New AI tool gives a helping hand to x ray diagnosis

Can artificial intelligence, or AI, potentially transform health care for the better?

Now, rising to the challenge, an Arizona State University team of researchers has built a powerful new AI tool, called Ark⁺, to help doctors read chest X‑rays better and improve health care outcomes.

“Ark+ is designed to be an open, reliable and ultimately useful tool in real-world health care systems,” said Jianming “Jimmy” Liang, an ASU professor from the College of Health Solutions, and lead author of the study recently published in the prestigious journal Nature.

In a proof-of-concept study, the new AI tool demonstrated exceptional capability in diagnosis, from common lung diseases to rare and even emerging ones like COVID-19 or avian flu. It also was more accurate and outperformed proprietary software currently released by industry titans like Google and Microsoft.

“Our goal was to build a tool that not only performed well in our study but also can help democratize the technology to get it into the hands of potentially everyone,” said Liang. “Ultimately, we want AI to help doctors save lives.”

More bang for the health care buck

People certainly are demanding more bang for their health care buck.

Yet, with health care now the leading driver of the US economy, the US continues to rank lower than many countries in many indicators, including 49^th in life expectancy, according to the World Bank. That’s lower than countries like Cuba and Qatar.

Patients want to live healthier lives and have better outcomes. And doctors want to make sure to get the diagnosis right the first time for better patient care.

That’s when AI enters the waiting room.

A new AI healthcare tool

Liang’s research team wanted to use AI to help interpret the most common type of X-ray used in medicine, the chest X-ray.

Chest X-rays are a big help for doctors to quickly diagnose various conditions affecting the chest, including lung problems (like pneumonia, tuberculosis or Valley fever), heart issues, broken ribs and even certain gut conditions. 

But sometime, they can be hard to interpret, even for experienced physicians, or they may miss diagnosing rare conditions or emerging diseases, as was seen in the first year of the COVID-19 pandemic.

The Ark+ tool makes chest X-rays easier by reducing mistakes, speeding up diagnosis and making the technology more equitable by providing top‑quality AI health tools free and open access worldwide.

“We believe in open science, said Liang. “So, we used a public data and a global data set as we think this will more quickly develop the AI model.”

Ark+ outperforms previous AI chest x-ray tools

AI works by training computer software on large data sets, or in the case of the Ark+ model, a total of more than 700,000 worldwide images from several publicly available X-ray datasets.

The key difference-maker for Ark+ was adding value and expertise from the human art of medicine. Liang’s team critically included all the detailed doctors’ notes compiled for every image. “You learn more knowledge from experts,” said Liang.

These expert physician notes were critical in the Ark+ learning and getting more and more accuracy as it was trained on each data set.

“Ark+ is accruing and reusing knowledge,” said Liang, explaining the acronym. “That's how we train it. And pretty much, we were thinking of a new way to train AI models with numerous datasets via fully supervised learning.”

“Because before this, if you wanted to train a large model using multiple data sets, people usually used self-supervised learning, or you train it on the disease model, the abnormal, versus a normal x-ray.”

Large companies like Google and Microsoft have been developing AI healthcare models this way.

“That means you are not using the expert labels,” said Liang. “And so, that means you throw out the most valuable information from the data sets, these expert labels. We wanted AI to learn from expert knowledge, not only from the raw data.”

So, in a case of David versus Goliath, Liang’s small yet plucky research team, including graduate students DongAo Ma and Jiaxuan Pang, worked on the project with funding from the National Institutes of Health, National Science Foundation and seed funding from a long-standing collaboration with Mayo Clinic Arizona radiologist Michael Gotway.

ASU’s new tool may be the slingshot needed to give medicine a boost, as it was shown to outperform private and property software developed by giants.

Other key highlights from the pilot project include:

• Foundation model for X‑rays: Ark+ is trained on many different chest X‑ray datasets from hospitals and institutions around the world. This makes it better at detecting a wide range of lung issues.
• Open and sharable: The team has released the code and pretrained models. This means other researchers can improve it or adjust it for local clinics.
• Quick learning: Ark+ can identify rare diseases even when only a few examples are available.
• Adapts to new tasks: Ark+ can be also fine‑tuned to spot new or unseen lung problems without needing full retraining.
• Resilient and fair: Ark+ works well even with uneven data and fights against biases. It can also be used in private, secure ways.

Among the most important aspects of outcompeting proprietary companies was making the Ark+ software open access, and free to all.

“If we compete directly, it’s unlikely that we're going to win,” said Liang. “But with open-source software, we invite collaborations with many other labs. And with everyone involved, I think we are more powerful than one company.”

Putting the AI into the hands of doctors

Liang also notes that the software can be adapted for any kind of medical imaging diagnosis, including CT, MRI and other imaging tools, thereby expanding its impact in the future. 

Liang and his research team hopes Ark+ will become a foundation for future AI tools in medicine, allowing better care no matter where patients live.

The Ark+ team hopes to further commercialize the software for hospitals so that researchers everywhere will use and build on their work. By sharing everything openly, they want to help doctors in all countries, even rural places without big data resources.

Their goal is to make medical AI safer, smarter and more helpful for everyone.

“By making this model fully open, we’re inviting others to join us in making medical AI more fair, accurate and accessible,” Liang added. “We believe this will help save lives.”

That’s a better pill for US healthcare that every American would like to swallow.

                                                                        ###

About this Study:
Published in Nature, the paper is titled “A fully open AI foundation model applied to chest radiography.”  Authors: DongAo Ma1, Jiaxuan Pang1, Michael B. Gotway3, Jianming Liang2*

1School of Computing and Augmented Intelligence, Arizona State University, 1151 S Forest Ave, Tempe, 85281, AZ, USA. 2Biomedical Informatics and Data Science, Arizona State University, 6161 E Mayo Blvd, Phoenix, 85054, AZ, USA. 3Department of Radiology, Mayo Clinic, 5881 E. Mayo Blvd., Phoenix, 85054, AZ, USA.

*Corresponding author(s). E-mail(s): Jianming.Liang@asu.edu; Contributing authors: dongaoma@asu.edu; jpang12@asu.edu; Gotway.Michael@mayo.edu

Why this research matters

Research is the invisible hand that powers America’s progress. It unlocks discoveries and creates opportunity. It develops new technologies and new ways of doing things.

Learn more about ASU discoveries that are contributing to changing the world and making America the world’s leading economic power at researchmatters.asu.edu.

###