• Shaikh Mohammed Ashfaque
• Shadaab Hasan
• Siddharth Pallar
• Ayan Mastim
• Hamza Khan

Skin cancer is one of the most prevalent forms of cancer globally and according to the World Health Organization, it accounts for one in three diagnosed cancer types. With increasing incidence rates each year it necessitates the need for early detection. Early detection, accurate prediction and precise prognosis are crucial for successful treatment outcomes. In this project, we propose the development of a skin cancer prediction system. The primary objective of this project is to create a robust predictive model capable of accurately classifying different types of skin cancers based on various features extracted from dermoscopic images. The dataset (HAM10000) used for training and testing the model consists of a diverse collection of high-resolution images annotated by dermatologists ensuring the accuracy of the predictive model. The project workflow involves several key stages: 1. Data Preprocessing: The raw image data undergo preprocessing steps such as resizing, normalization, and augmentation to enhance the quality and diversity of the dataset. 2. Model Selection and Training: A variety of machine learning algorithms, including but not limited to support vector machines (SVM), random forests, and convolutional neural networks (CNN), are explored for their suitability in skin cancer classification. 3. Model Evaluation: The trained models are evaluated using performance metrics such as accuracy, precision, recall, and F1-score on a separate test dataset. Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) scores are also analyzed to assess the models' discriminatory power and robustness. 4. Deployment in Jupyter Notebook: The final predictive model, along with detailed documentation and code, is encapsulated within a Jupyter Notebook environment for ease of access and reproducibility. The proposed skin cancer prediction system aims to empower healthcare professionals with a tool for early detection and diagnosis, thereby improving patient outcomes and reducing the burden on healthcare systems. In conclusion, this project demonstrates the feasibility and effectiveness of utilizing machine learning techniques within the Jupyter Notebook environment

Skin cancer, Jupyter notebook, Machine learning, HAM10000, Convolutional neural networks(CNN)

"Skin cancer detection system", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.j442-j453, June-2024, Available :http://www.jetir.org/papers/JETIR2406947.pdf

"Skin cancer detection system", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. ppj442-j453, June-2024, Available at : http://www.jetir.org/papers/JETIR2406947.pdf