Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: Scalable analysis of Big pathology image data cohorts using efficient methods and high-performance computing strategies

Fig. 4

Pipeline for segmenting nuclei in a whole slide tissue image, and computing a feature vector of characteristics per nucleus. The input to the pipeline is an image or image tile. The output is a set of features for each segmented nucleus. The segmentation stage consists of a pipeline of operations that detect nuclei and extract the boundary of each nucleus – please see Tables 1 and 2 for the full names of the operations. Each segmented nucleus is processed in the feature computation stage to compute a set of shape and texture features. The features include circularity, area, mean gradient of intensity (please see Tables 1 and 2 for the types and names of the features) as shown in the figure

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us