Texture and Mathematical Morphology for Hot-Spot Detection in Whole Slide Images of Meningiomas and Oligodendrogliomas

摘要

The paper presents a combined method for an automatic hot-spot areas selection in the whole slide images to support the pathomorphological diagnostic procedure. The studied slides represent the meningiomas and oligodendrogliomas tumour stained with the Ki-67/MIB-1 immunohistochemical reaction. The presented method based on mathematical morphology and texture analysis helps to determine the tumour proliferation index complementing medical information for prognosis and treatment. The major functions of the algorithm include detection of immunopositive cells in the tumour area and the identification and elimination of hemorrhages areas from the specimen map. The results of the numerical experiments confirm high efficiency of the proposed solutions.