Skip to main content

New algorithm could make screening for cervical cancer cheaper and more accurate

The use of artificial intelligence in medicine isn’t just about top-flight university labs and pricey private hospitals; a group of researchers want to use it to help screen for cancer in the developing world.

“Cervical cancer is the second most common cancer to affect women,” Sharon Xiaolei Huang, associate professor of computer science and engineering at Lehigh University, told Digital Trends. “More than 80 percent of the deaths from cervical cancer occur in developing countries. The current screening methods — which include PAP smears, HPV tests, and other tests — often have low sensitivity. That means that a lot of patients, even if they go for screening, have their cancer undetected. That’s if they can have screenings at all, since the high cost can often prove prohibitive. Motivated by that, we saw that there was a call for a more sensitive, less expensive, and more highly automated screening method.”

Recommended Videos

That’s where the algorithm developed by Huang and her colleagues comes into play. Based on 10 years of work, their algorithm is able to recognize signs of cervical cancer based on noninvasive photos of the cervix. It was trained using data from 1,112 patient visits, of which 345 had lesions that were positive for dysplasia likely to develop into cancer, and 767 had lesions that did not fall into this category.

Searching for visual signs of cancer, the team’s algorithm turned out to have 10 percent better sensitivity and specificity than any other screening method, while also being lower cost. Its accuracy levels were upwards of 85 percent.

The researchers’ work is described in an article in the journal Pattern Recognition titled, “Multi-feature base benchmark for cervical dysplasia classification.” Next up, the team hopes to carry out trials using the AI system.

“There has been massive growth in AI technologies, especially over the past five or six years,” Huang said. “For example, we’ve seen a big increase in the recognition accuracy of image recognition systems. That’s very useful for medicine, which is what I’ve been working on. With recent developments, these tools are really starting to reach a point where they could be used in clinical settings. At the same time, there’s been more acceptance from clinicians and the general population about AI assisting with medicine.”

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Optical illusions could help us build the next generation of AI
Artificial intelligence digital eye closeup.

You look at an image of a black circle on a grid of circular dots. It resembles a hole burned into a piece of white mesh material, although it’s actually a flat, stationary image on a screen or piece of paper. But your brain doesn’t comprehend it like that. Like some low-level hallucinatory experience, your mind trips out; perceiving the static image as the mouth of a black tunnel that’s moving towards you.

Responding to the verisimilitude of the effect, the body starts to unconsciously react: the eye’s pupils dilate to let more light in, just as they would adjust if you were about to be plunged into darkness to ensure the best possible vision.

Read more
Nvidia’s new Polaris supercomputer to tackle climate, cancer, and more
Nvidia Clara Supercomputer GTC

Nvidia pulled back the curtain on a new supercomputer that's set to take on some of the world's biggest problems. It's called Polaris, and Nvidia says it will be at Argonne National Laboratory near Chicago to tackle issues like climate change and offer insight into fields like neuroscience in 2022.

Polaris can handle complex simulations, charting, and machine learning -- and that's only part of what it can do. Nvidia says the machine is capable of 1.4 exaflops of theoretical A.I. performance and over 44 petaflops of FP64 performance. Those numbers put it within the top 10 most powerful supercomputers in the world based on the most recent TOP500 list, which tracks supercomputers around the globe.

Read more
Algorithmic architecture: Should we let A.I. design buildings for us?
Generated Venice cities

Designs iterate over time. Architecture designed and built in 1921 won’t look the same as a building from 1971 or from 2021. Trends change, materials evolve, and issues like sustainability gain importance, among other factors. But what if this evolution wasn’t just about the types of buildings architects design, but was, in fact, key to how they design? That’s the promise of evolutionary algorithms as a design tool.

While designers have long since used tools like Computer Aided Design (CAD) to help conceptualize projects, proponents of generative design want to go several steps further. They want to use algorithms that mimic evolutionary processes inside a computer to help design buildings from the ground up. And, at least when it comes to houses, the results are pretty darn interesting.
Generative design
Celestino Soddu has been working with evolutionary algorithms for longer than most people working today have been using computers. A contemporary Italian architect and designer now in his mid-70s, Soddu became interested in the technology’s potential impact on design back in the days of the Apple II. What interested him was the potential for endlessly riffing on a theme. Or as Soddu, who is also professor of generative design at the Polytechnic University of Milan in Italy, told Digital Trends, he liked the idea of “opening the door to endless variation.”

Read more