Microfluidic Nerve Culture Segmentation for Neurite Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for assessing the effect of medicinal agents on nerves, such as those using microfluidic devices or petri dishes, face challenges in observing and analyzing individual neurites due to overlapping structures, making it difficult to quantify neurotoxicity effectively.
Innovation Solution
A microfluidic device system with separate culture spaces for nerve cells and neurites, combined with machine learning using microscope images and known substances, allows for the prediction of medicinal agent effects by generating a learned model that assesses the probability of nerve impairment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If nerve cells are cultured in a microfluidic device channel with width 100 μm to 150 μm and height 100 μm to 200 μm, then the channel can accommodate neurite growth, but the neurites form bundle-like structures that cannot be individually observed and analyzed
Solution Approach 1:
The patent divides the culture system into two separate compartments: a first culture space for nerve cell bodies and a second culture space for neurites. This segmentation allows neurites to grow in a dedicated space where they can be individually observed without forming bundles, while still maintaining connection to the nerve cell bodies in the first space.
Solution Approach 2:
The patent transitions from a single three-dimensional culture space to a two-compartment system separated by a membrane. This dimensional reorganization allows neurites to extend into a separate observation space, enabling individual neurite analysis while maintaining the overall culture system integrity.
2Ease of manufacture
If nerve cells are cultured in a petri dish, then the culture method is simple, but nerve cells and neurites overlap each other making it difficult to identify observation sites and perform quantitative assessment
Solution Approach 1:
The patent segments the overlapping nerve cell and neurite culture into two distinct spaces separated by a porous membrane. The first culture space contains nerve cell bodies while the second culture space contains extended neurites, eliminating overlap and enabling precise identification and quantitative assessment of observation sites.
3Quantity of substance
If nerve cells are cultured at high density to form a network structure of neurites, then a network structure is formed, but nerve cells and neurites overlap irregularly making it difficult to perform quantitative assessment
Solution Approach 1:
The patent resolves the overlap problem by segmenting the culture into two spaces. High-density neurite networks can form in the second culture space without overlapping with nerve cell bodies in the first space, allowing quantitative assessment while maintaining network structure integrity.
Solution Approach 2:
The porous membrane acts as an intermediary between the first and second culture spaces. It allows neurites to pass through and form networks in the second space while preventing nerve cell bodies from entering, thus maintaining high neurite density without overlap-related assessment difficulties.
Data Source
AI summary
The medicinal agent effect prediction system includes: a storage unit that records a learned model based on a plurality of teaching data obtained by associating input data for learning, which is based on images of neurites in culture spaces respectively growing from nerve cells cultured in a state where each of known substances is individually added to a culture solution, with output data for learning which relates to information about impaired nerve sites resulting from the known substances; a data input receiving unit that receives input of input data for assessment based on a microscope image of the neurites; and an assessment unit that outputs information derived from probability of occurrence of impairment of each nerve site belonging to the group of impaired site candidates resulting from introduction of the test substance, by applying the input data for assessment to the learned model.