Process monitoring and quality assessment in extrusion-based bioprinting: Defect formation, identification strategies, and the role of artificial intelligence

Abstract

Bioprinting has emerged as a transformative technology in tissue engineering and regenerative medicine, enabling the precise fabrication of three-dimensional biological constructs. The bioprinting process is governed by a complex interplay among material behavior, complex design of bioconstructs, and printing parameters. Any mismatch among these factors can introduce diverse structural defects, thereby compromising the structural integrity, dimensional accuracy, and cell viability of the bioprinted samples. Therefore, ensuring structural integrity requires a robust process monitoring and defect detection approach to produce reliable and functional bioconstructs. This review provides an analysis of sources and impacts of different types of anomalies found in the extrusion-based bioprinting process. Moreover, it discusses the most widely adopted structural health monitoring (SHM) techniques, and assesses their sensitivity, effectiveness, and practical integration within bioprinting processes. The role of artificial intelligence (AI) and machine learning (ML) is further explored, highlighting how the traditional structural health monitoring techniques utilize AI and ML to enable defect detection and predictive quality control. The review also critically examines the key challenges and limitations in bioprinting, including the scarcity of standardized defect datasets and difficulties in sensor integration, and identifies research gaps that must be bridged to advance reliable, intelligent monitoring systems. Collectively, this review aims to provide a structured foundation for developing SHM frameworks capable of supporting the translation of bioprinting from laboratory research toward consistent, clinically viable fabrication.