A comprehensive survey on convolutional neural network in medical image analysis
- PDF / 5,504,415 Bytes
- 45 Pages / 439.37 x 666.142 pts Page_size
- 57 Downloads / 194 Views
A comprehensive survey on convolutional neural network in medical image analysis Xujing Yao 1 & Xinyue Wang 1 & Shui-Hua Wang 1,2,3 & Yu-Dong Zhang 1,2 Received: 21 May 2020 / Revised: 30 July 2020 / Accepted: 13 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
CNN is inspired from Primary Visual (V1) neurons. It is a typical deep learning technique and can help teach machine how to see and identify objects. In the most recent decade, deep learning develops rapidly and has been well used in various fields of expertise such as computer vision and natural language processing. As the representative algorithm of deep learning, Convolution Neural Network (CNN) has been regarded as a breakthrough of historic significance in image processing and visual recognition tasks since the astonishing results achieved on ImageNet Large Scale Visual Recognition Competition (ILSVRC) Unlike methods based on handcrafted features, CNN models can build highlevel features from low-level ones in a data-driven fashion and have displayed great potential in medical image analysis among the aspects of segmentation of histological images identification, lesion detection, tissue classification, etc. This paper provides a review on CNN from the perspectives of its basic mechanism introduction, structure, typical architecture and main application in medical image analysis through analyzing over 100 references from Google Scholar, PubMed, Web of Science and various sources published from 1958 to 2020. Keywords Deep learning . Feedforward Neural Network . Convolutional neural network . Breast Cancer . Lung Nodule . Brain Tumor . Medical image analysis
* Shui-Hua Wang [email protected] * Yu-Dong Zhang [email protected] Xujing Yao [email protected] Xinyue Wang [email protected] Extended author information available on the last page of the article
Multimedia Tools and Applications
1 Background Deep Learning (DL) is a promising research direction in the Machine Learning (ML) area. By means of utilizing DL technique, computational models are capable to learn the features and representation of data with a process of extraction. This is an innovation that brings dramatical improvements in image recognition, object detection, voice recognition, genomic science and many other domains in real life [51, 84]. The study of machine learning is inspired in part by the exploration of human brain. Around 300 B.C., the concept of understanding the brain has attracted a lot of attention of researchers, among which the celebrated philosopher Aristotle is considered as the forerunner, due to the reason that he opens the history of human trying to learn the brain [72]. In 1943, the team of McCulloch and Pitts [61] brought the earlier neural network model: MCP Neural Model into the attention of public. About one decade later, Rosenblatt [75] introduced the perceptron based on this MCP model to complete the classification task. However, just one decade after the introduction, a significant flaw was identified by Minsky and Pa
Data Loading...
