Cargando…

A Novel Computer-Aided Diagnosis Scheme on Small Annotated Set: G2C-CAD

PURPOSE: Computer-aided diagnosis (CAD) can aid in improving diagnostic level; however, the main problem currently faced by CAD is that it cannot obtain sufficient labeled samples. To solve this problem, in this study, we adopt a generative adversarial network (GAN) approach and design a semisupervi...

Descripción completa

Detalles Bibliográficos
Autores principales: Zheng, Guangyuan, Han, Guanghui, Soomro, Nouman Q., Ma, Linjuan, Zhang, Fuquan, Zhao, Yanfeng, Zhao, Xinming, Zhou, Chunwu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6500711/
https://www.ncbi.nlm.nih.gov/pubmed/31119180
http://dx.doi.org/10.1155/2019/6425963
_version_ 1783416003252715520
author Zheng, Guangyuan
Han, Guanghui
Soomro, Nouman Q.
Ma, Linjuan
Zhang, Fuquan
Zhao, Yanfeng
Zhao, Xinming
Zhou, Chunwu
author_facet Zheng, Guangyuan
Han, Guanghui
Soomro, Nouman Q.
Ma, Linjuan
Zhang, Fuquan
Zhao, Yanfeng
Zhao, Xinming
Zhou, Chunwu
author_sort Zheng, Guangyuan
collection PubMed
description PURPOSE: Computer-aided diagnosis (CAD) can aid in improving diagnostic level; however, the main problem currently faced by CAD is that it cannot obtain sufficient labeled samples. To solve this problem, in this study, we adopt a generative adversarial network (GAN) approach and design a semisupervised learning algorithm, named G2C-CAD. METHODS: From the National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) dataset, we extracted four types of pulmonary nodule sign images closely related to lung cancer: noncentral calcification, lobulation, spiculation, and nonsolid/ground-glass opacity (GGO) texture, obtaining a total of 3,196 samples. In addition, we randomly selected 2,000 non-lesion image blocks as negative samples. We split the data 90% for training and 10% for testing. We designed a DCGAN generative adversarial framework and trained it on the small sample set. We also trained our designed CNN-based fuzzy Co-forest on the labeled small sample set and obtained a preliminary classifier. Then, coupled with the simulated unlabeled samples generated by the trained DCGAN, we conducted iterative semisupervised learning, which continually improved the classification performance of the fuzzy Co-forest until the termination condition was reached. Finally, we tested the fuzzy Co-forest and compared its performance with that of a C4.5 random decision forest and the G2C-CAD system without the fuzzy scheme, using ROC and confusion matrix for evaluation. RESULTS: Four different types of lung cancer-related signs were used in the classification experiment: noncentral calcification, lobulation, spiculation, and nonsolid/ground-glass opacity (GGO) texture, along with negative image samples. For these five classes, the G2C-CAD system obtained AUCs of 0.946, 0.912, 0.908, 0.887, and 0.939, respectively. The average accuracy of G2C-CAD exceeded that of the C4.5 random decision tree by 14%. G2C-CAD also obtained promising test results on the LISS signs dataset; its AUCs for GGO, lobulation, spiculation, pleural indentation, and negative image samples were 0.972, 0.964, 0.941, 0.967, and 0.953, respectively. CONCLUSION: The experimental results show that G2C-CAD is an appropriate method for addressing the problem of insufficient labeled samples in the medical image analysis field. Moreover, our system can be used to establish a training sample library for CAD classification diagnosis, which is important for future medical image analysis.
format Online
Article
Text
id pubmed-6500711
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-65007112019-05-22 A Novel Computer-Aided Diagnosis Scheme on Small Annotated Set: G2C-CAD Zheng, Guangyuan Han, Guanghui Soomro, Nouman Q. Ma, Linjuan Zhang, Fuquan Zhao, Yanfeng Zhao, Xinming Zhou, Chunwu Biomed Res Int Research Article PURPOSE: Computer-aided diagnosis (CAD) can aid in improving diagnostic level; however, the main problem currently faced by CAD is that it cannot obtain sufficient labeled samples. To solve this problem, in this study, we adopt a generative adversarial network (GAN) approach and design a semisupervised learning algorithm, named G2C-CAD. METHODS: From the National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) dataset, we extracted four types of pulmonary nodule sign images closely related to lung cancer: noncentral calcification, lobulation, spiculation, and nonsolid/ground-glass opacity (GGO) texture, obtaining a total of 3,196 samples. In addition, we randomly selected 2,000 non-lesion image blocks as negative samples. We split the data 90% for training and 10% for testing. We designed a DCGAN generative adversarial framework and trained it on the small sample set. We also trained our designed CNN-based fuzzy Co-forest on the labeled small sample set and obtained a preliminary classifier. Then, coupled with the simulated unlabeled samples generated by the trained DCGAN, we conducted iterative semisupervised learning, which continually improved the classification performance of the fuzzy Co-forest until the termination condition was reached. Finally, we tested the fuzzy Co-forest and compared its performance with that of a C4.5 random decision forest and the G2C-CAD system without the fuzzy scheme, using ROC and confusion matrix for evaluation. RESULTS: Four different types of lung cancer-related signs were used in the classification experiment: noncentral calcification, lobulation, spiculation, and nonsolid/ground-glass opacity (GGO) texture, along with negative image samples. For these five classes, the G2C-CAD system obtained AUCs of 0.946, 0.912, 0.908, 0.887, and 0.939, respectively. The average accuracy of G2C-CAD exceeded that of the C4.5 random decision tree by 14%. G2C-CAD also obtained promising test results on the LISS signs dataset; its AUCs for GGO, lobulation, spiculation, pleural indentation, and negative image samples were 0.972, 0.964, 0.941, 0.967, and 0.953, respectively. CONCLUSION: The experimental results show that G2C-CAD is an appropriate method for addressing the problem of insufficient labeled samples in the medical image analysis field. Moreover, our system can be used to establish a training sample library for CAD classification diagnosis, which is important for future medical image analysis. Hindawi 2019-04-15 /pmc/articles/PMC6500711/ /pubmed/31119180 http://dx.doi.org/10.1155/2019/6425963 Text en Copyright © 2019 Guangyuan Zheng et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Zheng, Guangyuan
Han, Guanghui
Soomro, Nouman Q.
Ma, Linjuan
Zhang, Fuquan
Zhao, Yanfeng
Zhao, Xinming
Zhou, Chunwu
A Novel Computer-Aided Diagnosis Scheme on Small Annotated Set: G2C-CAD
title A Novel Computer-Aided Diagnosis Scheme on Small Annotated Set: G2C-CAD
title_full A Novel Computer-Aided Diagnosis Scheme on Small Annotated Set: G2C-CAD
title_fullStr A Novel Computer-Aided Diagnosis Scheme on Small Annotated Set: G2C-CAD
title_full_unstemmed A Novel Computer-Aided Diagnosis Scheme on Small Annotated Set: G2C-CAD
title_short A Novel Computer-Aided Diagnosis Scheme on Small Annotated Set: G2C-CAD
title_sort novel computer-aided diagnosis scheme on small annotated set: g2c-cad
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6500711/
https://www.ncbi.nlm.nih.gov/pubmed/31119180
http://dx.doi.org/10.1155/2019/6425963
work_keys_str_mv AT zhengguangyuan anovelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT hanguanghui anovelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT soomronoumanq anovelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT malinjuan anovelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT zhangfuquan anovelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT zhaoyanfeng anovelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT zhaoxinming anovelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT zhouchunwu anovelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT zhengguangyuan novelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT hanguanghui novelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT soomronoumanq novelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT malinjuan novelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT zhangfuquan novelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT zhaoyanfeng novelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT zhaoxinming novelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad
AT zhouchunwu novelcomputeraideddiagnosisschemeonsmallannotatedsetg2ccad