Selim IM and Eldesoky A
The topic of morphological analysis has received much attention with the increasing demands in different applications spatial in bioinformatics and biomedical applications. This paper summarizes the recent advances automated machine learning supervised suitable method for morphological Breast Cancer/masses Image Classification based on Non-Negative Matrix Factorization Algorithm. This scheme is making distinctions between all types roughly corresponding to Breast Cancer/masses types. Among many factors that morphological Classification of Breast Cancer and statistics have made great contributions for a radiologist and detection. Morphological (texture features, echogenicity, and homogenous). Breast masses analysis assists classification whether the mass is benign or malignant and finds the Breast Cancer shape. The Experimental results show that Breast Cancer images from the dataset can be classified automatically. With performance (average 94% accuracy) on a large-scale dataset, this demonstrates the strength of our method in providing an efficient tool for breast cancer multi-classification in clinical settings.
PDFShare this article
Journal of Integrative Oncology received 495 citations as per Google Scholar report
