Image classification using deep learning algorithms
Skin cancer is one of the most common cancers not only in the United States, but also worldwide, with almost 10,000 people in the U.S. being diagnosed with it every day. Early detection is important in order to save the lives of the affected patients. Computer aided diagnostic systems, such as Neural Networks, can drastically aid physicians to detect skin cancer in the early stages and avoid unnecessary biopsies, improving patient care and reducing cost. Moreover, portable systems and even mobile apps, without of course replacing physicians, assist people by providing suggested diagnoses that can act as a warning sign and lead to the early detection of skin lesions. With the goal of creating a portable system that is accessible to various health care facilities, I built upon a Convolutional Neural Network previously designed for the concept. In this, the system is able to take in images and assess what type of skin lesion is captured. This model is then compared to the diagnosis of a trained Physician to see how well it performs comparatively.