An integrated deep learning and Bayesian computational method-based quantification of angiogenesis in the chick...

Area of Science:

• Biomedical Engineering
• Developmental Biology
• Computational Biology

Background:

• Angiogenesis, the formation of new blood vessels, is crucial for development and homeostasis but implicated in diseases like cancer and diabetic retinopathy.
• Current screening methods, including cell-based assays and animal models, have limitations in physiological relevance, cost, and ethical considerations.
• The chick embryo yolk sac membrane (YSM) model offers a complex, cost-effective alternative for studying angiogenesis, but lacks adequate image analysis tools.

Purpose of the Study:

• To develop an integrated deep learning method for quantitative angiogenesis estimation from chick embryo YSM experimental data.
• To create a tailored image analysis pipeline addressing the YSM assay's specific optical challenges, such as low signal-to-background ratio.
• To validate the developed method using pharmacological treatments known to affect angiogenesis.

Main Methods:

• An integrated deep learning approach combining standard image processing (channel separation, CLAHE enhancement) with a Bayesian hierarchical Gompertz Gaussian process model.
• Development of a specialized image analysis pipeline optimized for the chick embryo YSM assay.
• Pharmacological validation using VEGF, anti-VEGF antibody, and hydrocortisone treatments.

Main Results:

• Successful quantitative estimation of angiogenesis from chick embryo YSM data using the developed deep learning method.
• The image analysis pipeline effectively handled the YSM assay's low signal-to-background ratio, enabling detailed time-based analysis.
• The method demonstrated pharmacological validation, accurately reflecting the effects of VEGF, anti-VEGF antibody, and hydrocortisone on vessel growth.

Conclusions:

• The integrated deep learning method provides a robust and quantitative approach for angiogenesis assessment in the chick embryo YSM model.
• This novel analysis pipeline overcomes previous limitations of the YSM assay, making it a more accessible and reliable tool for research.
• The developed system facilitates mechanistic studies and therapeutic screening for angiogenesis-related diseases.