Key points are not available for this paper at this time.
Grading of breast carcinoma plays an important role for identification of severity of the disease and prognostic treatment in histopathology. It also is one of important indicators of carcinoma patterns. In general, it depends on three indices: tubule formation, nuclear plemorphism, and mitotic counts by scoring based on the degrees of cell differentiation or proliferation. However, scoring on these indices often subjects to intra-and inter-observer variability due to its complexities and manual classifications by pathologists. This study aims to accurately determine the scoring of tubule formation for histological grading using a series of image processing and a classifier consisting of support vector machine with Gaussian kernel function. To demonstrate the performance of the proposed method, a number of H&E stained images acquired from biopsy tissues of patients were tested with the proposed system for the scoring. Experimental result reveals that the proposed algorithms can obtain satisfactory scoring compared to other reported works. Therefore, it can provide reliable scores in the tubule formation and grade of breast carcinoma especially for ductal carcinoma.
Ko et al. (Tue,) studied this question.