Imagine if the very scans used to position prostate cancer patients for radiotherapy could also predict and prevent painful side effects. That's exactly what a groundbreaking study suggests is possible.
Researchers at the University of Edinburgh, alongside colleagues from the University of Cambridge and The Christie NHS Foundation Trust, have uncovered a potentially game-changing use for daily imaging data collected during prostate cancer radiotherapy. Using artificial intelligence, they discovered that these routine scans, typically used for patient alignment, hold hidden clues about future rectal bleeding – a common and distressing side effect of treatment.
And this is the part most people miss: These clues emerge as early as one week into treatment. By analyzing subtle changes in tissue patterns, known as radiomic features, the AI could predict with surprising accuracy which patients were at higher risk of developing rectal bleeding within two years. Combining data from the first three weeks of scans proved to be the most reliable predictor.
Radiotherapy is a powerful weapon against prostate cancer, but it's not without its drawbacks. The treatment's precision can be compromised by the natural movement of the prostate and surrounding organs, leading to unintended radiation exposure to healthy tissues like the rectum. This can result in rectal bleeding and other side effects that significantly impact a patient's quality of life.
But here's where it gets controversial: The study challenges the notion that we need entirely new scans or technologies to personalize radiotherapy and minimize side effects. Instead, it suggests that the key lies in better utilizing the wealth of data we already collect.
"The key result here is that early treatment imaging contains quantitative information about later toxicity risk, long before symptoms occur," explains Dr. Zhuolin Yang, a Research Fellow at the University of Edinburgh's Institute of Genetics and Cancer. "This supports the idea that predictive biomarkers for adaptive radiotherapy may not require new scans or technology, only better use of the data we already collect."
This approach, known as adaptive radiotherapy, involves regularly adjusting treatment plans based on changes in a patient's anatomy. By incorporating radiomic feature analysis into routine treatment planning and monitoring, doctors could potentially intervene earlier, modifying treatment to reduce side effects while maintaining cancer control.
While the findings are promising, researchers caution that widespread implementation is still years away. Larger studies are needed to confirm these results and refine the technology.
Funded by Prostate Cancer UK, in partnership with Movember and the Garfield Weston Foundation, this research represents a significant step towards kinder, more personalized radiotherapy. As Dr. Hayley Luxton, Head of Research Impact at Prostate Cancer UK, emphasizes, "We know there's a need to make treatments kinder...this marks a great step forward in personalising radiotherapy to make it kinder and better for more men who need it."
What do you think? Is this a breakthrough in cancer treatment, or are we getting ahead of ourselves? Could this approach be applied to other types of cancer? Share your thoughts in the comments below.
Source: University of Edinburgh
16.12.2025
DOI: https://doi.org/10.1016/j.phro.2025.100850
