Department of Computer and Software Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan.
Faculty of Science and Technology, University of Tromsø, Tromso, Norway.
Comput Math Methods Med. 2022 Aug 16;2022:5869529. doi: 10.1155/2022/5869529. eCollection 2022.
Breast cancer is one of the leading causes of increasing deaths in women worldwide. The complex nature (microcalcification and masses) of breast cancer cells makes it quite difficult for radiologists to diagnose it properly. Subsequently, various computer-aided diagnosis (CAD) systems have previously been developed and are being used to aid radiologists in the diagnosis of cancer cells. However, due to intrinsic risks associated with the delayed and/or incorrect diagnosis, it is indispensable to improve the developed diagnostic systems. In this regard, machine learning has recently been playing a potential role in the early and precise detection of breast cancer. This paper presents a new machine learning-based framework that utilizes the Random Forest, Gradient Boosting, Support Vector Machine, Artificial Neural Network, and Multilayer Perception approaches to efficiently predict breast cancer from the patient data. For this purpose, the Wisconsin Diagnostic Breast Cancer (WDBC) dataset has been utilized and classified using a hybrid Multilayer Perceptron Model (MLP) and 5-fold cross-validation framework as a working prototype. For the improved classification, a connection-based feature selection technique has been used that also eliminates the recursive features. The proposed framework has been validated on two separate datasets, i.e., the Wisconsin Prognostic dataset (WPBC) and Wisconsin Original Breast Cancer (WOBC) datasets. The results demonstrate improved accuracy of 99.12% due to efficient data preprocessing and feature selection applied to the input data.
乳腺癌是全球女性死亡人数不断增加的主要原因之一。乳腺癌细胞的复杂性质（微钙化和肿块）使得放射科医生很难正确诊断。因此，之前已经开发了各种计算机辅助诊断 (CAD) 系统，并被用于帮助放射科医生诊断癌细胞。然而，由于延迟和/或错误诊断带来的固有风险，改进已开发的诊断系统是必不可少的。在这方面，机器学习最近在乳腺癌的早期和精确检测中发挥了潜在作用。本文提出了一个新的基于机器学习的框架，该框架利用随机森林、梯度提升、支持向量机、人工神经网络和多层感知方法，从患者数据中高效预测乳腺癌。为此，使用了威斯康星州诊断乳腺癌 (WDBC) 数据集，并使用混合多层感知器模型 (MLP) 和 5 倍交叉验证框架进行分类，作为工作原型。为了提高分类准确性，使用了基于连接的特征选择技术，该技术还消除了递归特征。该框架已在两个独立的数据集上进行了验证，即威斯康星州预后数据集 (WPBC) 和威斯康星州原始乳腺癌数据集 (WOBC)。结果表明，由于对输入数据进行了有效的数据预处理和特征选择，因此准确性提高到了 99.12%。
