Skip to main content
Fig. 3 | Diagnostic Pathology

Fig. 3

From: Pre-screening of endomysial microvessel density by fast random forest image processing machine learning algorithm accelerates recognition of a modified vascular network in idiopathic inflammatory myopathies

Fig. 3

Representative images of CD31-immunolabeled human muscle tissue showing the CD31+ vascular network in a female anti-HMGCR+ IMNM patient (a) and a female PM patient (b), (c, d) FRF processed images highlighting the quantifiable red pixels of endomysial microvessels, class 2 for the FRF classifier. The red pixel distribution is shown in the insets. The pixel distribution is related to the isolated endothelial cells of class 2, the black region contains other parts of the muscle tissue not included in the class 2. These excluded regions could contain agglomerates of blood vessels (the red color indicates a high probability of finding isolated endothelial cells only). As mentioned in the main text, the different density of vascular network is useful to discriminate between the various kind of IIM

Back to article page