Physicians and researchers at the Netherlands Cancer Institute have developed an AI model that outperforms physicians in evaluating treatment response in pleural mesothelioma. Far more accurate than the current international standard criteria (RECIST), the model provides patients with greater certainty and tailored treatments. It changes how physicians assess tumors and could accelerate the development of new treatments by making clinical trials more reliable and efficient.

Physicians evaluate treatment response by measuring tumor growth. The current diameter-based RECIST criteria are of limited use for pleural mesothelioma because this cancer type grows in a thin, irregular layer along the lung wall. Where, then, do you measure the diameter to determine whether the therapy is working? This leads to uncertainty and frustration among patients and physicians.

AI experts, radiologists and pulmonologists from the Netherlands Cancer Institute (NKI) have now solved this problem. Together, they developed the AI model ARTIMES, which can measure the entire volume of a tumor and compare it with previous scans.