IBEGBUNAM, CHIDERA UGOCHUKWU (2025) AI-POWERED SKIN LESION DETECTION SYSTEM. Other thesis, GODFREY OKOYE UNIVERSITY, ENUGU.
![[img]](https://eprints.gouni.edu.ng/style/images/fileicons/text.png) |
Text
REPO317.docx Download (2MB) |
Abstract
Cancer on the skin over the years have continued to be one of the most common and life threatening type of cancer in every part of the world, with melanoma been the leading type of skin cancer related killing type of infection. Early and correct diagnosis plays a vital role in better patient outcomes, but in most cases, prompt diagnosis is not being done and it is most incidences where there is lack of dermatological specialist found in the rural and underdeveloped areas. The study is an exploration into how an AI-based skin lesion detection system can be developed and deployed by taking advantage of the capabilities of deep learning algorithms, in this case, Convolutional Neural Networks (CNNs) that will allow classifying a skin lesion as benign, malignant, or suspicious. The research also critically examined the current literature and systems with most of them presenting serious weaknesses, which include bias in the datasets, a lack of model transparency, reliance on expert interpretation, poor ease of use, and inability to accommodate darker skin tones. The study is part of a series of AI implemented in dermatology and will not only further the diagnostic precision, but, unlike other possibilities, it will focus on inclusivity, accessibility, and explainability. The built-in ability to offer decision support and feedback only goes further to make the system a worthwhile addition to clinical decision support. The results support the visionary role of AI in improving early skin cancer detection when informed by ethical design missions and policies of implementation contextualizing users.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Natural and Applied Sciences |
| Depositing User: | Uchenna Eneogwe |
| Date Deposited: | 01 Jun 2026 12:23 |
| Last Modified: | 01 Jun 2026 12:23 |
| URI: | http://eprints.gouni.edu.ng/id/eprint/5698 |
Actions (login required)
 |
View Item |
