BrUNO
Introducing
A revolutionary AI-powered skin cancer detector that is designed to provide accurate and reliable results in a matter of seconds. Dermo has trained this cutting-edge model using the latest technology and thousands of clinically validated images to ensure that it can detect even the slightest signs of skin cancer with precision and confidence.
Our model's advanced algorithms analyze skin lesion images with a high degree of accuracy, providing users with a comprehensive report that highlights any areas of concern. BrUNO's capabilities are constantly being improved and refined, so you can trust that you are always receiving the most accurate and up-to-date results.
At the end of the day, your skin health is crucial and BrUNO is here to provide you with the peace of mind you need to take control of your skin care.
With its advanced technology, user-friendly approach and constant improvement, BrUNO is the go-to AI-powered skin cancer detector for anyone who values accuracy and reliability.
Motivation
Melanoma causes 60,000 deaths each year, 1 person every 9 minutes. More than 320,000 people are diagnosed each year with some dermatological disease. In addition, according to the WHO, half of the population does not have access to public health under appropriate conditions, but they do have access to a mobile phone and the internet.
We are driven by a mission to improve people's lives through technology. By creating this AI model, we hope to provide people with a tool that can help identify potential skin cancer early on, giving them the best chance for successful treatment and recovery. Our goal is to use the power of technology to make a positive impact on people's lives, and we believe this AI model is one step in that direction.
BrUNO-1 Limitations
Limited to image analysis: BrUNO-1 is limited to analyzing skin lesion images, and cannot detect skin cancer from other forms of medical data such as blood tests or biopsies.
Limited by training data: The effectiveness of BrUNO depends on the quality and diversity of the training data it has received. In some cases the training data is limited by the wide range of skin types, so it may not perform as well as expected.
False positives and false negatives: While BrUNO is designed to be highly accurate, it is not infallible. There is a risk of false positives, which could lead to unnecessary medical treatment, or false negatives, which could lead to undiagnosed skin cancer.
Cannot replace a medical professional: While BrUNO can provide an initial diagnosis, it cannot replace the expertise of a trained medical professional. It is important to always consult with a doctor or dermatologist for a comprehensive evaluation of any skin concerns.
Behind the UI
BrUNO is a machine learning model that was built using the TensorFlow open-source software library. TensorFlow is a framework for developing AI models that allows to build and train models efficiently. A TF model is created by defining the network architecture using a high-level programming language, in this case Python. The model is then trained on a dataset using various optimization algorithms to adjust the weights of the network, minimizing the error between the predicted and actual outputs.
The training process involves feeding the input data to the model, calculating the error between the predicted and actual output, and then updating the model's parameters to reduce the error. This process is repeated over a large number of epochs until the model achieves a satisfactory level of accuracy. Once is trained, it can be used to make predictions on new data.
CHECK THE DATABASE WE USED FOR OUR MAIN TRAINING
Hosted and built with Streamlit
Streamlit is an open-source Python library that allows developers to easily create web applications for data science and machine learning projects. It enables developers to create interactive, real-time web applications without getting involved in difficult web development or JavaScript. ​
Dermoverse uses Streamlit to create an interactive web application for users that acts as a bridge between them and the BrUNO-1 model. This web app allows users to upload an image of a skin lesion and it returns back the prediction on that photo.
Next Phase: Multi-disease
Date Announced Soon