Discriminant Analysis and Neural Network Based Breast Cancer Classifier Using Electrical Impedance
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2016, Vol 18, Issue 5
Abstract
Abstract: Breast cancer presents a serious medical and social problem worldwide. Early detection is key to effective breast cancer treatment. Therefore, scientists are consistently looking for new diagnostic techniques that would be more efficient, easy to use and safe for the patient. Electrical impedance tomography (EIT) is anattractive alternative modality for breast imaging. The procedure is comfortable; the clinical system cost is a small fraction of the cost of an X-ray system, making it affordable for widespread screening. Artificial neural networks (ANNs) may be good pattern classifiers for this application. A preliminary study to show the potential of neural networks to distinguish benign from malignant skin lesions using electrical impedance is presented. In this paper Discriminant Analysis and ANN based classifiers are verified for breast cancer detection using electrical impedance imaging in frequency scanning. Neural networks were able to classify measurements in a test set with 99% accuracy and 93.7% accuracy for the Discriminant Analysis. These results indicate electrical impedance may be a promising clinical diagnostic tool for detection of breast cancer.
Authors and Affiliations
Praveen C. Shetiye, Ashok A. Ghatol and Vilas N. Ghate
Keywords
Related Articles
- EP ID EP133706
- DOI -
- Views 109
- Downloads 0
Latent Fingerprint Matching Using Grey Level Co-Occurrence Matrix
Abstract: Recognizing defendant based on impressions of fingers from crime scenes is important to law enforcement agencies. Latents are partial fingerprints with small area, contain nonlinear distortion,and are usu...
Best Practices in Implementation of Cloud
Cloud computing is one of the latest developments in the IT industry also known as on-demand computing. It provides the full scalability, reliability, high performance and relatively low cost feasible solution as c...
An Efficient Method for Noisy Annotation Data Modeling
Abstract : Probabilistic topic models are used for analyzing and extracting content-related annotations from noisy annotated discrete data like WebPages on WWW and these WebPages are stored using social bookmarking servi...
JTAG Architecture with Multi Level Security
For in–circuit testing and debugging JTAG (Joint Test Access Group) is one of the most powerful standard architecture of DFT (Design For Testability). But JTAG can also act as a tool for hacking and hence makes...
RKO Technique for Color Visual Cryptography
Abstract : To maintain the secrecy and confidentiality of images two different approaches are being followed, Image Encryption and Visual Cryptography. The former being encrypting the images through encryption algo...