Automated breast lesion detection with semi-supervised learning approaches | |
| Author | Weeraphat Tulathon |
| Call Number | AIT Thesis no.TC-24-01 |
| Subject(s) | Breast--Cancer--Diagnosis Artificial intelligence--Medical applications Machine learning |
| 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 remains a significant global health concern, necessitating the development of advanced and accurate diagnostic tools. This study presents a novel automated breast cancer detection approach by harnessing complex S21 data obtained through microwave imaging. The proposed method integrates semi-supervised learning techniques to enhance the accuracy and reliability of breast cancer classification. This study adopts a semi-supervised learning paradigm,combining labeled data from known breast cancer cases with unlabeled data, resulting in a more robust and cost effective classification model. Three types of semi-supervised techniques, including self-training, label propagation, and label spreading, are employed to explore the potential of each approach. This innovative approach contributes to the ongoing efforts in early breast cancer detection, providing the opportunity to decrease false positives and increase diagnostic . The results of this study hold promise for enhancing breast cancer screening and, subsequently, improving patient outcomes and quality of life. |
| 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) | Teerapat Sanguankotchakorn;Poompat Saengudomlert |
| Scholarship Donor(s) | Royal Thai Government Fellowship |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2024 |