AI helping doctors to detect intestinal disease

One of the above images is real; the other is AI-generated. Can you tell which is which? The images depict intestinal polyps, often benign growths on the inside of the colon or rectum. Polyps are usually removed because some can develop into bowel cancer over time.

If diseases of the stomach and intestine are suspected, patients are typically examined using a long, thin tube and a camera. The equipment is inserted via the throat (gastroscopy) or the rectum (colonoscopy).

Researchers at NTNU in Gjøvik, alongside doctors and researchers at Gjøvik Hospital, have collaborated in the pioneering use of AI to help doctors prioritize which patients require a gastroscopy or colonoscopy.

Capsule endoscopy

An alternative option for finding polyps in the intestine is to use a capsule with a built-in camera. The patient swallows the capsule and, seven hours later, the camera has taken tens of thousands of images from inside the stomach and intestine.

“Capsule endoscopy uses a small camera that passes through the gastrointestinal system,” explains Øistein Hovde, a senior consultant at the Gastroenterology Laboratory at Gjøvik Hospital. “The camera is inside a large pill that the patient swallows and which later comes out in the toilet bowl.”

Up to 50,000 images from the intestine

The Gastroenterology Laboratory receives patients who need to be examined and treated for gastrointestinal diseases. Using a capsule can avoid the costs and discomfort of a colonoscopy. The problem? The amount of data that requires processing.

A single capsule can take up to 50,000 images during one examination. The journey takes six to seven hours, with the camera sending images continuously to a computer worn by the patient.

“This is simply a lot of data for a doctor to go through manually, even though the images can be run at high speed,” says Marius Pedersen, a professor at Colourlab in the Department of Computer Science (IDI) at NTNU in Gjøvik.

More images needed

The starting point was 1,350 images from 10 patients with the inflammatory bowel disease ulcerative colitis. These images were captured using a colonoscopy. The same patients also underwent a capsule endoscopy.

However, the AI needed to be trained before it could identify abnormal polyps captured by the capsule camera.

“Artificial intelligence needs to have large amounts of data to be effective, and that required more than the original 1,350 images,” says Pedersen. “At the same time, it was difficult to collect enough traditional images using manual tubes and cameras because of time constraints and privacy concerns.”

The solution was to create more images artificially.

‘Doctored’ images

The research team used diffusion models and the machine-learning method CLIP to generate new, realistic images of polyps.

The content of the images had to be varied, including:

• Where in the intestine the image appeared to be taken
• The number of polyps
• The location of the polyps
• Visibility conditions that could be affected by debris, blood or bubbles
• Polyps at different stages of development

Are doctors able to tell the difference?

In addition to obtaining manual images via colonoscopy, the doctors also used pill cameras—capsule endoscopy—on the same patients. Would gastroenterologists be able to tell the difference between the real and artificially generated images?

The size and appearance of the polyps provide an indication of cancer risk, says Hovde. Photo: Private

“The doctors answered correctly in 54% of the cases,” says Pedersen. “The artificial images were difficult to distinguish from the real ones.”

“This tells us that the synthetic images in this context are of comparable quality to conventional images,” concludes Pedersen.

Less discomfort for the patient

The goal is not to replace current examinations but to make the process easier and more efficient.

“Colonoscopy remains the gold standard. It allows us to examine the inside of the intestine and take samples,” says Hovde.

One goal of the new AI-created images is to make assessments more consistent from doctor to doctor. Today, two specialists may interpret the same image differently, even when using standardized measurement systems such as the Mayo score to assess inflammation in ulcerative colitis.

“With more and better images, it can be easier to train doctors and reach a common agreement on what we are actually seeing,” states Hovde.

Easier to prioritize

Hovde also believes artificial intelligence can help doctors prioritize which images to examine.

Instead of browsing through tens of thousands of images, a doctor could, for example, be presented with the 100 most relevant pictures. The doctor would also receive precise information about where in the intestine the images were taken.

“AI would reduce the number of examinations and require less analysis work, which often takes three to four days per patient. With this approach, it could be reduced to one day. The pill camera also reduces patient discomfort,” says Hovde.

Screening

The pill camera could also be useful in detecting bowel cancer. Norway has one of the highest rates of the disease in the world, with around 5,000 people diagnosed each year. Excluding gender-specific types of cancer, such as ovarian and prostate cancer, it is the most common form of cancer.

Norway has a national screening program for bowel cancer. All 55-year-olds are invited to submit a stool sample, which is tested for traces of blood.

Many bowel cancer cases start as small polyps in the intestine. At least nine out of 10 polyps will never develop into cancer. But size and appearance can provide an indication of cancer risk.

“Pill cameras could be used for patients whose stool samples indicate that further investigation is needed,” says Hovde.

“If the images show polyps whose size and appearance suggest a risk of cancer, the patient should undergo a colonoscopy. But if traces of blood are found in the stool and the pill camera reveals only harmless polyps, the patient could avoid a colonoscopy. This will spare patients discomfort and reduce costs for the health care system.”

Who’s behind this story?

Swati Mestri

Swati Mestri holds a bachelor’s degree in Electronics Engineering and has worked as a content editor since 2019. She has experience editing research documents across technology, health care, and materials science, and has a particular interest in technology and space.

Full profile →

Advertisements

Robert Egan

Bachelor’s in mathematical biology, Master’s in creative writing. Well-traveled with unique perspectives on science and language.

Full profile →