Additional file 2 of Validation of machine learning models to detect amyloid pathologies across institutions

Autor: Vizcarra, Juan C., Gearing, Marla, Keiser, Michael J., Glass, Jonathan D., Dugger, Brittany N., Gutman, David A.
Rok vydání: 2020
DOI: 10.6084/m9.figshare.12211502.v1
Popis: Additional file 2: Supplementary figures. Figure S1. Recreation of Receiver operating curves and precision recall curves for validation dataset and test dataset. Figure S2. comparison between Emory and Tang dataset grouped by CERAD-like scores. Figure S3. combined results of Tang & Emory datasets grouped by CERAD-like scores. Figure S4. pathological diagnosis CNN scores comparison when including 2 cases with cognitive normal diagnosis but AD pathology. Figure S5. CAA CNN score grouped by pathological diagnosis. Figure S6. Gray matter CNN scores grouped by CERAD-like scores for Emory dataset. Figure S7. Gray Matter CNN scores grouped by pathological diagnosis (Emory cohort). Figure S8. Gray Matter CNN score grouped by Reagan criteria score for Emory data. Figure S9. Correlations between whole tissue CNN scores vs highest density FOV score. Figure S10. Tinctorial differences between slides between the two institutions. Figure S11. Low-res images of the Tang train dataset. Figure S12. Low-res images of the Tang hold-out dataset. Figure S13. Low-res images of the Emory dataset. Figure S14. High resolution sample images for the Emory dataset, Tang train and holdout datasets.
Databáze: OpenAIRE