AI outperforms standard scan criteria in mesothelioma assessment

Clinical Takeaway: Pleural mesothelioma can be difficult to track on imaging because tumors often spread in thin, irregular layers along the pleura. AI-based tumor volume measurement may help clinicians assess treatment response more reliably and identify progression sooner than standard scan criteria.

Assessing treatment response in pleural mesothelioma is challenging because tumors often do not grow as discrete masses. Instead, they can spread in uneven sheets around the lung, making small changes difficult to capture with standard diameter-based measurements.

Researchers developed an AI-based method to measure total mesothelioma tumor volume on CT scans and compare changes over time. The retrospective study included more than 10,000 CT scans from more than 2,000 patients across routine-care and clinical-trial cohorts.

The AI-based approach performed better than standard imaging criteria used in mesothelioma. It detected disease progression a median of five weeks earlier and better predicted overall survival.

The findings matter because earlier and more reliable identification of nonresponse could help clinicians stop ineffective treatment sooner, switch therapy when appropriate, and reduce unnecessary toxicity. More accurate tumor measurement could also make mesothelioma trials more reliable by improving how progression and treatment benefit are assessed.

AI-derived baseline tumor volume also predicted overall survival better than conventional factors such as T stage and World Health Organization performance status, suggesting that total tumor burden may provide clinically useful prognostic information.

The study was retrospective, and the approach still needs prospective validation before broad clinical adoption. At the Netherlands Cancer Institute, where the model was developed, AI-generated measurements are already being used with physician review.

“We can now assess tumor response to treatments much more accurately,” said Sjaak Burgers, pulmonologist at the Netherlands Cancer Institute. “We can discover the lack of response much sooner than before. This allows a patient to stop treatment earlier and, if possible, switch to a different treatment.”

Source: Groot Lipman KBW, et al. 2026 June 17. Lancet Oncol. Development and validation of artificial intelligence-assisted volumetric response criteria in pleural mesothelioma (ARTIMES): a retrospective, multicohort, multicentre study