Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Joint analysis of histopathology image features and gene expression in breast cancer

Fig. 1

Codeblocks and codebook. a An example of four different hypothetical distributions of the codeblocks leading to identical frequencies. To cope with such situations, the distribution of codeblocks is also taken into account through extended image features. b A visual representation of the obtained codebook. The 70 image patches are the closest to the codeblocks obtained after k-means clustering. The three groups of codeblocks (with 29, 20 and 21 elements, respectively) correspond to the major clusters in Fig. 2 and the ordering of the image patches is the same as in the clustering

Back to article page