Artificial intelligence application in routine pathology: ChatGPT-4.0 and Gemini 2.5 pro performance in detection of MMR-deficiency in colorectal cancer
This drop in sensitivity was attributed to the models' reluctance to confirm true protein loss, often categorizing the result as "Indeterminate" or "Inadequate". Crucially, the diagnostic certainty of the AI models increased dramatically only when a clear Internal Positive Control (IPC) was visible in the image, establishing the IPC as an indispensable feature for robust dMMR identification and differentiating true biological loss from technical artifacts.
Authors
- Gerardo Cazzato (ORCID: https://orcid.org/0000-0003-0325-4316)
- Magda Zanelli
- Nektarios Koufopoulos (ORCID: https://orcid.org/0000-0001-9502-7916)
- Ioannis Boutas
- Andrea Palicelli (ORCID: https://orcid.org/0000-0003-2299-5160)
- Serena Salzano (ORCID: https://orcid.org/0009-0005-3669-8759)
- Rosario Caltabiano
- Giuseppe Broggi
- Massimiliano Fabozzi
Institutions
- National and Kapodistrian University of Athens (GR)
- University of Catania (IT)
- Azienda Sanitaria Unità Locale di Reggio Emilia (IT)
- University of Bari Aldo Moro (IT)
Publication Details
- Journal
- Surgical Oncology
- Published
- 2026-02-18
- DOI
- https://doi.org/10.1016/j.suronc.2026.102383
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00