Assessing Biomaterial‐Induced Stem Cell Lineage Fate by Machine Learning‐Based Artificial Intelligence

Zhou, Yingying; Ping, Xianfeng; Guo, Yusi; Heng, Boon Chin; Wang, Yijun; Meng, Yanze; Jiang, Shengjie; Yan, Wei; Lai, Binbin; Zhang, Xuehui; Deng, Xuliang

doi:10.1002/adma.202210637

Cited by 6 publications

(1 citation statement)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With over 85% accuracy, the results demonstrated the potential of a computer vision based method for identifying stem cell differentiation ( Kim et al, 2022b ). More recently, Zhou et al introduced a predictive model for classifying hMSC differentiation lineages using the k-nearest neighbors (kNN) algorithm ( Zhou et al, 2023 ). It provided accurate prediction of lineage fate on different types of biomaterials as early as the first week of hMSCs culture with an overall accuracy of 90.63% on the test data set.…”

Section: Introductionmentioning

confidence: 99%

Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs)

Mai,

Luo,

Fasciano

et al. 2023

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs)

Mai,

Luo,

Fasciano

et al. 2023

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

show abstract

Transcriptome‐Optimized Hydrogel Design of a Stem Cell Niche for Enhanced Tendon Regeneration

Zhang,

Rao,

Wong

et al. 2024

Advanced Materials

View full text Add to dashboard Cite

Bioactive hydrogels have emerged as promising artificial niches for enhancing stem cell‐mediated tendon repair. However, a substantial knowledge gap remains regarding the optimal combination of niche features for targeted cellular responses, which often leads to lengthy development cycles and uncontrolled healing outcomes. To address this critical gap, an innovative, data‐driven materiomics strategy is developed. This approach is based on in‐house RNA‐seq data that integrates bioinformatics and mathematical modeling, which is a significant departure from traditional trial‐and‐error methods. It aims to provide both mechanistic insights and quantitative assessments and predictions of the tenogenic effects of adipose‐derived stem cells induced by systematically modulated features of a tendon‐mimetic hydrogel (TenoGel). The knowledge generated has enabled a rational approach for TenoGel design, addressing key considerations, such as tendon extracellular matrix concentration, uniaxial tensile loading, and in vitro pre‐conditioning duration. Remarkably, our optimized TenoGel demonstrated robust tenogenesis in vitro and facilitated tendon regeneration while preventing undesired ectopic ossification in a rat tendon injury model. These findings shed light on the importance of tailoring hydrogel features for efficient tendon repair. They also highlight the tremendous potential of the innovative materiomics strategy as a powerful predictive and assessment tool in biomaterial development for regenerative medicine.

show abstract

Identification of Adipogenic and Osteogenic Differentiation using transfer learning of ResNet-18

Mai,

Luo,

Wang

et al. 2023

2023 International Conference on Machine Learning and Applications (ICMLA)

View full text Add to dashboard Cite

Assessing Biomaterial‐Induced Stem Cell Lineage Fate by Machine Learning‐Based Artificial Intelligence

Cited by 6 publications

References 82 publications

Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs)

Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs)

Transcriptome‐Optimized Hydrogel Design of a Stem Cell Niche for Enhanced Tendon Regeneration

Identification of Adipogenic and Osteogenic Differentiation using transfer learning of ResNet-18

Contact Info

Product

Resources

About