Breast Cancer Diagnosis from Perspective of Class Imbalance
Introduction: Breast cancer is the second cause of mortality among women. Early detection is the only rescue to reduce the risk of breast cancer mortality. Traditional methods cannot effectively diagnose tumor since they are based on the assumption of well-balanced dataset.. However, a hybrid method...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Mashhad University of Medical Sciences
2019-05-01
|
| Series: | Iranian Journal of Medical Physics |
| Subjects: | |
| Online Access: | http://ijmp.mums.ac.ir/article_11544_41bfd081e4a14c065e7902efd1ad73fe.pdf |
| _version_ | 1818558838443343872 |
|---|---|
| author | Jue Zhang Li Chen |
| author_facet | Jue Zhang Li Chen |
| author_sort | Jue Zhang |
| collection | DOAJ |
| description | Introduction: Breast cancer is the second cause of mortality among women. Early detection is the only rescue to reduce the risk of breast cancer mortality. Traditional methods cannot effectively diagnose tumor since they are based on the assumption of well-balanced dataset.. However, a hybrid method can help to alleviate the two-class imbalance problem existing in the diagnosis of breast cancer and establish a more accurate diagnosis. Material and Methods: The proposed hybrid approach was based on improved Laplacian score (LS) andK-nearest neighbor (KNN) algorithms called LS-KNN. An improved LS algorithm was used for obtaining the optimal feature subset. The KNN with automatic K was utilized for classifying the data which guaranteed the effectiveness of the proposed method by reducing the computational effort and making the classification more faster. The effectiveness of LS-KNN was also examined on two biased-representative breast cancer datasets using classification accuracy, sensitivity, specificity, G-mean, and Matthews correlation coefficient. Results: Applying the proposed algorithm on two breast cancer datasets indicated that the efficiency of the new method was higher than the previously introduced methods. The obtained values of accuracy, sensitivity, specificity, G-mean, and Matthews correlation coefficient were 99.27%, 99.12%, 99.51%, 99.42%, respectively. Conclusion: Experimental results showed that the proposed approach worked well with breast cancer datasets and could be a good alternative to the well-known machine learning methods |
| first_indexed | 2024-12-14T00:17:31Z |
| format | Article |
| id | doaj.art-a4e99b082a6741a9a83d2b3d1dae122b |
| institution | Directory Open Access Journal |
| issn | 2345-3672 2345-3672 |
| language | English |
| last_indexed | 2024-12-14T00:17:31Z |
| publishDate | 2019-05-01 |
| publisher | Mashhad University of Medical Sciences |
| record_format | Article |
| series | Iranian Journal of Medical Physics |
| spelling | doaj.art-a4e99b082a6741a9a83d2b3d1dae122b2022-12-21T23:25:26ZengMashhad University of Medical SciencesIranian Journal of Medical Physics2345-36722345-36722019-05-0116324124910.22038/ijmp.2018.31600.137311544Breast Cancer Diagnosis from Perspective of Class ImbalanceJue Zhang0Li Chen1Scholl of Information and Technology, Northwest University, Xi'an,Chinashool of Information and Technology, Northwest Nniversity, Xi'an, ChianIntroduction: Breast cancer is the second cause of mortality among women. Early detection is the only rescue to reduce the risk of breast cancer mortality. Traditional methods cannot effectively diagnose tumor since they are based on the assumption of well-balanced dataset.. However, a hybrid method can help to alleviate the two-class imbalance problem existing in the diagnosis of breast cancer and establish a more accurate diagnosis. Material and Methods: The proposed hybrid approach was based on improved Laplacian score (LS) andK-nearest neighbor (KNN) algorithms called LS-KNN. An improved LS algorithm was used for obtaining the optimal feature subset. The KNN with automatic K was utilized for classifying the data which guaranteed the effectiveness of the proposed method by reducing the computational effort and making the classification more faster. The effectiveness of LS-KNN was also examined on two biased-representative breast cancer datasets using classification accuracy, sensitivity, specificity, G-mean, and Matthews correlation coefficient. Results: Applying the proposed algorithm on two breast cancer datasets indicated that the efficiency of the new method was higher than the previously introduced methods. The obtained values of accuracy, sensitivity, specificity, G-mean, and Matthews correlation coefficient were 99.27%, 99.12%, 99.51%, 99.42%, respectively. Conclusion: Experimental results showed that the proposed approach worked well with breast cancer datasets and could be a good alternative to the well-known machine learning methodshttp://ijmp.mums.ac.ir/article_11544_41bfd081e4a14c065e7902efd1ad73fe.pdfBreast CancerclassificationimbalanceComputer aided diagnosis |
| spellingShingle | Jue Zhang Li Chen Breast Cancer Diagnosis from Perspective of Class Imbalance Iranian Journal of Medical Physics Breast Cancer classification imbalance Computer aided diagnosis |
| title | Breast Cancer Diagnosis from Perspective of Class Imbalance |
| title_full | Breast Cancer Diagnosis from Perspective of Class Imbalance |
| title_fullStr | Breast Cancer Diagnosis from Perspective of Class Imbalance |
| title_full_unstemmed | Breast Cancer Diagnosis from Perspective of Class Imbalance |
| title_short | Breast Cancer Diagnosis from Perspective of Class Imbalance |
| title_sort | breast cancer diagnosis from perspective of class imbalance |
| topic | Breast Cancer classification imbalance Computer aided diagnosis |
| url | http://ijmp.mums.ac.ir/article_11544_41bfd081e4a14c065e7902efd1ad73fe.pdf |
| work_keys_str_mv | AT juezhang breastcancerdiagnosisfromperspectiveofclassimbalance AT lichen breastcancerdiagnosisfromperspectiveofclassimbalance |