Convolutional neural networks: an overview and application in radiology

By Rikiya Yamashita, Mizuho Nishio, Richard K. G. Do, Kaori Togashi. 2018

4,045 citations recorded by the source corpus.

Convolutional neural network (CNN), a class of artificial neural networks that has become dominant in various computer vision tasks, is attracting interest across a variety of domains, including radiology. CNN is designed to automatically and adaptively learn spatial hierarchies of features through backpropagation by using multiple building blocks, such as convolution layers, pooling layers, and fully connected layers. This review article offers a perspective on the basic concepts of CNN and its application to various radiological tasks, and discusses its challenges and future directions in the field of radiology. Two challenges in applying CNN to radiological tasks, small dataset and overfitting, will also be covered in this article, as well as techniques to minimize them. Being familiar with the concepts and advantages, as well as limitations, of CNN is essential to leverage its potential in diagnostic radiology, with the goal of augmenting the performance of radiologists and improving patient care.Key Points• 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.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Synthesis of Realistic ECG using Generative Adversarial Networks (2019, methodology): “When designing the convolution layers, small and odd-numbered ﬁlter sizes and strides were used as recommended in the literature [40].”
COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from X-ray images (2020, positive): “…revealing the potentials of computed tomography (CT) scans and X-ray images in detecting COVID-19 and weakness of the human-centered diagnosis, there have been several studies [5]-[7] trying to develop automatic COVID-19 classiﬁcation systems, mainly using Convolutional Neural Networks (CNNs) [4].”
Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of Medical Images: Results from Recently Published Papers (2019, background): “Notably, there is a remarkable interest in using AI for diagnostic analysis of various types of medical images, primarily through convolutional neural networks, a type of deep learning technology referred to as “computer vision” (2-4).”
What the radiologist should know about artificial intelligence – an ESR white paper (2019, background): “” [ 13].”
Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis (2020, background): “represents the fundamental component of the CNN architecture [47].”
A review of medical image data augmentation techniques for deep learning applications (2021, background): “Convolutional Neural Networks (CNNs) are a type of deep learning approach which are able to automatically learn a set of feature detectors, usually over a number of layers (making the model ‘deep’), from a labelled dataset.(2) CNNs have been utilised in medical imaging tasks including image classifi”
A Review of Convolutional Neural Network Applied to Fruit Image Processing (2020, methodology): “Alternatively, we can apply a padding technique to keep the same in-plane dimension by adding zeroes around the input and ﬁtting the center of the kernel on outermost elements [44,45].”
Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition (2019, background): “Although, there is some attempt in the past to address the challenges in PR tasks using convolutional NN (CNN) and processing of image [58]–[60].”
A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis (2019, neutral): “We refer the reader to a number of reviews of DL in medical imaging (Hesamian et al., 2019; Lundervold and Lundervold, 2019; Yamashita et al., 2018).”