HTT: R data package
Data, scripts, and functions of the High-Throughput
Truthing project (HTT project). The “inst” directory
will be used to archive scripts that reproduce the
analyses done for different presentations and publications.
Project hub space: https://didsr.github.io/HTT.home/
To install this package from the R command line: install_github(‘DIDSR/HTT’)
Data and Code Repository
Manual documenting the data and functions in the R package:
Manuscript describing the project:
- Dudgeon et al. (2020), “A Pathologist-Annotated Dataset for Validating Artificial Intelligence: A Project Description and Pilot Study,” Journal of Pathology Informatics, 12, p. 45. https://www.doi.org/10.4103/jpi.jpi_83_20
Manuscript describing expert panel based on pilot study:
- Garcia et al. (2022), “Development of Training Materials for Pathologists to Provide Machine Learning Validation Data of Tumor-Infiltrating Lymphocytes in Breast Cancer,” Cancers, 14, p. 2467, https://www.doi.org/10.3390/cancers14102467.
Manuscript describing pilot study results:
Elfer et al. (2022), “Pilot study to evaluate tools to collect pathologist annotations for validating machine learning algorithms,” J. Med. Imag., 9, p. 047501, https://www.doi.org/10.1117/1.JMI.9.4.047501.
Manuscript about Multi-reader Multi-case Analysis of Limits of Agreement
- Wen and Gallas (2022), “Three-Way Mixed Effect ANOVA to Estimate MRMC Limits of Agreement,” Stat Biopharm Res, p. 1–10, https://www.doi.org/10.1080/19466315.2022.2063169.
Library of work from HTT team
https://www.zotero.org/groups/4384613/eedap_studies_presentations_publications_and_studies/library