Using an artificial intelligence tool to improve the recognition of pseudoprogression in pleural mesothelioma patients treated with immunotherapy: a case series

Our plain-English summary of Using an artificial intelligence tool to improve the recognition of pseudoprogression in pleural mesothelioma patients treated with immunotherapy: a case series, by I. Smesseim, K. Chupetlovska, V. Pugliese, et al (Translational Lung Cancer Research, 2026).

The study

• Authors: I. Smesseim, K. Chupetlovska, V. Pugliese, J.A. Burgers, K.B.W.G. Lipman
• Journal: Translational Lung Cancer Research
• Published: 2026;15(8):254
• Type of article: Case report
• Read it: PubMed · Publisher · Free full text

Abstract

Background: Pseudoprogression, defined as initial radiological tumor growth followed by treatment response, can complicate treatment response assessment in patients receiving immunotherapy. In pleural mesothelioma (PM) patients treated with immunotherapy reliable identification of pseudoprogression remains challenging with the modified Response Evaluation Criteria in Solid Tumors (mRECIST) v1.1 criteria. Automated volumetric assessment using an artificial intelligence (AI) tool (ARTIMES) may provide additional insight into tumor response patterns. We aim to describe cases of pseudoprogression identified using the ARTIMES criteria in PM patients treated with immunotherapy.

Case Description: We performed a retrospective observational study of adult PM patients treated with immunotherapy at a tertiary center between January 1, 2013 and July 1, 2022. Tumor volumes were automatically segmented and quantified using the ARTIMES model. Patients demonstrating disease progression according to ARTIMES criteria followed by subsequent tumor volume decrease were evaluated for pseudoprogression. The results were presented in graphs depicting tumor volume, treatment duration, and the start and stop dates of immunotherapy. Among 368 PM patients treated with immunotherapy, 8 patients met inclusion criteria for confirmed pseudoprogression. All patients were male, with a median age of 67.5 years. Most patients had epithelioid histology (75.0%). All patients showed initial volumetric progression on early follow-up imaging, followed by objective tumor volume reduction either during continued immunotherapy or after treatment discontinuation. Volumetric tumor tracking enabled visualization of delayed responses that would have been difficult to interpret using standard imaging comparisons alone.

Conclusions: Pseudoprogression occurs in a subset of PM patients treated with immunotherapy. Automated volumetric tumor assessment can help identify pseudoprogression patterns. Integrating volumetric analysis with clinical evaluation may reduce premature discontinuation of potentially effective immunotherapy.

© AME Publishing Company.

In plain English

This case series came from a tertiary cancer center in the Netherlands. The authors reviewed records of 368 adults with pleural mesothelioma treated with immunotherapy between January 1, 2013 and July 1, 2022. An artificial intelligence tool, ARTIMES, measured tumor volume on CT scans automatically. The authors looked for pseudoprogression, meaning tumor growth on early scans followed by shrinkage. ARTIMES flagged 20 possible cases. After scans were matched to treatment dates, 8 of 368 (2.2%) were classed as confirmed. All 8 were men, with a median age of 67.5 years. Six had epithelioid, one sarcomatoid and one biphasic mesothelioma. In each, tumor volume first rose and later fell, either while immunotherapy continued or after it stopped. When one radiologist re-read the early scans with the standard mRECIST criteria, only one of the eight showed pseudoprogression. The authors concluded that pseudoprogression is uncommon or may be underdiagnosed in these patients. They noted the small, retrospective design and varying scan timing. The article did not discuss asbestos exposure.

We wrote this plain-English summary from the full article with the help of AI, and a second AI model checked each sentence against the article. It is not the authors' wording; the abstract and the article are their own account.

What the study did and found

• Design: Retrospective observational study presented as a case series (8 cases)
• Who was studied: 368 adults with histologically proven pleural mesothelioma treated with immunotherapy at a tertiary center in the Netherlands (Netherlands Cancer Institute) from January 1, 2013 to July 1, 2022. ARTIMES identified 20 with potential pseudoprogression, and 8 were confirmed. All 8 were male, with a median age of 67.5 years (interquartile range 65.5 to 78.0 years).
• Exposure: Immunotherapy (nivolumab alone, or nivolumab plus ipilimumab), mostly after prior platinum-based chemotherapy. Tumor volume on CT was measured by the ARTIMES AI tool. The article does not address asbestos exposure.
• Main results:
  • Pseudoprogression by ARTIMES criteria was confirmed in 8 of 368 pleural mesothelioma patients treated with immunotherapy (2.2%). Twelve of the 20 potential cases were excluded after treatment start and end dates were aligned with the scans.
  • Among the 8 confirmed cases, 6 (75.0%) had epithelioid, 1 sarcomatoid and 1 biphasic mesothelioma.
  • All 8 patients showed an initial increase in tumor volume on early follow-up imaging, followed by a reduction in tumor volume either during continued immunotherapy or after treatment was stopped.
  • In some patients (for example patient D), a delayed response was seen only after immunotherapy had been stopped.
  • When one thoracic radiologist assessed the first scans of the 8 patients using mRECIST 1.1, only patient F showed pseudoprogression (initial progressive disease followed by partial response).
• The authors' conclusion: The authors concluded that pseudoprogression is uncommon, or may be underdiagnosed, in pleural mesothelioma patients treated with immunotherapy. In their view, careful monitoring of clinical signs and imaging is needed to avoid stopping therapy prematurely.
• Limitations the authors state:
  • Retrospective design and small sample size
  • Pseudoprogression was identified using ARTIMES criteria rather than mRECIST v1.1, which differs from clinical practice.
  • Prior treatments, immunotherapy regimens and follow-up intervals differed between patients, which may affect interpretation of treatment response.
  • CT scan timing varied, so even patients classified as having no pseudoprogression may not have been classified accurately.

Topics

Medical terms in this study, explained in our Lexicon: Pleural Mesothelioma, Immunotherapy, Modified RECIST (mRECIST), Disease Progression, Epithelioid, Histology.

Related studies

• Prospective validation of an artificial intelligence assessment in a cohort of applicants seeking financial compensation for asbestosis (PROSBEST) — I. Smesseim, K.B.W.G. Lipman, et al. (2025)
• Artificial Intelligence-based Quantification of Pleural Plaque Volume and Association With Lung Function in Asbestos-exposed Patients — K.B.W. Groot Lipman, T.N. Boellaard, et al. (2024)
• Pre-treatment Tumor Volume Growth Rate and Baseline Volume Measured by an Artificial Intelligence Program Predict Overall Survival in Patients With Pleural Mesothelioma Undergoing Deferred Systemic Therapy — I. Smesseim, V. Pugliese, et al. (2026)
• Artificial intelligence-based diagnosis of asbestosis: analysis of a database with applicants for asbestosis state aid — K.B.W. Groot Lipman, C.J. de Gooijer, et al. (2023)
• Artificial Intelligence Techniques to Predict the Airway Disorders Illness: A Systematic Review — A. Koul, R.K. Bawa, et al. (2023)
• Gender Differences in the Use of ChatGPT as Generative Artificial Intelligence for Clinical Research and Decision-Making in Occupational Medicine — P. Mashburn, F.A. Weuthen, et al. (2025)

Browse more research in Translational Lung Cancer Research, or return to medical research.