageanalysisusingconvolutionalneuralnetworks AT olgakrasnova qualitycontrolofhumanpluripotentstemcellcoloniesbycomputationalimageanalysisusingconvolutionalneuralnetworks AT irinakhvorova qualitycontrolofhumanpluripotentstemcellcoloniesbycomputationalimageanalysisusingconvolutionalneuralnetworks AT konstantinkozlov qualitycontrolofhumanpluripotentstemcellcoloniesbycomputationalimageanalysisusingconvolutionalneuralnetworks AT vitalygursky qualitycontrolofhumanpluripotentstemcellcoloniesbycomputationalimageanalysisusingconvolutionalneuralnetworks AT mariasamsonova qualitycontrolofhumanpluripotentstemcellcoloniesbycomputationalimageanalysisusingconvolutionalneuralnetworks AT olgatikhonova qualitycontrolofhumanpluripotentstemcellcoloniesbycomputationalimageanalysisusingconvolutionalneuralnetworks AT irinaneganova qualitycontrolofhumanpluripotentstemcellcoloniesbycomputationalimageanalysisusingconvolutionalneuralnetworks |