• Sankar Mandal, Abhisekh Baruah
• Sonali Mondal
• Biswajit Das

Skin cancer, inclusive of melanoma, presents a substantial global health challenge given its escalating prevalence and the intricacies entailed in diagnosis. The emergence of deep learning technologies has spurred advancements in automated diagnostic systems, particularly within the healthcare domain. This paper introduces a hybrid deep learning approach for melanoma cancer classification from lesion images, utilizing Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The model is structured into four phases: data collection, preprocessing and feature extraction, model design and training and model evaluation. While CNN extracts feature from images, LSTM captures temporal dependencies, augmenting model training accuracy. This methodology yielded an 82% accuracy rate in melanoma classification. While promising, further research is needed to refine model architecture, explore techniques for data augmentation, and diversify datasets. This model holds promise as a valuable tool for clinicians in early diagnosis and treatment planning, contributing to enhanced patient outcomes in the combat against melanoma cancer.

Convolutional Neural Network, Deep learning, Long-Short-Term Memory, Melanoma

"Melanoma Cancer Classification Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.p754-p759, April-2024, Available :http://www.jetir.org/papers/JETIR2404G99.pdf

"Melanoma Cancer Classification Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppp754-p759, April-2024, Available at : http://www.jetir.org/papers/JETIR2404G99.pdf