Skin Cancer Detection using Convolutional Neural Networks

Khare, Vasu (2025) Skin Cancer Detection using Convolutional Neural Networks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (62kB) | Preview

Abstract

This study looks at how we can use deep learning, mostly CNN models, to detect different types of skin cancer. Skin cancer rates are going up all over the world, and the old ways doctors use to diagnose it have some big limits. That's why we wanted to make a model that works well but also makes sense to people who need to use it. We worked with the derm12345 dataset and did a bunch of things to get it ready, like fixing the problem where some cancer types had way more examples than others. We also added ways to show why the model made each decision, using stuff like Grad-CAM to create visual explanations. The model we ended up with is meant to help skin doctors make better diagnoses because it's both more reliable at classifying skin cancers and shows its work in a way that doctors can actually understand and trust when they're seeing patients.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Zahoor, Sheresh UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > Life sciences > Medical sciences > Pathology > Tumors > Cancer Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	28 May 2026 14:34
Last Modified:	28 May 2026 14:34
URI:	https://norma.ncirl.ie/id/eprint/9326

Actions (login required)

View Item