A recent article in Veterinary Pathology presents a 9-point checklist aimed at enhancing the reporting quality of studies employing artificial intelligence (AI)-based automated image analysis (AIA). As the utilization of AI in pathology research increases, concerns regarding reproducibility and transparency have surfaced. Developed by a team of veterinary pathologists, machine learning experts, and journal editors, the checklist outlines essential methodological details, including dataset creation, model training, performance evaluation, and AI interaction. The authors stress that transparent reporting is vital for ensuring reproducibility and effective integration of AI into standard pathology workflows. Availability of supporting data—such as training datasets, source code, and model weights—is crucial for validation and broader application. These guidelines are intended to aid authors, reviewers, and editors, particularly for the upcoming special issue on AI in Veterinary Pathology. For further details, view the publication: Bertram, C. A., et al. (2025). doi.org/10.1177/03009858251344320.
