Diagnosing Breast Cancer with the Aid of Fuzzy Logic Based on Data Mining of a Genetic Algorithm in Infrared Images.
Background: Breast cancer is one of the most prevalent cancers among women today. The importance of breast cancer screening, its role in the timely identification of patients, and the reduction in treatment expenses are considered to be among the highest sanitary priorities of a modern country. Ther...
| Publicado en: | Middle East Journal of Cancer Vol. 3; no. 4; pp. 119 - 130 |
|---|---|
| Autores principales: | , , , , |
| Formato: | algorithm equations & formulas research tables/charts Journal Article |
| Publicado: |
Middle East Journal of Cancer
2012
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=100779247&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 100779247 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 20086709 B7LE jtl: Middle East Journal of Cancer issn: 20086709 maglogo: N pubinfo: dt: 2012 vid: 3 iid: 4 pid: 67247 pub: Middle East Journal of Cancer artinfo: ui: 100779247 100779247 103752430 100779247 ppf: 119 ppct: 11 formats: fmt: @attributes: type: P tig: atl: Diagnosing Breast Cancer with the Aid of Fuzzy Logic Based on Data Mining of a Genetic Algorithm in Infrared Images. aug: au: Zadeh, Hossein Ghayoumi Pakdelazar, Omid Haddadnia, Javad Rezai-Rad, Gholamali Mohammad-Zadeh, Mohammad affil: Biomedical Engineering Department, Hakim Sabzevari University, Sabzevar, Khorasan Razavi, Iran sug: subj: Breast Neoplasms Diagnosis Spectrophotometry, Infrared Utilization Genomics Human Academic Medical Centers Iran Sensitivity and Specificity Female Adult Algorithms Early Diagnosis Breast Neoplasms Epidemiology Adult: 19-44 years Female ab: Background: Breast cancer is one of the most prevalent cancers among women today. The importance of breast cancer screening, its role in the timely identification of patients, and the reduction in treatment expenses are considered to be among the highest sanitary priorities of a modern country. Thermal imaging clearly possesses a special role in this stage due to rapid diagnosis and use of harmless rays. Methods: We used a thermal camera for imaging of the patients. Important parameters were derived from the images for their posterior analysis with the aid of a genetic algorithm. The principal components that were entered in a fuzzy neural network for clustering breast cancer were identified. Results: The number of images considered for the test included a database of 200 patients out of whom 15 were diagnosed with breast cancer via mammography. Results of the base method show a sensitivity of 93%. The selection of parameters in the combination module gave rise measured errors, which in training of the fuzzy-neural network were of the order of clustering 1.0923x10-5, which reached 2%. Conclusion: The study indicates that thermal image scanning coupled with the presented method based on artificial intelligence can possess a special status in screening women for breast cancer due to the use of harmless non-radiation rays. There are cases where physicians cannot decisively say that the observed pattern in the image is benign or malignant. In such cases, the response of the computer model can be a valuable support tool for the physician enabling an accurate diagnosis based on the type of imaging pattern as a response from the computer model. pubtype: Academic Journal doctype: algorithm equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|