The First AI Breast Cancer Sleuth that Shows its Work

Computer engineers and radiologists at Duke University have developed an artificial intelligence (AI) platform to analyze potentially cancerous lesions in mammography scans to determine if a patient should receive an invasive biopsy. But unlike its many predecessors, this algorithm is interpretable, meaning it shows physicians exactly how it came to its conclusions.

The researchers trained the AI to locate and evaluate lesions just like an actual radiologist would be trained, rather than allowing it to freely develop its own procedures, giving it several advantages over its "black box" counterparts. It could make for a useful training platform to teach students how to read mammography images. It could also help physicians in sparsely populated regions around the world who do not regularly read mammography scans make better health care decisions.

The results appeared online December 15 in the journal Nature Machine Intelligence.

"If a computer is going to help make important medical decisions, physicians need to trust that the AI is basing its conclusions on something that makes sense," said Joseph Lo, professor of radiology at Duke. "We need algorithms that not only work, but explain themselves and show examples of what they’re basing their conclusions on. That way, whether a physician agrees with the outcome or not, the AI is helping to make better decisions."

Engineering AI that reads medical images is a huge industry. Thousands of independent algorithms already exist, and the FDA has approved more than 100 of them for clinical use. Whether reading MRI, CT or mammogram scans, however, very few of them use validation datasets with more than 1000 images or contain demographic information. This dearth of information, coupled with the recent failures of several notable examples, has led many physicians to question the use of AI in high-stakes medical decisions.

In one instance, an AI model failed even when researchers trained it with images taken from different facilities using different equipment. Rather than focusing exclusively on the lesions of interest, the AI learned to use subtle differences introduced by the equipment itself to recognize the images coming from the cancer ward and assigning those lesions a higher probability of being cancerous. As one would expect, the AI did not transfer well to other hospitals using different equipment. But because nobody knew what the algorithm was looking at when making decisions, nobody knew it was destined to fail in real-world applications.

"Our idea was to instead build a system to say that this specific part of a potential cancerous lesion looks a lot like this other one that I’ve seen before," said Alina Barnett, a computer science PhD candidate at Duke and first author of the study. "Without these explicit details, medical practitioners will lose time and faith in the system if there’s no way to understand why it sometimes makes mistakes."

Cynthia Rudin, professor of electrical and computer engineering and computer science at Duke, compares the new AI platform's process to that of a real-estate appraiser. In the black box models that dominate the field, an appraiser would provide a price for a home without any explanation at all. In a model that includes what is known as a 'saliency map,' the appraiser might point out that a home's roof and backyard were key factors in its pricing decision, but it would not provide any details beyond that.

"Our method would say that you have a unique copper roof and a backyard pool that are similar to these other houses in your neighborhood, which made their prices increase by this amount," Rudin said. "This is what transparency in medical imaging AI could look like and what those in the medical field should be demanding for any radiology challenge."

The researchers trained the new AI with 1,136 images taken from 484 patients at Duke University Health System.

They first taught the AI to find the suspicious lesions in question and ignore all of the healthy tissue and other irrelevant data. Then they hired radiologists to carefully label the images to teach the AI to focus on the edges of the lesions, where the potential tumors meet healthy surrounding tissue, and compare those edges to edges in images with known cancerous and benign outcomes.

Radiating lines or fuzzy edges, known medically as mass margins, are the best predictor of cancerous breast tumors and the first thing that radiologists look for. This is because cancerous cells replicate and expand so fast that not all of a developing tumor’s edges are easy to see in mammograms.

"This is a unique way to train an AI how to look at medical imagery," Barnett said. "Other AIs are not trying to imitate radiologists; they're coming up with their own methods for answering the question that are often not helpful or, in some cases, depend on flawed reasoning processes."

After training was complete, the researches put the AI to the test. While it did not outperform human radiologists, it did just as well as other black box computer models. When the new AI is wrong, people working with it will be able to recognize that it is wrong and why it made the mistake.

Moving forward, the team is working to add other physical characteristics for the AI to consider when making its decisions, such as a lesion’s shape, which is a second feature radiologists learn to look at. Rudin and Lo also recently received a Duke MEDx High-Risk High-Impact Award to continue developing the algorithm and conduct a radiologist reader study to see if it helps clinical performance and/or confidence.

"There was a lot of excitement when researchers first started applying AI to medical images, that maybe the computer will be able to see something or figure something out that people couldn’t," said Fides Schwartz, research fellow at Duke Radiology. "In some rare instances that might be the case, but it’s probably not the case in a majority of scenarios. So we are better off making sure we as humans understand what information the computer has used to base its decisions on."

This research was supported by the National Institutes of Health/National Cancer Institute (U01-CA214183, U2C-CA233254), MIT Lincoln Laboratory, Duke TRIPODS (CCF-1934964) and the Duke Incubation Fund.

Alina Jade Barnett, Fides Regina Schwartz, Chaofan Tao, Chaofan Chen, Yinhao Ren, Joseph Y. Lo, Cynthia Rudin.
A Case-Based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography.
Nature Machine Intelligence, Dec. 15, 2021. doi: 10.1038/s42256-021-00423-x

Most Popular Now

Philips and Medtronic Advocacy Partnersh…

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, and Medtronic Neurovascular, a leading innovator in neurovascular therapies, today announced a strategic advocacy partnership. Delivering timely stroke...

New AI Tool Predicts Protein-Protein Int…

Scientists from Cleveland Clinic and Cornell University have designed a publicly-available software and web database to break down barriers to identifying key protein-protein interactions to treat with medication. The computational tool...

AI for Real-Rime, Patient-Focused Insigh…

A picture may be worth a thousand words, but still... they both have a lot of work to do to catch up to BiomedGPT. Covered recently in the prestigious journal Nature...

New Research Shows Promise and Limitatio…

Published in JAMA Network Open, a collaborative team of researchers from the University of Minnesota Medical School, Stanford University, Beth Israel Deaconess Medical Center and the University of Virginia studied...

G-Cloud 14 Makes it Easier for NHS to Bu…

NHS organisations will be able to save valuable time and resource in the procurement of technologies that can make a significant difference to patient experience, in the latest iteration of...

Start-Ups will Once Again Have a Starrin…

11 - 14 November 2024, Düsseldorf, Germany. The finalists in the 16th Healthcare Innovation World Cup and the 13th MEDICA START-UP COMPETITION have advanced from around 550 candidates based in 62...

Hampshire Emergency Departments Digitise…

Emergency departments in three hospitals across Hampshire Hospitals NHS Foundation Trust have deployed Alcidion's Miya Emergency, digitising paper processes, saving clinical teams time, automating tasks, and providing trust-wide visibility of...

MEDICA HEALTH IT FORUM: Success in Maste…

11 - 14 November 2024, Düsseldorf, Germany. How can innovations help to master the great challenges and demands with which healthcare is confronted across international borders? This central question will be...

A "Chemical ChatGPT" for New M…

Researchers from the University of Bonn have trained an AI process to predict potential active ingredients with special properties. Therefore, they derived a chemical language model - a kind of...

Siemens Healthineers co-leads EU Project…

Siemens Healthineers is joining forces with more than 20 industry and public partners, including seven leading stroke hospitals, to improve stroke management for patients all over Europe. With a total...

MEDICA and COMPAMED 2024: Shining a Ligh…

11 - 14 November 2024, Düsseldorf, Germany. Christian Grosser, Director Health & Medical Technologies, is looking forward to events getting under way: "From next Monday to Thursday, we will once again...

In 10 Seconds, an AI Model Detects Cance…

Researchers have developed an AI powered model that - in 10 seconds - can determine during surgery if any part of a cancerous brain tumor that could be removed remains...