Skip to main content
Fig. 2 | Breast Cancer Research

Fig. 2

From: Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation

Fig. 2

Left: Representative selection of tiles (512 × 512 pixels) with the corresponding tissue labels by manual annotation used for training the deep learning models. Right: Manual and automatic segmentation of the full CD-31 IHC digital pathology slide of a core needle biopsy from the MISSION study using a CNN trained on the BEHOLD study data

Back to article page