Figure 3 | Scientific Reports

Figure 3

From: Comparison between a deep-learning and a pixel-based approach for the automated quantification of HIV target cells in foreskin tissue

Figure 3

Comparison of manual cell counts with automated cell counts generated using a pixel-based model and the StarDist model. Cell counting was completed on 10 validation field-of-view images (600 × 600 µm) randomly generated from a set of 232 full section scans (imaged at 200 × total magnification) of foreskin tissue stained for CD3, CD4, CCR5, and nuclei. Manual counts are presented in the center (black dots), automated counts from the pixel-based model on the left (pink dots), and automated counts from the StarDist model on the right (cyan dots). Gray lines connect counts acquired by each method from the same validation FOV. The black center line and box represent the mean and SD. Differences between manual counts and the two automated counting methods was assess using two-tailed paired T-tests. Significant differences are indicated by asterisks (*p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001).

Back to article page