About this Abstract |
Meeting |
2021 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2021)
|
Symposium
|
Special Session
|
Presentation Title |
Deep Learning Assisted Approach to Monitoring Anomalies of 3D-bioprinting Process |
Author(s) |
Zeqing Jin, Grace X. Gu |
On-Site Speaker (Planned) |
Zeqing Jin |
Abstract Scope |
Advances in additive manufacturing (AM) have enabled the fabrication of parts with complex designs and multiple functionalities. Recent 3D-bioprinting technology is now able to create biocompatible materials and structures for functional living cells. Meanwhile, the success of long-term biological applications is dependent on creating a high-quality bioprinted part identical to the desired design. However, challenges exist in detecting the anomalies within transparent bioprinted parts with complex features accurately and efficiently. In this study, an anomaly detection system based on layer-by-layer camera images and machine learning algorithms is developed to distinguish and classify imperfections for transparent hydrogel-based bio-printed materials. High accuracy is obtained by utilizing convolutional neural network methods as well as image processing techniques. It is envisioned that this work will provide effective information on the layer-wise printing conditions as well as potential applications in autonomous correction of bioprinters without human interaction. |
Proceedings Inclusion? |
Definite: Post-meeting proceedings |