Researchers at Washington State University have made a groundbreaking advancement in the field of 3D printing. Their newly developed artificial intelligence algorithm is set to revolutionize manufacturing intricate structures. This game-changing technology promises to significantly enhance the production of complex designs across various industries, including artificial organs, flexible electronics, and wearable biosensors.
In their study, the algorithm not only identified but also printed the best versions of kidney and prostate organ models, continually refining them over 60 iterations. This breakthrough has the potential to reshape the landscape of 3D printing and propel innovation to unprecedented heights.
“You can optimize the results, saving time, cost, and labor,” said Kaiyan Qiu, co-corresponding author on the paper and Berry Assistant Professor in the WSU School of Mechanical and Materials Engineering.
The use of 3D printing has experienced significant growth in recent years, empowering industrial engineers to efficiently transform custom designs from the computer screen to a diverse array of products, ranging from wearable devices to aerospace parts and batteries.
However, engineers face a cumbersome and inefficient process when trying to develop the optimal settings for their printing projects. They are tasked with making critical decisions about materials, printer configuration, and the dispensing pressure of the nozzle, all of which directly impact the quality of the final product.
“The sheer number of potential combinations is overwhelming, and each trial costs time and money,” said Jana Doppa, co-corresponding author and Huie-Rogers Endowed Chair Associate Professor of Computer Science at WSU.
The researchers, including Qiu and Doppa, have invested significant time and effort into developing advanced, lifelike 3D-printed models of human organs. These models are invaluable for training surgeons and evaluating implant devices, as they accurately replicate the mechanical and physical properties of real organs, including intricate details such as veins, arteries, and channels.
To achieve optimal 3D printing settings for these complex models, Qiu, Doppa, and their students employed an AI technique known as Bayesian Optimization. Through this approach, the researchers were able to simultaneously optimize three different objectives for their organ models: the precision of the geometry, the weight or porosity, and the printing time. The porosity of the organ model holds particular significance for surgical practice, as the mechanical properties of the model can vary based on its density.
“It’s hard to balance all the objectives, but we were able to strike a favorable balance and achieve the best possible printing of a quality object, regardless of the printing type or material shape,” said co-first author Eric Chen, a WSU visiting student working in Qiu’s group in the School of Mechanical and Materials Engineering.
Alaleh Ahmadian, co-first author and WSU graduate student in the School of Electrical Engineering and Computer Science emphasized the significance of balanced objectives in achieving favorable results. She also highlighted the project’s interdisciplinary perspective, stating, “It is very rewarding to work on interdisciplinary research by performing physical lab experiments to create real-world impact.”
Furthermore, the researchers initially trained the computer program to generate a surgical rehearsal model of a prostate, demonstrating the algorithm’s broad generalizability. Notably, they could easily adapt it with minor adjustments to develop a kidney model.
“That means that this method can be used to manufacture other more complicated biomedical devices and even to other fields,” said Qiu.
Journal reference:
- Eric S. Chen, Alaleh Ahmadianshalchi, Sonja S. Sparks, Chuchu Chen, Aryan Deshwal, Janardhan R. Doppa, Kaiyan Qiu. Machine Learning Enabled Design and Optimization for 3D-Printing of High-Fidelity Presurgical Organ Models. Advanced Materials Technologies, 2024; DOI: 10.1002/admt.202400037