Fig. 5: Identification of polarization markers that correlates with HCC differentiation degree. | Communications Engineering

Fig. 5: Identification of polarization markers that correlates with HCC differentiation degree.

From: Unsupervised learning of pixel clustering in Mueller matrix images for mapping microstructural features in pathological tissues

Fig. 5

The logarithm scale density heat maps of normal and malignant hepatocellular carcinoma (HCC) samples are compared in (a), and the two potential polarization markers are enlarged for better view. Proportion of pixels belongs to cluster 2 and 6 in each region of interest (ROI) are calculated, and the box whisker plots are shown in (b) and (c) for each differentiation degree. The box and the whiskers mark the 10, 25, 50, 75, and 90 percentiles respectively. d displays the heat map for each differentiation degree, and the dashed line indicates the selected polarization marker in the cytoplasm cluster to differentiate well and moderately differentiated samples. e This shows the box-whisker plot of the selected polarization marker in (d).

Back to article page