Predicting quality decay in continuously passaged mesenchymal stem cells by detecting morphological anomalies

Takemoto, Yuto; Imai, Yasufumi; Kanie, Kei; Kato, Ryuji

doi:10.1016/j.jbiosc.2020.09.022

Cited by 9 publications

(18 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although our prediction can combine just two quality attribute evaluations simultaneously, it should be noted that such multiple non-invasive evaluations without cell consumption are never possible with the conventional cell assay methods. Moreover, considering that morphology-based cell quality prediction works have shown that it can predict various cell potencies [ 19 – 22 , 24 – 26 ], our prediction technology has the potential to cover more categories of potencies from the same image.…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, good varieties of training data for better machine learning must be collected; however, control of such balanced quality variation in the training data is also difficult in MSC data collection, as which donor cell data will be similar or different in prior cannot be identified. Consequently, to tackle such data unbalance issue, we reported one solution of introducing an anomaly detection approach for machine learning to effectively use unbalanced training data in cell morphology machine learning [ 25 , 26 ]. Our results in the present report added a new feature wherein morphological data can be shared for quality prediction machine learning between different types of MSCs, which implies that such unbalance of data may be covered by morphology data sharing.…”

Section: Discussionmentioning

confidence: 99%

“…Morphology of cells had been used as an important signature to check cells and is still employed worldwide as a cell status monitoring technique in cell manufacturing. Coupled with advanced image processing, morphological descriptors measured from cell images has been reported to show quantitative correlation with MSC’s quality attributes [ 17 – 26 ]. Moreover, the application of machine learning has aided in the realization of automatic linkages to utilize the image-derived morphological descriptors to predict the cell quality attributes that are obtained by invasive assays using only images, with high potentials as manufacturing supporting technology [ 24 – 26 ].…”

Section: Introductionmentioning

confidence: 99%

“…Coupled with advanced image processing, morphological descriptors measured from cell images has been reported to show quantitative correlation with MSC’s quality attributes [ 17 – 26 ]. Moreover, the application of machine learning has aided in the realization of automatic linkages to utilize the image-derived morphological descriptors to predict the cell quality attributes that are obtained by invasive assays using only images, with high potentials as manufacturing supporting technology [ 24 – 26 ]. Robust and high-performance morphology-based cell quality prediction methods for predicting cell growth rate have been reported in studies [ 22 , 25 ].…”

Section: Introductionmentioning

confidence: 99%

“…Further, even multiple osteogenic/adipogenic/chondrogenic differentiation potencies that can only be measured at the final stage of cell culture have been predicted in continuously passaged MSCs obtained from early morphological information [ 19 , 20 , 22 ]. Moreover, it has been found that even in the cases where quality attributes cannot be simply defined using single bio-marker measurements, overall anomaly can be detected via comparison of differences of multiple morphological parameters throughout the time course [ 25 , 26 ]. Taken together, such computer-assisted non-invasive morphology-based quality prediction approaches have high potential to solve the bottlenecks in cell manufacturing.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Morphological heterogeneity description enabled early and parallel non-invasive prediction of T-cell proliferation inhibitory potency and growth rate for facilitating donor selection of human mesenchymal stem cells

2022

Self Cite

View full text Add to dashboard Cite

Background Within the extensively developed therapeutic application of mesenchymal stem cells (MSCs), allogenic immunomodulatory therapy is among the promising categories. Although donor selection is a critical early process that can maximize the production yield, determining the promising candidate is challenging owing to the lack of effective biomarkers and variations of cell sources. In this study, we developed the morphology-based non-invasive prediction models for two quality attributes, the T-cell proliferation inhibitory potency and growth rate. Methods Eleven lots of mixing bone marrow-derived and adipose-derived MSCs were analyzed. Their morphological profiles and growth rates were quantified by image processing by acquiring 6 h interval time-course phase-contrast microscopic image acquisition. T-cell proliferation inhibitory potency was measured by employing flow cytometry for counting the proliferation rate of peripheral blood mononuclear cells (PBMCs) co-cultured with MSCs. Subsequently, the morphological profile comprising 32 parameters describing the time-course transition of cell population distribution was used for explanatory parameters to construct T-cell proliferation inhibitory potency classification and growth rate prediction models. For constructing prediction models, the effect of machine learning methods, parameter types, and time-course window size of morphological profiles were examined to identify those providing the best performance. Results Unsupervised morphology-based visualization enabled the identification of anomaly lots lacking T-cell proliferation inhibitory potencies. The best performing machine learning models exhibited high performances of predictions (accuracy > 0.95 for classifying risky lots, and RMSE < 1.50 for predicting growth rate) using only the first 4 days of morphological profiles. A comparison of morphological parameter types showed that the accumulated time-course information of morphological heterogeneity in cell populations is important for predicting the potencies. Conclusions To enable more consistent cell manufacturing of allogenic MSC-based therapeutic products, this study indicated that early non-invasive morphology-based prediction can facilitate the lot selection process for effective cell bank establishment. It was also found that morphological heterogeneity description is important for such potency prediction. Furthermore, performances of the morphology-based prediction models trained with data consisting of origin-different MSCs demonstrated the effectiveness of sharing morphological data between different types of MSCs, thereby complementing the data limitation issue in the morphology-based quality prediction concept.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Morphological heterogeneity description enabled early and parallel non-invasive prediction of T-cell proliferation inhibitory potency and growth rate for facilitating donor selection of human mesenchymal stem cells

2022

Self Cite

View full text Add to dashboard Cite

show abstract

Image‐based hybrid model incorporating initial spatial distribution for mesenchymal stem cell cultivation process design

Hirono,

Hayashi,

A. Udugama

et al. 2024

AIChE Journal

Self Cite

View full text Add to dashboard Cite

This work presents an image‐based hybrid model incorporating the initial spatial distribution for mesenchymal stem cell (MSC) cultivation process design. First, three levels of seeding bias in static MSC cultivation were experimentally investigated, and the resulting initial distribution was quantified using phase contrast microscopy image analysis. Second, the observed spatial heterogeneity was defined as a new parameter by calculating the standard deviation of the seeded cell number fraction among numerical 8 × 8 tiles on two‐dimensional plates. Third, the parameter was incorporated into kinetic models to consider spatial growth limitation. The model was then applied to simulate MSC cultivation processes with experimental data. Using dynamic and stochastic simulation outputs, feasible ranges of cell‐harvesting time could be determined to satisfy a given requirement for the minimum cell number and acceptable confluency level. The developed hybrid model could serve as a basis for quantitative decision‐making in the design of MSC cultivation processes.

show abstract

The role of process systems engineering in applying quality by design (QbD) in mesenchymal stem cell production

Udugma

Badr

Hirono

et al. 2023

Computers & Chemical Engineering

View full text Add to dashboard Cite

Predicting quality decay in continuously passaged mesenchymal stem cells by detecting morphological anomalies

Cited by 9 publications

References 32 publications

Morphological heterogeneity description enabled early and parallel non-invasive prediction of T-cell proliferation inhibitory potency and growth rate for facilitating donor selection of human mesenchymal stem cells

Morphological heterogeneity description enabled early and parallel non-invasive prediction of T-cell proliferation inhibitory potency and growth rate for facilitating donor selection of human mesenchymal stem cells

Image‐based hybrid model incorporating initial spatial distribution for mesenchymal stem cell cultivation process design

The role of process systems engineering in applying quality by design (QbD) in mesenchymal stem cell production

Contact Info

Product

Resources

About