How reproducible is AI-research in Veterinary Pathology?

Reproducibility in science is not a “nice to have”, but a prerequisite. However, reproducibility depends on accurate reporting of all relevant details of an experiment. This is especially important for machine learning, where each experiment is highly dependent on a multitude of parameters.

Sweta Banerjee investigated for the field of Veterinary Pathology and found that many factors that influence reproducibility are not reported well.

The results are now available in a new journal paper in the journal Veterinary Pathology:

Sweta Banerjee, Christof A. Bertram, Viktoria Weiss, Jonas Ammeling, Thomas Conrad, Nils Porsche, Robert Klopfleisch, Christoph Stoblberger, Christopher Kaltenecker, Katharina Breininger, Marc Aubreville: Reporting Transparency in Veterinary Pathology Deep Learning: A Systematic Review of Reproducibility-Critical Details. In: Veterinary Pathology, 2026.