AI tool for computing radiation dose helps personalize prostate cancer treatment
Radiopharmaceutical therapy (RPT) has made significant strides over the past 50 years, although it only recently received FDA approval to treat prostate cancer. But despite the progress—and billions of dollars in industry investments—one area that has lagged behind is dosing, which is still one-size-fits-all. Now, researchers at the University of Massachusetts Amherst have developed an AI model…
The development of an AI model called DiffuDose at the University of Massachusetts Amherst has revolutionized radiation dose computation for prostate cancer treatment. Despite significant advancements in radiopharmaceutical therapy (RPT) over the past five decades and billions in industry investment, dosing has remained a challenge, with a one-size-fits-all approach limiting therapy potential.
Traditional dosing methods are inaccurate and time-consuming, taking hours to provide a full-resolution radiation dose map. The new AI system, however, generates a personalized radiation dose map in under 23 seconds, matching gold-standard accuracy and outperforming six competing methods. By measuring radiation absorption in each tissue, DiffuDose enables personalized treatment, optimizing drug quantity and frequency while minimizing organ toxicity.
The system's ability to reveal drug concentration after treatment could help doctors determine safe higher doses for subsequent treatments. The AI model's success was achieved through a combination of two AI modules: one generating a coarse dose estimate and another refining it into a full-resolution map. Researchers are now collaborating with UMass Chan Medical School to further develop AI models using post-RPT scans and patient biomarkers, aiming to enhance personalized treatment understanding.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
