Deep Neural Network for Breast Tumor Classification Through Histopathological Image | ||||
| Journal of Advanced Engineering Trends | ||||
| Article 10, Volume 42, Issue 1, January 2022, Page 121-129 PDF (749.86 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/jaet.2021.67697.1099 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
amira mofreh ibrahim   1; Kamel Rahouma 2; Hesham Fathy Aly Hamed3
| ||||
| 1School of engineering and applied science, Nile University, Giza, Egypt | ||||
| 2Minia University | ||||
| 3Electrical Eng. Depart. , Faculty of Eng. Minia University | ||||
| Abstract | ||||
| Most oncologists differ in their opinions about the diagnosis using histopathological images, so the manual diagnosis of breast cancer is one of the difficult tasks, and it also needs high experience. Building a model of breast tumor classification is an essential task. Computer-aided diagnosis (CAD) enables efficient and accurate diagnosis of this type of imaging. Moreover, it helps early diagnosis of breast tumors. Conventional neural networks (CNN) are used to classify breast tumors. This study's theoretical basis is the development of a deep learning tumor classification system through histopathological images based on a benign or malignant tumor. It uses a deep learning approach, i.e., the proposed CNN Network consists of three stages. The first stage is pre-processing. The second stage is the feature extraction stage that takes input as augmented preprocessed images. The third stage classifies the extracted features as benign or malignant images. The BreakHis database is used and implemented and contains 7909 images of breast tumor tissue for 82 patients. Several tests were performed to achieve the best diagnostic accuracy of 91.37 % in the shortest treatment time. | ||||
| Keywords | ||||
| Breast cancer; CAD system; Images classification; histopathology imaging; Conventional neural networks | ||||
|
Supplementary Files
|
||||
|
Statistics Article View: 314 PDF Download: 351 |
||||
