Convolutional Neural Networks Can Predict Retinal Differentiation in Retinal Organoids

Kegeles, Evgenii; Наумов, А. В.; Karpulevich, Evgeny; Volchkov, Pavel; Baranov, Petr

doi:10.3389/fncel.2020.00171

Cited by 42 publications

(41 citation statements)

References 38 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, the development and differentiation process of ROs can be continuously monitored and quantitatively evaluated. Some studies have developed an algorithm based on deep learning using bright-field images, allowing researchers to predict the direction of differentiation and identify differentiation even before gene expression in the mouse–derived organoid culture ( Kegeles et al, 2020a ). When human–derived organoids develop into a lamellar structure, real-time imaging modalities such as fluorescence lifetime imaging microscopy, hyperspectral imaging, and optical coherence tomography can be used to monitor the metabolic status of ROs and even PRCs, and these methods will not damage the culture structure ( Browne et al, 2017 ).…”

Section: Development Of Retinal Organoidsmentioning

confidence: 99%

“…Summary of improved protocols of retinal organoids Kegeles et al, 2020a. An algorithm based on deep learning using bright-field images Predicting the direction of differentiation and identify differentiationBrowne et al, 2017 Real-time imaging modalities including fluorescence lifetime imaging microscopy, hyperspectral imaging, and optical coherence tomography Non-invasive real-time monitoring of metabolic status of ROs and even PRCs nerve aggregates will appear first, and they can differentiate into ROs after being induced by neural stem cells medium.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Retinal Organoids: Cultivation, Differentiation, and Transplantation

Zhang

Tang³

et al. 2021

Front. Cell. Neurosci.

View full text Add to dashboard Cite

Retinal organoids (ROs), which are derived from stem cells, can automatically form three-dimensional laminar structures that include all cell types and the ultrastructure of the retina. Therefore, they are highly similar to the retinal structure in the human body. The development of organoids has been a great technological breakthrough in the fields of transplantation therapy and disease modeling. However, the translation of RO applications into medical practice still has various deficiencies at the current stage, including the long culture process, insufficient yield, and great heterogeneity among ROs produced under different conditions. Nevertheless, many technological breakthroughs have been made in transplanting ROs for treatment of diseases such as retinal degeneration. This review discusses recent advances in the development of ROs, improvements of the culture protocol, and the latest developments in RO replacement therapy techniques.

show abstract

Section: Development Of Retinal Organoidsmentioning

confidence: 99%

mentioning

confidence: 99%

Retinal Organoids: Cultivation, Differentiation, and Transplantation

Zhang

Tang³

et al. 2021

Front. Cell. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Phenotypic alterations that appear during the culture process could be easily discerned using computational or bioinformatic methodology, such as machine-learning methods, and integration of omics and imaging. Studies have begun to predict the differentiation efficiency of retinal organoid cultures based on bright-field images ( Kegeles et al, 2020 ) or functionality and quality of hPSC-derived RPE from live or immunofluorescence images ( Schaub et al, 2020 ; Ye et al, 2020 ).…”

Section: Next-generation Retinal Organoidsmentioning

confidence: 99%

Retinal organoids: a window into human retinal development

2020

View full text Add to dashboard Cite

Retinal development and maturation are orchestrated by a series of interacting signalling networks that drive the morphogenetic transformation of the anterior developing brain. Studies in model organisms continue to elucidate these complex series of events. However, the human retina shows many differences from that of other organisms and the investigation of human eye development now benefits from stem cell-derived organoids. Retinal differentiation methods have progressed from simple 2D adherent cultures to self-organising micro-physiological systems. As models of development, these have collectively offered new insights into the previously unexplored early development of the human retina and informed our knowledge of the key cell fate decisions that govern the specification of light-sensitive photoreceptors. Although the developmental trajectories of other retinal cell types remain more elusive, the collation of omics datasets, combined with advanced culture methodology, will enable modelling of the intricate process of human retinogenesis and retinal disease in vitro.

show abstract

“…A study based on iPSC-derived cortical organoids grown over several months documented a similarity between the electrophysiological activity pattern of cortical organoids and human preterm neonatal electroencephalography using supervised machine learning [ 130 ]. In another study, iPSC-derived retinal organoids adopted a deep-learning computer algorithm based on bright-field imaging to recognize and predict retinal differentiation [ 131 ]. Particularly, they applied a transfer learning approach using convolutional neural network (CNN) algorithms that are loosely modeled on the network of a human brain agglomerated into multiple functional layers [ 87 ].…”

Section: Overcoming Challenges With Possible Technical Solutionsmentioning

confidence: 99%

Advancing Drug Discovery for Neurological Disorders Using iPSC-Derived Neural Organoids

Costamagna

Comi

Corti

2021

IJMS

View full text Add to dashboard Cite

In the last decade, different research groups in the academic setting have developed induced pluripotent stem cell-based protocols to generate three-dimensional, multicellular, neural organoids. Their use to model brain biology, early neural development, and human diseases has provided new insights into the pathophysiology of neuropsychiatric and neurological disorders, including microcephaly, autism, Parkinson’s disease, and Alzheimer’s disease. However, the adoption of organoid technology for large-scale drug screening in the industry has been hampered by challenges with reproducibility, scalability, and translatability to human disease. Potential technical solutions to expand their use in drug discovery pipelines include Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) to create isogenic models, single-cell RNA sequencing to characterize the model at a cellular level, and machine learning to analyze complex data sets. In addition, high-content imaging, automated liquid handling, and standardized assays represent other valuable tools toward this goal. Though several open issues still hamper the full implementation of the organoid technology outside academia, rapid progress in this field will help to prompt its translation toward large-scale drug screening for neurological disorders.

show abstract

Convolutional Neural Networks Can Predict Retinal Differentiation in Retinal Organoids

Cited by 42 publications

References 38 publications

Retinal Organoids: Cultivation, Differentiation, and Transplantation

Retinal Organoids: Cultivation, Differentiation, and Transplantation

Retinal organoids: a window into human retinal development

Advancing Drug Discovery for Neurological Disorders Using iPSC-Derived Neural Organoids

Contact Info

Product

Resources

About