An integrative machine learning framework for classifying SEER breast cancer

Abstract

Breast cancer is the commonest type of cancer in women worldwide and the leading cause of mortality for females. The aim of this research is to classify the alive and death status of breast cancer patients using the Surveillance, Epidemiology, and End Results dataset. Due to its capacity to handle enormous data sets systematically, machine learning and deep learning has been widely employed in biomedical research to answer diverse classification difficulties. Pre-processing the data enables its visualization and analysis for use in making important decisions. This research presents a feasible machine learning-based approach for categorizing SEER breast cancer dataset. Moreover, a two-step feature selection method based on Variance Threshold and Principal Component Analysis was employed to select the features from the SEER breast cancer dataset. After selecting the features, the classification of the breast cancer dataset is carried out using Supervised and Ensemble learning techniques such as Ada Boosting, XG Boosting, Gradient Boosting, Naive Bayes and Decision Tree. Utilizing the train-test split and k-fold cross-validation approaches, the performance of various machine learning algorithms is examined. The accuracy of Decision Tree for both train-test split and cross validation achieved as 98%. In this study, it is observed that the Decision Tree algorithm outperforms other supervised and ensemble learning approaches for the SEER Breast Cancer dataset.

A Modified LeNet CNN for Breast Cancer Diagnosis in Ultrasound Images

“…Manikandan et al [32] have studied clinical, epidemiology, and end outcome datasets to distinguish between cancer cases and deaths. This study presents a machine learningbased approach to classify SEER breast cancer data.…”

“…In addition to this, the classifier provides batch normalization [17] and continuous output to prevent overfitting and improve generalization. The limitations of current models that use LeNet for cancer diagnosis and classification are: although LeNet can be used effectively for cancer diagnosis and classification, it also has some drawbacks, which include limited capacity and flexibility, overfitting, pre-processing, and hardware requirements which are significant challenges [32]. To overcome these drawbacks, the present model aims to develop LeNet architecture with the following modifications: In the data preparation process, the Breast Ultrasound (BUS) image datasets are obtained and divided into three groups: training, validation, and testing [50].…”