1. Deep learning model for fully automated breast cancer detection system from thermograms
- Author
-
Tarek Gaber, Essam Rashed, Oliver Karam, Omar Karam, and Damaševičius, R
- Subjects
Computer and Information Sciences ,Neural Networks ,Databases, Factual ,Imaging Techniques ,Science ,Breast Neoplasms ,Research and Analysis Methods ,Sensitivity and Specificity ,Machine Learning ,Deep Learning ,Mathematical and Statistical Techniques ,Artificial Intelligence ,Diagnostic Medicine ,Support Vector Machines ,Breast Tumors ,Breast Cancer ,Medicine and Health Sciences ,Cancer Detection and Diagnosis ,Image Processing, Computer-Assisted ,Humans ,Breast ,Early Detection of Cancer ,Automation, Laboratory ,Multidisciplinary ,Cancers and Neoplasms ,Biology and Life Sciences ,Convolution ,Data Accuracy ,Benchmarking ,Oncology ,Thermography ,Medicine ,Female ,Neural Networks, Computer ,Mathematical Functions ,Algorithms ,Research Article ,Neuroscience - Abstract
Breast cancer is one of the most common diseases among women worldwide. It is considered one of the leading causes of death among women. Therefore, early detection is necessary to save lives. Thermography imaging is an effective diagnostic technique which is used for breast cancer detection with the help of infrared technology. In this paper, we propose a fully automatic breast cancer detection system. First, U-Net network is used to automatically extract and isolate the breast area from the rest of the body which behaves as noise during the breast cancer detection model. Second, we propose a two-class deep learning model, which is trained from scratch for the classification of normal and abnormal breast tissues from thermal images. Also, it is used to extract more characteristics from the dataset that is helpful in training the network and improve the efficiency of the classification process. The proposed system is evaluated using real data (A benchmark, database (DMR-IR)) and achieved accuracy = 99.33%, sensitivity = 100% and specificity = 98.67%. The proposed system is expected to be a helpful tool for physicians in clinical use.
- Published
- 2022