Development and validation of the ISGPP model marks a significant advancement in automating residual pancreatic cancer (RPC) quantification. The model demonstrated robust performance across diverse scanners, achieving mean F1 scores of 0.81-0.71 upon validation. A comprehensive dataset of 528 unique H&E slides from 528 patients facilitated training the model, which is now publicly available. This innovation supports objective evaluation of neoadjuvant treatment responses in pancreatic cancer, filling a critical gap in the assessment process.
• Why it matters: Automated RPC quantification enhances treatment response assessment in oncology.
Journal Article by Janssen BV, Oteman B (…) de Boer OJ et 25 al. in Am J Surg Pathol
Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc.