Scots researchers have helped develop a computer system they say harnesses the power of AI to learn the language of cancer, and that’s capable of spotting the signs of the disease in biological samples with remarkable accuracy.

An international team of AI specialists and cancer scientists, led by researchers from the University of Glasgow and New York University, are behind the development—which can also provide reliable predictions of patient outcomes.

Currently, pathologists examine and characterise the features of tissue samples taken from cancer patients on slides under a microscope. Their observations on the tumour’s type and stage of growth help doctors determine each patient’s course of treatment and their chances of recovery.

The new system, which has been dubbed “Histomorphological Phenotype Learning” (HPL), could aid human pathologists to provide faster, more accurate diagnoses of the disease, potentially helping to improve cancer care in the future.

The researchers involved have outlined how the HPL system was developed and trained in a new paper published in Nature Communications, an academic journal.

They began by collecting thousands of high-resolution images of tissue samples of lung adenocarcinoma, taken from 452 patients stored in the United States National Cancer Institute’s Cancer Genome Atlas database.

Next, they developed an algorithm which used a training process called self-supervised deep learning to analyse the images and spot patterns based on the visual data in each slide.

The algorithm then broke down the slide images into thousands of tiny tiles, each representing a small amount of human tissue. A deep neural network scrutinised the tiles, teaching itself in the process to recognise and classify any visual features shared across any of the cells in each tissue sample.

When the team added analysis of slides from squamous cell lung cancer to the HPL system, it was capable of correctly distinguishing between their features with 99% accuracy.

Once the algorithm had identified patterns in the samples, the researchers used it to analyse links between the phenotypes it had classified and the clinical outcomes stored in the database, including how long patients lived after having cancer surgery.

The predictions made by the HPL system correlated with the real-life outcomes of the patients stored in the database, correctly assessing the likelihood and timing of cancer’s return 72% of the time. Human pathologists tasked with the same prediction drew the correct conclusions with 64% accuracy.

When the research was expanded to include analysis of thousands of slides across 10 other types of cancers, including breast, prostate, and bladder cancers, the results were similarly accurate despite the increased complexity of the task.

Recommended reading

• Cancer Innovation Challenge Boosts Scotland’s Cancer Care
• Glasgow Hospital Trials AI CT Scan Tech in “UK First”
• Persistent Data Breaches Are Failing People With HIV

Dr Adalberto Claudio Quiros, a research associate in the University of Glasgow’s School of Cancer Sciences and School of Computing Science, is a co-first author of the paper. “This research shows the potential that cutting-edge machine learning has to create advances in cancer science which could have significant benefits for patient care,” he said.

“This kind of self-learning algorithm will only become more accurate as additional data is added, helping it become more fluent in the language of cancer. Unlike humans, it brings no pre-conceived ideas to its work, so it may even find patterns across the datasets that haven’t been fully explored before.

“Ultimately, our aim is to provide doctors and patients with a tool that can help provide them with an improved understanding of their prognosis and treatment.”

The research was supported by funding from the Engineering and Physical Sciences Research Council (EPSRC), the Biotechnology and Biological Sciences Research Council (BBSRC), and the National Institutes of Health.