Research project working on detecting skin cancer using Deep Learning techniques
The number of people diagnosed with skin cancer in the last three decades is higher than all previous decades combined, and that number is still increasing. $8.1 million a year goes to skin cancer treatment, with a $3.3 million single attribute to melanoma. The ratio of dermatologists vs. patients with skin diseases in some of the third world countries is 1:6700. Mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 and can, therefore, likely provide low-cost universal access to vital diagnostic care.
Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. A part of the system would use computational intelligence techniques like filtering, segmentation, feature extraction, image pre-processing, and edge detection. These are part of image processing and are used to identify the region affected by the disease, the form of the affected area and its color, etc. Earlier diagnosis can prevent patients from missing the best time of treatments; hence it can reduce the costs of treatment and avoid complications. We see great potential in technologies like machine learning with various applications in the healthcare industry, which in turn inspires us to use it for solving skin disease prediction problems, to make this world a better place for everyone