Pilot study to evaluate tools to collect pathologist annotations for validating machine learning algorithms Journal Article


Authors: Elfer, K.; Dudgeon, S.; Garcia, V.; Blenman, K.; Hytopoulos, E.; Wen, S.; Li, X.; Ly, A.; Werness, B.; Sheth, M. S.; Amgad, M.; Gupta, R.; Saltz, J.; Hanna, M. G.; Ehinger, A.; Peeters, D.; Salgado, R.; Gallas, B. D.
Article Title: Pilot study to evaluate tools to collect pathologist annotations for validating machine learning algorithms
Abstract: Purpose: Validation of artificial intelligence (AI) algorithms in digital pathology with a reference standard is necessary before widespread clinical use, but few examples focus on creating a reference standard based on pathologist annotations. This work assesses the results of a pilot study that collects density estimates of stromal tumor-infiltrating lymphocytes (sTILs) in breast cancer biopsy specimens. This work will inform the creation of a validation dataset for the evaluation of AI algorithms fit for a regulatory purpose. Approach: Collaborators and crowdsourced pathologists contributed glass slides, digital images, and annotations. Here, "annotations" refer to any marks, segmentations, measurements, or labels a pathologist adds to a report, image, region of interest (ROI), or biological feature. Pathologists estimated sTILs density in 640 ROIs from hematoxylin and eosin stained slides of 64 patients via two modalities: an optical light microscope and two digital image viewing platforms. Results: The pilot study generated 7373 sTILs density estimates from 29 pathologists. Analysis of annotations found the variability of density estimates per ROI increases with the mean; the root mean square differences were 4.46, 14.25, and 26.25 as the mean density ranged from 0% to 10%, 11% to 40%, and 41% to 100%, respectively. The pilot study informs three areas of improvement for future work: technical workflows, annotation platforms, and agreement analysis methods. Upgrades to the workflows and platforms will improve operability and increase annotation speed and consistency. Conclusions: Exploratory data analysis demonstrates the need to develop new statistical approaches for agreement. The pilot study dataset and analysis methods are publicly available to allow community feedback. The development and results of the validation dataset will be publicly available to serve as an instructive tool that can be replicated by developers and researchers. (C) The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License.
Keywords: artificial intelligence; breast-cancer; expression; tumor-infiltrating lymphocytes; images; digital pathology; relevance; machine learning; interobserver agreement; tils; reader studies; reader variability; frothing
Journal Title: Journal of Medical Imaging
Volume: 9
Issue: 4
ISSN: 2329-4302
Publisher: SPIE  
Date Published: 2022-07-01
Start Page: 047501-1
End Page: 047501-14
Language: English
ACCESSION: WOS:000847803200016
DOI: 10.1117/1.Jmi.9.4.047501
PROVIDER: wos
PMCID: PMC9326105
PUBMED: 35911208
Notes: Article -- 047501 -- Source: Wos
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Matthew George Hanna
    101 Hanna