Abstract: A breast tumor examination can help to detect the tumor in the early stages, which is meaningful for the cure. The medical image examination in digital mammography is the most effective method of the breast cancer detection. Computer-aided diagnosis (CAD) on breast tumor detection will provide a confirmation for the radiologists in detecting the suspicious regions in images and also improve accuracy and efficiency. This paper builds on prior work looking at neo adjuvant response to query whether baseline pharmacokinetic (PK) imaging heterogeneity can be used to predict prognosis. The Entire process is carried out in two phases: Segmentation and Classification of the breast tumor. In segmentation process, the tumor pixels are partitioned into groups that act similarly based on PK heterogeneity measures. Wavelet kinetic features are then extracted within each partitioned sub region to obtain the spatiotemporal patterns of the wavelet coefficients and contrast agent uptake. We extract localized spatiotemporal features within the obtained tumor pixel partitions, based on specific heterogeneity properties. During Classification Process, The features of the tumor are extracted, and input into ELM, as well as the judgment of radiologists which acts as the standard indicative of the classification, then the training of ELM is finished.
Keywords: Breast cancer recurrence prediction, breast dynamic contrast-enhanced magnetic resonance imaging (DCEMRI), feature extraction, gene expression, partitioning, ELM.
Title: A Novel Framework for Breast Tumor Segmentation and Classification Using Extreme Machine Learning
Author: A. Sahaya Archana, A. Anuja merlyn
International Journal of Healthcare Sciences
ISSN 2348-5728 (Online)
Research Publish Journals
