Please use this identifier to cite or link to this item: https://doi.org/10.1038/s41598-018-34300-2
Title: Deep learning enables automated scoring of liver fibrosis stages
Authors: Yu Y.
Wang J.
Ng C.W. 
Ma Y. 
Mo S.
Fong E.L.S. 
Xing J.
Song Z.
Xie Y.
Si K.
Wee A. 
Welsch R.E.
So P.T.C.
Yu H. 
Keywords: biological marker
collagen
algorithm
animal
artificial neural network
biopsy
diagnostic imaging
image processing
liver cirrhosis
machine learning
male
metabolism
microscopy
nuclear magnetic resonance imaging
pathology
procedures
rat
reproducibility
x-ray computed tomography
Algorithms
Animals
Biomarkers
Biopsy
Collagen
Deep Learning
Diagnostic Imaging
Image Processing, Computer-Assisted
Liver Cirrhosis
Machine Learning
Magnetic Resonance Imaging
Male
Microscopy
Neural Networks (Computer)
Rats
Reproducibility of Results
Tomography, X-Ray Computed
Issue Date: 2018
Publisher: Nature Publishing Group
Citation: Yu Y., Wang J., Ng C.W., Ma Y., Mo S., Fong E.L.S., Xing J., Song Z., Xie Y., Si K., Wee A., Welsch R.E., So P.T.C., Yu H. (2018). Deep learning enables automated scoring of liver fibrosis stages. Scientific Reports 8 (1) : 16016. ScholarBank@NUS Repository. https://doi.org/10.1038/s41598-018-34300-2
Abstract: Current liver fibrosis scoring by computer-assisted image analytics is not fully automated as it requires manual preprocessing (segmentation and feature extraction) typically based on domain knowledge in liver pathology. Deep learning-based algorithms can potentially classify these images without the need for preprocessing through learning from a large dataset of images. We investigated the performance of classification models built using a deep learning-based algorithm pre-trained using multiple sources of images to score liver fibrosis and compared them against conventional non-deep learning-based algorithms - artificial neural networks (ANN), multinomial logistic regression (MLR), support vector machines (SVM) and random forests (RF). Automated feature classification and fibrosis scoring were achieved by using a transfer learning-based deep learning network, AlexNet-Convolutional Neural Networks (CNN), with balanced area under receiver operating characteristic (AUROC) values of up to 0.85–0.95 versus ANN (AUROC of up to 0.87–1.00), MLR (AUROC of up to 0.73–1.00), SVM (AUROC of up to 0.69–0.99) and RF (AUROC of up to 0.94–0.99). Results indicate that a deep learning-based algorithm with transfer learning enables the construction of a fully automated and accurate prediction model for scoring liver fibrosis stages that is comparable to other conventional non-deep learning-based algorithms that are not fully automated. © 2018, The Author(s).
Source Title: Scientific Reports
URI: https://scholarbank.nus.edu.sg/handle/10635/174199
ISSN: 2045-2322
DOI: 10.1038/s41598-018-34300-2
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_1038_s41598-018-34300-2.pdf2.35 MBAdobe PDF

OPEN

NoneView/Download

SCOPUSTM   
Citations

11
checked on Oct 22, 2020

Page view(s)

13
checked on Oct 22, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.