Self-improving AI can revolutionize 3D printing of biomedical devices, organs

The researchers first trained the computer program to print out a surgical rehearsal model of a prostate.

Self-improving AI can revolutionize 3D printing of biomedical devices, organs

The heart printed on a 3d printer stock photo.

iStock/Scharfsinn86

Researchers have found out that an artificial intelligence algorithm can help them use 3D printing more effectively.

The study carried out by Washington State University researchers proposes that the new AI algorithm can help them make everything from artificial organs to bendable electronics and wearable with ease.

To put the theory to test, researchers used the algorithm to identify and print various human organ models – such as kidneys and prostate.

The AI produced 60 results in continuation, each better than the previous one, showing that it could improve continuously.

Introducing AI to 3D printing

3D printing has become more popular in the recent years and it is an easy option over traditional time-consuming manufacturing process.

In today’s world sensors, organ models, bone implants, batteries, wearable devices, and more have been made using the process. 3D printing today is being looked at as a one-stop solution for the many complexities associated with fields such as aerospace, medicine, surgery and more.

However, the process of selecting appropriate parameters for 3D-printing remains a labor-intensive and inefficient process. The methods currently being used for methods for optimizing 3D-printing parameters have limitations.

They often concentrate on optimizing the printing’s overall performance or focus on one specific aspect of printing quality.

This is where the role of AI arises; with its help users can expedite the process of refining 3D-printing parameter settings while reducing time and cost.

“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.

Washington State University study

In this study, the researchers designed a principled methodology which aimed at identifying optimal direct ink writing (DIW) 3D printing input parameters for manufacturing different presurgical organs.

Bayesian optimization (BO) is a powerful machine learning technique for optimizing complex, expensive, black-box objective functions.

The process consists of four steps, the first of which is input generation through a BO algorithm which sets the input parameters for 3D printing. This is followed by the actual 3D printing of the organ.

Flow-chart schematic of multi-objective BO assisted 3D-printing of presurgical organs models. Credit: WSU

Furthermore, in the third stage the 3D-printed organ models undergo geometric assessment, which is then followed by the output evaluation.

With the completion of the fourth stage, the AI algorithm picks up the defects, if any present, in the organ model and then fine tunes it in the next process.

“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. 

The researchers first trained the computer program to print out a surgical rehearsal model of a prostate. Because the algorithm is broadly generalizable, they could easily change it with small tunings to print out a kidney model.

RECOMMENDED ARTICLES

“That means that this method can be used to manufacture other more complicated biomedical devices, and even to other fields,” said Qiu.

The study was recently published in the journal Advanced Materials Technologies.

0COMMENT

ABOUT THE EDITOR

Abhishek Bhardwaj Abhishek brings a wealth of experience in covering diverse stories across different beats. Having contributed to renowned wire agencies and Indian media outlets like ANI and NDTV, he is keenly interested in Tech, Business and Defense coverage.