International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Melanoma Cancer Detection using Deep Learning |
|---|---|
| ABSTRACT | Early detection of melanoma drastically improves prognosis. This paper presents a compact, deployable deep- learning pipeline for binary melanoma classification (benign vs malignant) that emphasizes explainability and deployability. The approach uses a MobileNetV2 backbone with transfer learning, dataset-specific preprocessing, class-weighting to address imbalance, ROC-based threshold selection (Youden Index), and Grad-CAM visual explanations for clinical interpretability. We condensed a detailed project report into this single-column manuscript and included representative diagrams and results. The images used in this manuscript are the actual project visuals provided by the authors. |
| TITLE | |
| AUTHOR | CHETHAN K V, MANOJ H B, KURUBARAHALLI NINGARAJA, VISHNU N S, DR. MALLIKARJUNA S B Department of Artificial Intelligence & Machine Learning, BIET, Davanagere, Karnataka, India Guide, Department of Artificial Intelligence & Machine Learning, BIET, Davanagere, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312034 |
| pdf/34_Melanoma Cancer Detection using Deep Learning.pdf | |
| KEYWORDS |
