An investigation of XGBoost-based algorithm for breast cancer classification

• DOI: 10.1016/j.mlwa.2021.100154
• Publication Date: 2021-09-08T09:25:39Z
• Authors: Xin Yu Liew; Nazia Hameed; Jeremie Clos
• Keywords: Mucinous carcinoma

Breast cancer is one of the leading cancers affecting women around world. The Computer-Aided Diagnosis (CAD) system a powerful tool to assist pathologists during process diagnosing cancer, which effectively identifies presence cancerous cells. A standard CAD includes processes pre-processing, feature extraction, selection and classification. In this paper, we propose an enhanced breast classification technique called Deep Learning eXtreme Gradient Boosting (DLXGB) on histopathology images using BreaKHis dataset. This method first applies data augmentation stain normalization for then pre-trained DenseNet201 will automatically learn features within image combine with gradient boosting classifier. proposed designed classify histology into binary benign malignant, additionally eight non-overlapping/overlapping categories: i.e., Adenosis (A), Fibroadenoma (F), Phyllodes Tumour (PT), And Tubular Adenoma (TA) Ductal Carcinoma (DC), Lobular (LC), Mucinous (MC), Papillary (PC). With DLXGB, have obtained accuracy 97% both multi-classification improving exiting work done by researchers results indicated that could produce prediction