Login / Signup

Robust, credible, and interpretable AI-based histopathological prostate cancer grading.

Fabian WesthaeusserPatrick FuhlertEsther DietrichMaximilian LennartzRobin KhatriNico KaiserPontus RöbeckRoman David BülowSaskia von StillfriedAnja WitteSam LadjevardiAnders DrottePeter SevergardhJan BaumbachVictor G PuellesMichael HäggmanMichael BrehlerPeter BoorPeter WalhagenAnca DragomirChrister BuschMarkus GraefenEwert BengtssonGuido SauterMarina ZimmermannStefan Bonn
Published in: medRxiv : the preprint server for health sciences (2024)
Data variation poses serious risks for AI-based histopathological PCa grading, even when models are trained on large datasets. Algorithmic improvements for model robustness, interpretability, credibility, and training on high-variance data as well as outcome-based severity prediction gives rise to robust models with above ISUP-level PCa grading performance.
Keyphrases
  • prostate cancer
  • artificial intelligence
  • electronic health record
  • big data
  • radical prostatectomy
  • machine learning
  • deep learning
  • risk assessment
  • virtual reality
  • climate change
  • body composition