DIAGNOSIS AND CLASSIFICATION OF BREAST CANCER FROM THERMOGRAM IMAGES USING TEXTURE FEATURE AND ARTIFICIAL NEURAL NETWORK (ANN)
Authors/Creators
- 1. UG Scholar, Department of Biomedical Engineering, Dhanalakshmi Srinivasan Engineering College, Perambalur, Tamilnadu
- 2. Chief Consultant, Scientific Computing Solutions (SCS), India
- 3. Assistant Professor, Department of Biomedical Engineering, Dhanalakshmi Srinivasan Engineering College, Perambalur, Tamilnadu
Description
Early diagnosis of breast cancer is very vital for the treatment procedure and drastically save the cost and pain of treatment process. There are various techniques such as mammography; ultrasound and MRI are in use for breast cancer diagnosis. Mammography is considered the gold standard for detection of breast cancer but still has certain sensitivity and specificity. Whereas, infrared thermography has advantages over other methods, in terms of radiation risk, high sensitivity and specificity rate. In our work, texture features were extracted and classification was done using Artificial Neural Network (ANN) under MATLAB (version R2013a (8.1.0.604)). The system includes the steps of image acquisition, feature extraction, classification (training and testing). The proposed system achieved overall classification accuracy of 91.66% with Sensitivity 86.66% and Specificity 95.23% for total test samples of 36 images taken from Thermogram Center data.
Files
185.pdf
Additional details
References
- 1. Amir Ehsan Lashkari, Mohammad Firouzmand, "Early breast cancer detection in thermogram images using adaboost classifier and fuzzy c-means clustering algorithm", Middle East journal of cancer: July 2016; 7(3):113-124. 2. Marina Milosevic, Dragan Jankovic, Aleksantar Peulic, "Thermography based breast cancer detection using texture features and minimum variance quantization", EXCLI Journal, 2014; 13:1204-1215, ISSN 1611-2156. 3. Golestani N, Etehad Tavakol M, Ng EYK. Level set method for segmentation of infrared breast thermograms. EXCLI J. 2014; 13:241-51 4. Etehad Tavakol M, Ng EYK. Breast thermography as a potential non-contact method in the early detection of cancer: a review. J Mech Med Biol. 2013; 13:1330001. 5. Ghayoumi Zadeh H, Haddadnia J, Hashemian M. Hassanpour K. Diagnosis of breast cancer using a combination of genetic algorithm and artificial neural network in medical infrared thermal imaging. Iran J Med Phys. 2012; 9(4):265-74.