AI tool can analyse complex cancer images rapidly – offering potential to personalise treatment

Complex digital images of tissue samples that can take an experienced pathologist up to 20 minutes to annotate could be analysed in just one minute using a new AI tool developed by researchers at the University of Cambridge.

SMMILe, a machine learning algorithm, is able not only to correctly detect the presence of cancer cells on slides taken from biopsies and surgical sections, but it can predict where the tumour lesions are located and even the proportion of regions with different levels of aggressiveness.

The tool could be used in the future to guide a patient’s treatment, as well as helping scientists better understand how cancer develops and identify new biological signatures to improve detection.

Artificial intelligence (AI) tools offer incredible promise towards helping pathologists examine tissue samples from patients with suspected or confirmed cancer, producing ‘spatial maps’ that allow them to understand where the cancer cells are and how they are spreading. But training these tools has until now required a large number of high-quality, detailed reference slides annotated by trained pathologists.

In research published today in Nature Cancer, scientists at the University of Cambridge have developed an AI tool that can be trained using slides that have been given simple, patient-level diagnostic labels, such as cancer type or grade. Importantly, these slides did not need to include detailed region-by-region annotations from pathologists, which are time-consuming to produce.

Despite learning from such scant information, the algorithm – SMMILe (Superpatch-based Measurable Multiple Instance Learning) – was able to provide detailed information about each slide, including mapping the locations of tumour lesions, and estimating the proportions and spatial distribution of lesions with different subtypes and grades.

Dr Zeyu Gao from the Early Cancer Institute at the University of Cambridge, who developed the algorithm, said: “Cancer isn’t always uniform. A single tumour can contain different subtypes, some that are more aggressive than others. Our model doesn’t just say ‘yes, there’s cancer’, it maps out these subtypes and their proportions within the tissue. This could one day help doctors tailor treatments more effectively, moving to a more nuanced understanding of each patient’s cancer.”

The team tested the algorithm on eight datasets comprising 3,850 whole-slide images covering six cancer types: lung, kidney, ovarian, breast, stomach, and prostate cancer. When benchmarked against nine other state-of-the-art whole-slide image classification analysis AI tools, SMMILe’s performance matched – and in several cases exceeded – these tools at slide-level classification, while significantly outperforming them when it came to estimating the proportions and spatial distribution of lesions.

Dr Mireia Crispin-Ortuzar, Co-Lead of the Cancer Research UK Cambridge Centre Integrated Cancer Medicine Virtual Institute and the study’s joint senior author, said: “What we’ve developed is akin to a ‘sonar’ for images that essentially allows us to see in the dark. Often, we have information about a tumour, but we don't know how it's distributed in the tissue. There are technologies that allow you to get this information, but they are very costly.

“With our new AI method, we can accurately map the tumour samples – and the beauty is that it is trained on cheap, widely-available datasets that only contain bulk, non-spatial information.”

Although SMMILe is currently focused on classifying tissue slides, the researchers plan to use the tool to predict biomarkers – biological signatures – that reveal how a tumour behaves at a molecular level. This will help further understanding of how cancers develop and spread as well as potentially opening the door to personalised treatment decisions for each patient, guided by both what the tumour looks like and what its biology reveals.

Dr Gao added: “By allowing pathologists to make faster, more accurate diagnoses, we can make sure patients receive the best treatment even sooner, improving our chances of successfully treating their cancer. AI could have a huge impact on the lives of our patients.”

The research was funded mainly by Cancer Research UK and GE HealthCare.

Research Information Manager at Cancer Research UK, Dr Dani Skirrow, said: "We’re living in a golden age of cancer research, with new tools and technologies offering better, faster ways to diagnose cancer and personalise treatments.

“This study suggests SMMILe could help doctors quickly get detailed information about a person’s cancer so that they can give each individual the best treatment option for them. Further studies are needed to check how well SMMILe works in the clinic, but these promising early-stage findings show how artificial intelligence tools have the potential to help people receive personalised care sooner.”

The University of Cambridge and Addenbrooke's Charitable Trust (ACT) are fundraising for a new hospital that will transform how we diagnose and treat cancer. Cambridge Cancer Research Hospital, set to be built on the Cambridge Biomedical Campus, will bring together clinical excellence from Addenbrooke’s Hospital and world-leading researchers at the University of Cambridge. The research that takes place there promises to change the lives of cancer patients across the UK and beyond. Find out more here.

Reference

Gao, Z et al. SMMILE enables accurate spatial quantification in digital pathology using multiple instance learning. Nat Cancer; 19 Nov 2025; DOI: 10.1038/s43018-025-01060-8