New AI Tool Mimics Radiologist Gaze to Read Chest X-Rays

Artificial intelligence (AI) can scan a chest X-ray and diagnose if an abnormality is fluid in the lungs, an enlarged heart or cancer. But being right is not enough, said Ngan Le, a University of Arkansas assistant professor of computer science and computer engineering. We should understand how the computer makes its diagnosis, yet most AI systems are black boxes whose "thought process" even their creators cannot explain.

"When people understand the reasoning process and limitations behind AI decisions, they are more likely to trust and embrace the technology," Le said.

Le and her colleagues developed a transparent, and highly accurate, AI framework for reading chest X-rays called ItpCtrl-AI, which stands for interpretable and controllable artificial intelligence.

The team explained their approach in "ItpCtrl-AI: End-to-end interpretable and controllable artificial intelligence by modeling radiologists’ intentions," published in the current issue of Artificial Intelligence in Medicine.

The researchers taught the computer to look at chest X-rays like a radiologist. The gaze of radiologists, both where they looked and how long they focused on a specific area, was recorded as they reviewed chest X-rays. The heat map created from that eye-gaze dataset showed the computer where to search for abnormalities and what section of the image required less attention.

Creating an AI framework that uses a clear, transparent method to reach conclusions - in this case a gaze heat map - helps researchers adjust and correct the computer so it can provide more accurate results. In a medical context, transparency also bolsters the trust of doctors and patients in an AI-generated diagnosis.

"If an AI medical assistant system diagnoses a condition, doctors need to understand why it made that decision to ensure it is reliable and aligns with medical expertise," Le said.

A transparent AI framework is also more accountable, a legal and ethical concern in areas with high stakes, such as medicine, self-driving vehicles or financial markets. Because doctors know how ItpCtrl-AI works, they can take responsibility for its diagnosis.

"If we don't know how a system is making decisions, it’s challenging to ensure it is fair, unbiased, or aligned with societal values," Le said.

Le and her team, in collaboration with the MD Anderson Cancer Center in Houston, are now working to refine ItpCtrl-AI so it can read more complex, three-dimensional CT scans.

Trong-Thang Pham, Jacob Brecheisen, Carol C. Wu, Hien Nguyen, Zhigang Deng, Donald Adjeroh, Gianfranco Doretto, Arabinda Choudhary, Ngan Le.
ItpCtrl-AI: End-to-end interpretable and controllable artificial intelligence by modeling radiologists' intentions.
Artificial Intelligence in Medicine, 2025. doi: 10.1016/j.artmed.2024.103054

Most Popular Now

AI-Supported Breast Cancer Screening - N…

The new findings are published in The Lancet Digital Health. The initial results of the Mammography Screening with Artificial Intelligence (MASAI) study* - a randomised trial to evaluate whether AI...

The Future of Healthcare is Digital

8 - 10 April 2025, Berlin, Germany. The Berlin Exhibition Centre will be all about digital health from 8 to 10 April 2025. DMEA, Europe's leading event for digital healthcare, organised...

Stanford Medicine Study Suggests Physici…

Artificial intelligence-powered chatbots are getting pretty good at diagnosing some diseases, even when they are complex. But how do chatbots do when guiding treatment and care after the diagnosis? For...

OmicsFootPrint: Mayo Clinic's AI To…

Mayo Clinic researchers have pioneered an artificial intelligence (AI) tool, called OmicsFootPrint, that helps convert vast amounts of complex biological data into two-dimensional circular images. The details of the tool...

Testing AI with AI: Ensuring Effective A…

Using a pioneering artificial intelligence platform, Flinders University researchers have assessed whether a cardiac AI tool recently trialled in South Australian hospitals actually has the potential to assist doctors and...

AI Accelerates the Search for New Tuberc…

Tuberculosis is a serious global health threat that infected more than 10 million people in 2022. Spread through the air and into the lungs, the pathogen that causes "TB" can...

Students Around the World Find ChatGPT U…

An international survey study involving more than 23,000 higher education students reveals trends in how they use and experience ChatGPT, highlighting both positive perceptions and awareness of the AI chatbot’s...

How AI Bias Shapes Everything from Hirin…

Generative AI tools like ChatGPT, DeepSeek, Google's Gemini and Microsoft’s Copilot are transforming industries at a rapid pace. However, as these large language models become less expensive and more widely...

AI Unlocks Genetic Clues to Personalize …

A groundbreaking study led by USC Assistant Professor of Computer Science Ruishan Liu has uncovered how specific genetic mutations influence cancer treatment outcomes - insights that could help doctors tailor...

Adults don't Trust Health Care to U…

A study finds that 65.8% of adults surveyed had low trust in their health care system to use artificial intelligence responsibly and 57.7% had low trust in their health care...

The 10 Year Health Plan: What do We Need…

Opinion Article by Piyush Mahapatra, Consultant Orthopaedic Surgeon and Chief Innovation Officer at Open Medical. There is a new ten-year plan for the NHS. It will "focus efforts on preventing, as...

Deep Learning to Increase Accessibility…

Coronary artery disease is the leading cause of death globally. One of the most common tools used to diagnose and monitor heart disease, myocardial perfusion imaging (MPI) by single photon...