Detecting Cancer with Machine Learning and Computer Vision Models

Computer Vision and Machine Learning are two important fields of Artificial Intelligence. Computer Vision focuses on deciphering image content while Machine Learning attempts to extract knowledge from large amounts of data with the goal of creating models that can perform useful tasks in everyday life. The two fields are closely related as the integration of Machine Learning approaches lead to significant breakthroughs in many Computer Vision challenges. A crucial task within Computer Vision is classification, where we expect a model to sort new images into a predefined set of classes. There are many potential real-world applications of such models in a variety of fields such as autonomous driving, online commerce or industrial quality assurance. They are also likely to find their place in medicine in the future, where they may be used for detecting illnesses from different types of medical imaging such as MRIs, CT scans or X-ray images. Just recently, an AI tool has successfully identified signs of breast cancer that have been missed by doctors (read more here).

In this project, we will cover the basics of machine learning and image processing and combine the two to perform image classification. We will train simple image classification models and test their performance on expected inputs. We will look at existing datasets for medical imaging and apply our models to them.