Classification of Mammographic Micro calcification Clusters
Publication Date : 13/04/2018
Conference Name :
Goal: The presence of microcalcification clusters is a primary sign of breast cancer; however, it is difficult and time consuming for radiologists to classify microcalcifications as malignantor benign. In this paper, a novel method for the classification of microcalcification clusters in mammograms is proposed. Methods: Morphology, FCM are the two algorithms are used to detect the tumour by its time, area, accuracy, sensitivity and specificity. The parameters used in these two algorithms shows variation in detecting the tumour.Results: The validity of the proposed method is evaluated using MIAS (Mamographic Image Analysis Society).A full comparison of time, area, accuracy, sensitivity and specificity is done relatively to all algorithms. Conclusion: The results indicate that the proposed approach is able to outperform the current state-of-the-art methods. Significance: This study shows that morphological modeling is an important tool for microcalcification analysis not only because of the improved classification accuracy but also because the parameters like time, area, accuracy, sensitivity and specificity can be linked to clinical understanding.