Multimodal Three-Dimensional Printing for Micro-Modulation of Scaffold Stiffness Through Machine Learning.

Area of Science:

• Biomaterials Engineering
• Tissue Engineering
• Additive Manufacturing

Background:

• Light-based 3D printing offers precise control over scaffold microstructure and geometry.
• Modulating mechanical properties of 3D printed scaffolds via printing parameters remains underexplored.

Purpose of the Study:

• To develop a novel 3D printing workflow for creating elastomeric scaffolds with engineered stiffness control using machine learning.
• To enable spatial stiffness modulation in addition to high-resolution scaffold fabrication.

Main Methods:

• Utilized machine learning to optimize printing parameters (exposure time, light intensity, infill, laser pump current, printing speed) for poly (glycerol sebacate) acrylate (PGSA) scaffolds.
• Employed digital light processing (DLP) and two-photon polymerization (2PP) 3D printing methods to fabricate scaffolds with features ranging from submicron to hundreds of microns.
• Developed and validated a neural network model for user-defined stiffness modulation.

Main Results:

• Achieved a wide range of mechanical properties in PGSA scaffolds, from 49.3 ± 3.3 kPa to 2.8 ± 0.3 MPa.
• Demonstrated successful spatial stiffness modulation in scaffolds fabricated using both DLP and 2PP techniques.
• Created multiscale scaffolds with precise stiffness control over both gross and fine geometric features.

Conclusions:

• The novel 3D printing workflow enables precision-engineered stiffness control in complex, elastomeric scaffolds.
• This approach is suitable for various tissue engineering applications, particularly interfacial tissues with heterogeneous mechanical properties.
• The integration of machine learning with multiscale 3D printing offers a powerful tool for advanced scaffold design.