Non-Destructive Quantification of Mycelial Biocomposite Growth Over Time.

Area of Science:

• Materials Science
• Biotechnology
• Sustainable Manufacturing

Background:

• Mycelial biocomposites offer eco-friendly alternatives to conventional materials.
• Accurate, non-destructive growth monitoring is crucial for efficient biocomposite manufacturing.
• Existing quantification methods are often destructive or lack precision.

Purpose of the Study:

• To develop and evaluate non-destructive methods for quantifying mycelial growth in wood-flour biocomposites.
• To compare manual, algorithmic, and deep-learning approaches for growth assessment.
• To demonstrate the utility of automated quantification for analyzing substrate supplement effects.

Main Methods:

• Image analysis was used to define and track mycelial density levels (low, medium, high).
• Manual masking, algorithmic masking, and a deep-learning model were employed for quantification.
• The deep-learning model was applied to assess the impact of substrate supplements on growth patterns.

Main Results:

• Manual masking provided rapid but coarse estimates with low user variability.
• Algorithmic masking improved detail but increased variability.
• The deep-learning model offered the fastest, most consistent quantification, eliminating user variability and revealing distinct growth patterns influenced by substrate supplements.

Conclusions:

• Automated deep-learning quantification is effective for mycelial biocomposites.
• This non-destructive approach enables reproducible, high-resolution growth monitoring.
• The findings support precise engineering and broader adoption of mycelial biocomposites.