OPTIMIZATION OF 3D TRACTION MICROSCOPY WITH A FIBRE-BASED CONSTITUTIVE SYSTEM USING ARTIFICIAL INTELLIGENCE

Three-dimensional (3D) traction microscopy is a valuable technique for studying cellular forces and mechanical properties in biological systems. However, accurately measuring and understanding these forces pose challenges due to the complex nature of biological materials. In this study, we propose an optimized approach to 3D traction microscopy by integrating a fibre-based constitutive system with artificial intelligence (AI) techniques. The fibre-based constitutive system captures the anisotropic properties of the cellular substrate, leading to more accurate force reconstructions. We leverage AI algorithms, including deep learning and convolutional neural networks, to develop an efficient optimization framework. This framework iteratively updates the predicted forces, substrate deformation, and fibrebased constitutive parameters, resulting in enhanced accuracy and efficiency of force reconstructions. The proposed approach is validated using synthetic data and experimental measurements from biological samples. The results demonstrate that the integration of the fibre-based constitutive system improves the accuracy of force reconstructions compared to traditional methods. AI-driven optimization significantly reduces the computational burden, making it a practical and efficient approach for 3D traction microscopy analysis. This optimized 3D traction microscopy approach has implications in various fields, including cell biology, tissue engineering, cancer research, and regenerative medicine. By providing a better understanding of cellular forces and their spatial distribution, this approach contributes to unravelling the mechanobiology underlying cellular processes. It also enables the design and evaluation of tissue engineering strategies and aids in the study of cancer progression and response to therapies. In an optimized approach to 3D traction microscopy by integrating a fibre-based constitutive system with AI techniques. The demonstrate improved accuracy and efficiency in force reconstructions, facilitating a deeper understanding of cellular mechanics. This framework has broad applications in multiple disciplines, advancing our knowledge in various biological and medical research areas