Convolutional neural networks: an overview and application in radiology
Сверточные нейронные сети: обзор и применение в радиологии
2018-06-22
SCID: 54.1/beew2ump
Discuss with AI
Convolutional neural network (CNN)convolution layersfully connected layerspooling layersradiology applications
Figures from the paper
Abstract (AI)
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.
Key Findings
1
Applying CNNs in radiology faces key challenges of small datasets and overfitting, and the article discusses techniques to mitigate them.
2
CNNs are a dominant class of deep learning methods for computer vision and are increasingly applied in radiology.
3
CNNs automatically and adaptively learn spatial hierarchies of features using layers like convolution, pooling, and fully connected layers trained by backpropagation.
4
Understanding CNN concepts, advantages, and limitations is essential to augment radiologist performance and improve patient care.
Research Object
Convolutional neural networks (CNNs) applied in radiology
Research Subject
The concepts, architectures, challenges (e.g., small datasets, overfitting), techniques to mitigate them, and applications of CNNs to radiological tasks aimed at augmenting radiologist performance and patient care
Publication Details
Publication Date
2018-06-22
Journal
Publisher
ISSN
Cited by
4680
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
Deep Residual Learning for Image Recognition2016
Very Deep Convolutional Networks for Large-Scale Image Recognition2014
Intriguing properties of neural networks2013
Proceedings of the 24th international conference on Machine learning2007
Learning Deep Features for Discriminative Localization2016
Improving neural networks by preventing co-adaptation of feature detectors2012
Cited by10
An overview of deep learning in medical imaging focusing on MRI2018
Comprehensive Review of Artificial Neural Network Applications to Pattern Recognition2019
AI applications to medical images: From machine learning to deep learning2021
Signaling pathways involved in colorectal cancer: pathogenesis and targeted therapy2024
Machine Learning Methods for Small Data Challenges in Molecular Science2023
Human emotion recognition from EEG-based brain–computer interface using machine learning: a comprehensive review2022
Vision-language models for medical report generation and visual question answering: a review2024
Artificial Intelligence and Neuroscience: Transformative Synergies in Brain Research and Clinical Applications2025
How much is the view from the window worth? Machine learning-driven hedonic pricing model of the real estate market2022
Geodesign in the era of artificial intelligence2025