Breast cancer detection and classification using mammowave clinical data and CNN variants | |
| Author | Pandey, Miraj |
| Call Number | AIT Thesis no.TC-24-02 |
| Subject(s) | Breast--Cancer--Diagnosis Microwave imaging Artificial intelligence--Medical applications |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Telecommunications |
| Publisher | Asian Institute of Technology |
| Abstract | Breast cancer is the most prevailing type of carcinoma and a pre-eminent cause of cancer induced female mortality in developing countries worldwide. In contrast to its counter parts, such as other forms of cancer, it exhibits lower fatality rates and a good prognosis. Furthermore, the rates can be reduced with early-stage diagnosis of the disease. The existing gold standard technologies for breast cancer screening are fundamentally recommended for diagnosing the disease in women aged 40 and above. However, the efficacy of employing them in the diagnosis of breast cancer in young women may be reduced significantly due to the differences in breast profile within these age categories. Moreover, they tend to subject the patient to ionizing radiations, which have carcino genic effects and cause mutations in human genes. The use of non-ionizing, microwave imaging has shown promising results in detecting anomalies in breasts of females having dense breast tissue and is much safer. With the advent of Artificial Intelligence (AI) and Machine learning and its integration with the healthcare system, the development of robust and efficient models for diagno sis of this disease has been possible. From the literature, it is evident that the use of microwave imaging consolidated by its amalgamation with machine learning models, offers a better diagnosis system for breast cancer detection and classification. This study proposes an efficient machine learning model based on Convolutional Neural Networks (CNNs) , trained on an extensive labeled dataset comprising 180 patients and 352 breasts. This ingenious approach aims to contribute to the contemporary efforts in early screening and administering breast cancer at an early stage, thereby reducing the mortality rate. |
| Year | 2024 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Telecommunications (TC) |
| Chairperson(s) | Attaphongse Taparugssanagorn |
| Examination Committee(s) | Poompat Saengudomlert;Teerapat Sanguankotchakorn |
| Scholarship Donor(s) | His Majesty The King’s Scholarship (Thailand) |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2024 |