Enhancing gastrointestinal tumor detection in non-camera wireless capsule endoscopy using artificial intelligence for classification | |
| Author | Nunnapat Thaweesukolrat |
| Call Number | AIT Thesis no.TC-25-02 |
| Subject(s) | Gastrointestinal system--Diseases--Diagnosis Artificial intelligence--Medical applications Endoscopy--Technological innovations |
| 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 | The early detection of gastrointestinal cancers remains a major challenge due to the asymp tomatic nature of early-stage tumors, necessitating advancements in non-invasive diagnostic techniques. ThisstudyproposesanEfficientNet-basedradiosignalrecognitionframeworklever aging Ultra-Wideband Wireless Capsule Endoscopy (UWB-WCE) for the detection of small intestinal cancers. Unlike conventional imaging-based methods, our approach utilizes channel characteristics of UWB signals, processed through deep learning techniques, to differentiate normal and cancerous tissues. By integrating Convolutional Neural Networks (CNNs) with En semble learning, which combines feature extraction strength with reduced model variance, the framework enhances classification accuracy while maintaining computational efficiency. The results demonstrate superior performance in identifying diverse tumor signatures from S21 sig nal data, highlighting the potential for real-time, automated, and non-invasive cancer screening. These findings underscore the viability of radio signal-based diagnostics as a transformative tool for improving early detection and patient outcomes in gastrointestinal cancer screening. |
| Year | 2025 |
| 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) | Chaklam Silpasuwanchai;Chantri Polprasert |
| Scholarship Donor(s) | Royal Thai Government;AIT Fellowship |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2025 |