As a part of my internship at iSmile Technologies, I am currently working as the project lead on an Oncology project – something that I wanted to work on, for a very long time. I’m immensely grateful for this wonderful opportunity to lead and work with a very talented team. And for their hard work and contribution for materializing this project.
A little more about our project.
The inspiration for our Cancer Detection Project stemmed from the fact that countless people end up losing their energy, money and even their lives just because they were not able to detect and treat cancer on time. The idea was to develop a technology that helps people and doctors to be able to detect Cancer cells at a much earlier phase. Consequently, this project would be extremely relevant and important to people, as well as healthcare organizations worldwide.
The project enables users to click and securely upload images – of growths, lumps or other irregularities in the body that might be a symptom of Skin Cancer, on our app and find out whether it is cancerous. They can also learn about the next steps that are needed to be taken, if found positive. The user data will be kept completely confidential. For now, we are working with Skin cancer since it has the most visible symptoms. The app will also require certain contextual input (symptoms, mood, etc) from the users to further enhance the accuracy of prediction.
So far in this journey, we have collected and preprocessed the dataset which closely resemble the images users might click using their mobiles to ensure accuracy. After substantial research and discussions, we have a comprehensive idea for our data models and are now in the training and testing stage of the data models.
In the future, we look forward to achieving an even higher accuracy rate for our models, their successful deployment, incorporating a recommendation system for hospitals and making the app extremely user-friendly.
Hadoop is an open-source framework of programs that is used to store and process big data. Hadoop uses multiple clusters of computers to analyze big data sets in parallel. The distributed processing of data sets can