Improved statistical benchmarking of digital pathology models using pairwise frames evaluation
Computer Vision and Pattern Recognition
2023-06-09 v1 Machine Learning
Abstract
Nested pairwise frames is a method for relative benchmarking of cell or tissue digital pathology models against manual pathologist annotations on a set of sampled patches. At a high level, the method compares agreement between a candidate model and pathologist annotations with agreement among pathologists' annotations. This evaluation framework addresses fundamental issues of data size and annotator variability in using manual pathologist annotations as a source of ground truth for model validation. We implemented nested pairwise frames evaluation for tissue classification, cell classification, and cell count prediction tasks and show results for cell and tissue models deployed on an H&E-stained melanoma dataset.
Cite
@article{arxiv.2306.04709,
title = {Improved statistical benchmarking of digital pathology models using pairwise frames evaluation},
author = {Ylaine Gerardin and John Shamshoian and Judy Shen and Nhat Le and Jamie Prezioso and John Abel and Isaac Finberg and Daniel Borders and Raymond Biju and Michael Nercessian and Vaed Prasad and Joseph Lee and Spencer Wyman and Sid Gupta and Abigail Emerson and Bahar Rahsepar and Darpan Sanghavi and Ryan Leung and Limin Yu and Archit Khosla and Amaro Taylor-Weiner},
journal= {arXiv preprint arXiv:2306.04709},
year = {2023}
}
Comments
10 pages, 7 figures