Quantum Machine Learning for Cancer Detection in Medicine

Abstract

In global health, cancer represents a major problem. Its detection plays a crucial role in the personalisation of treatment. With traditional methods of cancer screening, certain limitations and problems have arisen such as diagnostic errors (false positive/negative), costs and the complexity of medical data (MRI,X-rays). With machine learning and deep learning, which is a sub-type of artificial intelligence, these problems can be solved using image processing techniques and complex data processing using specific algorithms such as Support Vector Machine (SVM), Neural Network (NN) and Convolutionel Neural Network (CNN). However, these approaches reach their limits when dealing with massive and multidimensional data. In response, a new approach has emerged as a promising solution, which exploits the principles of quantum mechanics such as superposition, which guarantees parralelism and entanglement. this is Quantum Computing. quite simply, it is the intersection of Physics, Mathematics and Computer Science. The combination of quantum computing and machine learning has led to the creation of a qualitative extension in the world of computation. Quantum Machine Learning (QML) is an approach that aims to solve all the problems mentioned above, focusing on the classical quantum architecture such as Quantum SVM, Quatnum NN and Quantum CNN. QML algorithms analyse multiple dimensions of medical data at the same time, while being more accurate and faster than classical machines.