Method for Computational Analysis of Histopathological Images to Support the Diagnosis of Cervical Cancer

Histopathology is considered one of the most important tools for diagnosis in medical routine. It is characterized by the study of structural and morphological changes of the cells, caused by diseases in biological tissues. The use of computational techniques in the processing of histopathological images allows the study of the structural organization of tissues and their pathological changes. The overall objective of this work includes the proposal, the implementation and the evaluation of a methodology for the analysis of cervical intraepithelial neoplasia (CIN) from histopathological images. For this pourpose, a pipeline of morphological operators were implemented for the segmentation of cell nuclei and the Delaunay Triangulation were used in order to represent the tissue architecture. Clustering algorithms and graph morphology were used in order to automatically obtain the boundary between the histological layers of the epithelial tissue. Similarity criteria and adjacency relations between the triangles of the network were explored. The proposed method was evaluated concerning the detection of the presence of lesions in the tissue as well as the their malignancy grading. Since this method is generic, it can be applied to other types of lesions and tissues. Keywords-Cervical Intraepithelial Neoplasia (CIN); Neighborhood Graphs; Medical Image Processing; Computer-Aided Diagnosis;