Convolutional neural network (CNN) is a class of deep learning methods dominant in various computer vision tasks and is attracting interest across a variety of domains, including radiology. This review article offers a perspective on the basic concepts of CNN and its application, and discusses the two challenges in applying CNN to radiological tasks – small dataset and overfitting – as well as techniques to minimize them.
• Convolutional neural network is a class of deep learning methods which has become dominant in various computer vision tasks and is attracting interest across a variety of domains, including radiology.
• Convolutional neural network is composed of multiple building blocks, such as convolution layers, pooling layers, and fully connected layers, and is designed to automatically and adaptively learn spatial hierarchies of features through a backpropagation algorithm.
• Familiarity with the concepts and advantages, as well as limitations, of convolutional neural network is essential to leverage its potential to improve radiologist performance and, eventually, patient care.
Authors: Rikiya Yamashita, Mizuho Nishio, Richard Kinh Gian Do, Kaori Togashi