An immune-inspired semi-supervised algorithm for breast cancer diagnosis

• Published in: Computer methods and programs in biomedicine Vol. 134; pp. 259 - 265
• Main Authors: Peng, Lingxi, Chen, Wenbin, Zhou, Wubai, Li, Fufang, Yang, Jin, Zhang, Jiandong
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier Ireland Ltd 01.10.2016
• Subjects: Algorithms; Artificial immune; Breast cancer diagnosis; Breast Neoplasms - diagnosis; Breast Neoplasms - immunology; Female; Humans; Internal Medicine; Machine learning; Other; Artificial immune; Breast cancer diagnosis; Machine learning
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2016.07.020

Highlights • In this paper, we seamlessly integrate the state-of-the-art in life science and artificial intelligence, and investigate a semi-supervised learning algorithm to reduce the need for labeled data. In the proposed algorithm, the Kent chaotic helps to search the best solution in the whole antibody cells feature vector space. Considering that the value of k is sensitive to the experiment results, we use the weighted k nearest neighbor algorithm to diagnose the breast cancer. • We used two well-known benchmark breast cancer datasets in our study, which were acquired from the UCI machine learning repository. Extensive experiments are conducted and evaluated on those two datasets demonstrating the effectiveness and efficiency of our proposed algorithm, which proves that our algorithm is a promising automatic diagnosis method for breast cancer. • The proposed algorithm has clonal selection, non-linear, immunological memory attractive property, and such excellent immune characteristics. The algorithm is also general one, which can be used not only in the research of the medical automatic diagnosis, but also in other related research areas, such as pattern recognition, optimization, etc.