Thermogram breast cancer prediction approach based on Neutrosophic sets and fuzzy c-means algorithm

• Published in: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Vol. 2015; pp. 4254 - 4257
• Main Authors: Gaber, Tarek, Ismail, Gehad, Anter, Ahmed, Soliman, Mona, Ali, Mona, Semary, Noura, Hassanien, Aboul Ella, Snasel, Vaclav
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.08.2015
• Subjects: Breast cancer; Design automation; Feature extraction; Image segmentation; Level set; Support vector machines
• ISSN: 1094-687X; 1557-170X
• DOI: 10.1109/EMBC.2015.7319334

The early detection of breast cancer makes many women survive. In this paper, a CAD system classifying breast cancer thermograms to normal and abnormal is proposed. This approach consists of two main phases: automatic segmentation and classification. For the former phase, an improved segmentation approach based on both Neutrosophic sets (NS) and optimized Fast Fuzzy c-mean (F-FCM) algorithm was proposed. Also, post-segmentation process was suggested to segment breast parenchyma (i.e. ROI) from thermogram images. For the classification, different kernel functions of the Support Vector Machine (SVM) were used to classify breast parenchyma into normal or abnormal cases. Using benchmark database, the proposed CAD system was evaluated based on precision, recall, and accuracy as well as a comparison with related work. The experimental results showed that our system would be a very promising step toward automatic diagnosis of breast cancer using thermograms as the accuracy reached 100%.