Skin Cancer Detection and Classification
Cancer Diagnosis via Convolutional Neural Networks IA + web application
Employing Python, Flask, and Convolutional Neural Networks for the predictive model, along with frontend technologies, this tool efficiently detects and classifies skin cancer types. This project constituted my Thesis research in Computer Engineering.
This project harnesses the power of Python, Flask, and CNNs for its core predictive model, alongside cutting-edge frontend technologies to accurately detect and categorize types of skin lesions. Originating as my thesis in Computer Engineering, the tool represents the culmination of rigorous research and development.
A concise, multidisciplinary project applying Convolutional Neural Networks to a web-based skin cancer diagnostic tool.
Integrating AI in Healthcare
The Skin Cancer Diagnosis application sets a new standard in medical diagnostic tools available online. By making use of interactive elements and an intuitive design, the platform ensures that users can effortlessly upload images for analysis, receive detailed diagnostic information, and understand the potential types of skin cancer they might be dealing with.
The objective of developing the Skin Cancer Diagnosis application was to integrate the analytical capabilities of neural networks with the accessibility of web technologies. The prime challenge was to harness CNNs, renowned for their efficacy in image recognition tasks, and merge them with a Flask backend to process user-uploaded skin lesion images. The frontend, designed for simplicity, provides a seamless user interface for individuals to upload images and receive instant diagnostic feedback.