Fig 1.
Flow chart of the steps in POSEA to assign pixels as TP, FP, or FN.
Fig 2.
Four half-white (pixel values = 1) and half-black (pixel values = 0) 256*256 pixel images evaluated by POSEA.
For each image, the white area was considered the segmented region. Each image was evaluated against the other image, including its replicate.
Fig 3.
Simulated grayscale images of adjacent objects created to compare the evaluation performance of POSEA and traditional pixel-level analysis for images with pixels misassigned to an adjacent object.
Table 1.
Precision values output from POSEA evaluation of simulated binary images (Fig 2) that are half-white and half-black either horizontally divided (Image 1, Image 3) or vertically divided (Image 2, Image 4).
Table 2.
Precision values output from the traditional pixel-level evaluation method of the simulated grayscale images of adjacent cells (Fig 3).
Table 3.
Precision, Recall, F-measure values output from POSEA per cell evaluation of the simulated grayscale images of adjacent cells (Fig 3).
Fig 4.
Representative fluorescence (first column) images, ground truth segmented images (second column), and CellProfiler segmented images (third column) of quiescent T cells (first row), activated T cells (second row), and MCF7 cells (third row).
Quiescent and activated T cells are segmented into individual cells whereas MCF7 cells are segmented into the cytoplasm.
Fig 5.
F-measure, Precision, and Recall values calculated by POSEA and the traditional pixel-level method (TM) to compare CellProfiler segmentation results with hand-segmented, ground truth images for quiescent T cells (A), activated T cells (B), and MCF7 cells (C). Each colored triangle is the value for an image (n = 5 images per group). The black circle and lines represent the mean and standard deviation of the 5 data points in each group.
Fig 6.
Violin plots and boxplots showing the distribution of the F-measure, Precision, and Recall values calculated by POSEA for each segmented object within the activated T cell images (n = 225 cells from 5 images).
Table 4.
Average (n = 5 images) time consumption of POSEA and the traditional pixel-level method to compare ground truth and segmented images of Quiescent T cells, Activated T cells, and MCF7 cells.
The average number of cells per image is 154 for Quiescent T cells, 45 for Activated T cells, and 44 for MCF7 cells.