الفهرس 
Introduction and Literature ReviewOnly 14 pages are availabe for public view
 |  | from | 120 |  |  |
| | | from | 120 | | |
Abstract
Breast cancer is one of the most serious types of cancer that can occur in women. The automatic diagnosis of breast cancer by analyzing histological images (HIs) is preferable for patients and their prognosis. The classification of HIs provides clinicians with an accurate understanding of diseases and allows them to treat patients more efficiently. Deep learning (DL) approaches have been successfully employed in a variety of fields, particularly medical imaging, and due to their capacity to extract features automatically. This study aims to classify different types of breast cancer using HIs. In this research, we present an enhanced capsule network that extracts multi-scale features using the Res2Net block and four additional convolutional layers. Furthermore, the proposed method has fewer parameters due to using small convolutional kernels and the Res2Net block. The suggested model was trained and evaluated using the publicly BreakHis dataset, achieving an accuracy of 95.6 % and a recall of 97.2%. As a result, the new method outperforms the old ones since it automatically learns the best possible features. The testing results show that the model outperformed the previous DL methods. Chapter 1 gives the introduction about the Breast anatomy and its medical problems. For instance, Breast tumors are explored because of its wide effect on the women in different ages. Then, the role of the artificial indigence has been explored in the medical imaging. The relevant literature survey has been done to indicate the importance of our study and to show the progress of the deep learning techniques for diagnosing the Breast cancer. Chapter 2 explained the basics and the physical concepts of the different medical imaging modalities. We started with X-ray and then CT crossing mammography and ultrasound to explain the background of such modalities. Chapter 3 offers brief, but relevant, basics of the image processing using the deep learning techniques. It starts with the different stages of preprocessing of medical images. Then followed by the definitions of the segmentation tools and the features extraction to understand the identification process. Chapter 4 explores the proposed method for Breast cancer identification that performed CAD system has been used to diagnose breast tumors early, quickly, and accurately. The study is based on breast cancer classification utilizing capsule net architecture. In this paper, a new model built on the capsule network is evaluated. The Res2Net block is used in the proposed capsule network to improve the feature extraction of convolutional layers. The proposed model also has fewer parameters due to using small convolutional kernels and the Res2Net block. On the publicly accessible BreakHis dataset, we conducted a comparative examination of multiple transfer learning models in this study. It has an accuracy of 95.6% in the proposed model. The results demonstrate that this method can be utilized as an automated tool to assist clinicians in disease detection, which may lead to more concentration in therapy in the early stages. For future work, we can combine two or more transfer learning models and extract features from them to achieve better results and develop more robust classifiers with stronger generalization abilities.