Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs)
Human mesenchymal stem cells (hMSCs) are multipotent progenitor cells with the potential to differentiate into various cell types, including osteoblasts, chondrocytes, and adipocytes. These cells have been extensively employed in the field of cell-based therapies and regenerative medicine due to the...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-11-01
|
| Series: | Frontiers in Cell and Developmental Biology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcell.2023.1329840/full |
| _version_ | 1797447851363532800 |
|---|---|
| author | Maxwell Mai Shuai Luo Samantha Fasciano Timilehin Esther Oluwole Justin Ortiz Yulei Pang Shue Wang |
| author_facet | Maxwell Mai Shuai Luo Samantha Fasciano Timilehin Esther Oluwole Justin Ortiz Yulei Pang Shue Wang |
| author_sort | Maxwell Mai |
| collection | DOAJ |
| description | Human mesenchymal stem cells (hMSCs) are multipotent progenitor cells with the potential to differentiate into various cell types, including osteoblasts, chondrocytes, and adipocytes. These cells have been extensively employed in the field of cell-based therapies and regenerative medicine due to their inherent attributes of self-renewal and multipotency. Traditional approaches for assessing hMSCs differentiation capacity have relied heavily on labor-intensive techniques, such as RT-PCR, immunostaining, and Western blot, to identify specific biomarkers. However, these methods are not only time-consuming and economically demanding, but also require the fixation of cells, resulting in the loss of temporal data. Consequently, there is an emerging need for a more efficient and precise approach to predict hMSCs differentiation in live cells, particularly for osteogenic and adipogenic differentiation. In response to this need, we developed innovative approaches that combine live-cell imaging with cutting-edge deep learning techniques, specifically employing a convolutional neural network (CNN) to meticulously classify osteogenic and adipogenic differentiation. Specifically, four notable pre-trained CNN models, VGG 19, Inception V3, ResNet 18, and ResNet 50, were developed and tested for identifying adipogenic and osteogenic differentiated cells based on cell morphology changes. We rigorously evaluated the performance of these four models concerning binary and multi-class classification of differentiated cells at various time intervals, focusing on pivotal metrics such as accuracy, the area under the receiver operating characteristic curve (AUC), sensitivity, precision, and F1-score. Among these four different models, ResNet 50 has proven to be the most effective choice with the highest accuracy (0.9572 for binary, 0.9474 for multi-class) and AUC (0.9958 for binary, 0.9836 for multi-class) in both multi-class and binary classification tasks. Although VGG 19 matched the accuracy of ResNet 50 in both tasks, ResNet 50 consistently outperformed it in terms of AUC, underscoring its superior effectiveness in identifying differentiated cells. Overall, our study demonstrated the capability to use a CNN approach to predict stem cell fate based on morphology changes, which will potentially provide insights for the application of cell-based therapy and advance our understanding of regenerative medicine. |
| first_indexed | 2024-03-09T14:01:55Z |
| format | Article |
| id | doaj.art-666d0cc626c2409bbbd444b78702545e |
| institution | Directory Open Access Journal |
| issn | 2296-634X |
| language | English |
| last_indexed | 2024-03-09T14:01:55Z |
| publishDate | 2023-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cell and Developmental Biology |
| spelling | doaj.art-666d0cc626c2409bbbd444b78702545e2023-11-30T07:41:57ZengFrontiers Media S.A.Frontiers in Cell and Developmental Biology2296-634X2023-11-011110.3389/fcell.2023.13298401329840Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs)Maxwell Mai0Shuai Luo1Samantha Fasciano2Timilehin Esther Oluwole3Justin Ortiz4Yulei Pang5Shue Wang6Department of Mathematics, Southern Connecticut State University, New Haven, CT, United StatesDepartment of Chemistry, Chemical and Biomedical Engineering, University of New Haven, West Haven, CT, United StatesDepartment of Cellular and Molecular Biology, University of New Haven, West Haven, CT, United StatesDepartment of Chemistry, Chemical and Biomedical Engineering, University of New Haven, West Haven, CT, United StatesDepartment of Mechanical and Industrial Engineering, University of New Haven, West Haven, CT, United StatesDepartment of Mathematics, Southern Connecticut State University, New Haven, CT, United StatesDepartment of Chemistry, Chemical and Biomedical Engineering, University of New Haven, West Haven, CT, United StatesHuman mesenchymal stem cells (hMSCs) are multipotent progenitor cells with the potential to differentiate into various cell types, including osteoblasts, chondrocytes, and adipocytes. These cells have been extensively employed in the field of cell-based therapies and regenerative medicine due to their inherent attributes of self-renewal and multipotency. Traditional approaches for assessing hMSCs differentiation capacity have relied heavily on labor-intensive techniques, such as RT-PCR, immunostaining, and Western blot, to identify specific biomarkers. However, these methods are not only time-consuming and economically demanding, but also require the fixation of cells, resulting in the loss of temporal data. Consequently, there is an emerging need for a more efficient and precise approach to predict hMSCs differentiation in live cells, particularly for osteogenic and adipogenic differentiation. In response to this need, we developed innovative approaches that combine live-cell imaging with cutting-edge deep learning techniques, specifically employing a convolutional neural network (CNN) to meticulously classify osteogenic and adipogenic differentiation. Specifically, four notable pre-trained CNN models, VGG 19, Inception V3, ResNet 18, and ResNet 50, were developed and tested for identifying adipogenic and osteogenic differentiated cells based on cell morphology changes. We rigorously evaluated the performance of these four models concerning binary and multi-class classification of differentiated cells at various time intervals, focusing on pivotal metrics such as accuracy, the area under the receiver operating characteristic curve (AUC), sensitivity, precision, and F1-score. Among these four different models, ResNet 50 has proven to be the most effective choice with the highest accuracy (0.9572 for binary, 0.9474 for multi-class) and AUC (0.9958 for binary, 0.9836 for multi-class) in both multi-class and binary classification tasks. Although VGG 19 matched the accuracy of ResNet 50 in both tasks, ResNet 50 consistently outperformed it in terms of AUC, underscoring its superior effectiveness in identifying differentiated cells. Overall, our study demonstrated the capability to use a CNN approach to predict stem cell fate based on morphology changes, which will potentially provide insights for the application of cell-based therapy and advance our understanding of regenerative medicine.https://www.frontiersin.org/articles/10.3389/fcell.2023.1329840/fullHMSCsosteogenic differentiationadipogenic differentiationtransfer learningdeep learningCNN |
| spellingShingle | Maxwell Mai Shuai Luo Samantha Fasciano Timilehin Esther Oluwole Justin Ortiz Yulei Pang Shue Wang Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs) Frontiers in Cell and Developmental Biology HMSCs osteogenic differentiation adipogenic differentiation transfer learning deep learning CNN |
| title | Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs) |
| title_full | Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs) |
| title_fullStr | Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs) |
| title_full_unstemmed | Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs) |
| title_short | Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs) |
| title_sort | morphology based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells hmscs |
| topic | HMSCs osteogenic differentiation adipogenic differentiation transfer learning deep learning CNN |
| url | https://www.frontiersin.org/articles/10.3389/fcell.2023.1329840/full |
| work_keys_str_mv | AT maxwellmai morphologybaseddeeplearningapproachforpredictingadipogenicandosteogenicdifferentiationofhumanmesenchymalstemcellshmscs AT shuailuo morphologybaseddeeplearningapproachforpredictingadipogenicandosteogenicdifferentiationofhumanmesenchymalstemcellshmscs AT samanthafasciano morphologybaseddeeplearningapproachforpredictingadipogenicandosteogenicdifferentiationofhumanmesenchymalstemcellshmscs AT timilehinestheroluwole morphologybaseddeeplearningapproachforpredictingadipogenicandosteogenicdifferentiationofhumanmesenchymalstemcellshmscs AT justinortiz morphologybaseddeeplearningapproachforpredictingadipogenicandosteogenicdifferentiationofhumanmesenchymalstemcellshmscs AT yuleipang morphologybaseddeeplearningapproachforpredictingadipogenicandosteogenicdifferentiationofhumanmesenchymalstemcellshmscs AT shuewang morphologybaseddeeplearningapproachforpredictingadipogenicandosteogenicdifferentiationofhumanmesenchymalstemcellshmscs |