Basic cell carcinoma pathological tissue automatic identification method and system based on deep learning

The invention discloses a basal cell carcinoma pathological tissue automatic identification method and system based on deep learning, and belongs to the field of image identification. In order to solve the problems that in the prior art, existing basal cell carcinoma pathological tissue recognition standards are not uniform, and efficiency is poor, the invention provides an automatic basal cell carcinoma pathological tissue recognition method and system based on deep learning. Tissue image blocks are extracted from the sample image after tissue marking to serve as a data set of a tissue segmentation model, the tissue segmentation model is constructed and trained, and epidermis, tumor epithelium, normal tissue and slide background are automatically segmented; according to the method, tissue feature extraction is carried out on a tumor epithelium region, extracted image blocks are used as a data set of a cell segmentation model, feature extraction is carried out, tissue features and cell features are screened a