Detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligence
Abstract Background A deep learning computer artificial intelligence system is helpful for early identification of ground glass opacities (GGOs). Methods Images from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) database were used in AlexNet and GoogLeNet to d...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2019-01-01
|
Series: | BioMedical Engineering OnLine |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12938-019-0627-4 |
id |
doaj-b2c19cd0b8754cb2a95dd35a90ab6b93 |
---|---|
record_format |
Article |
spelling |
doaj-b2c19cd0b8754cb2a95dd35a90ab6b932020-11-25T01:57:16ZengBMCBioMedical Engineering OnLine1475-925X2019-01-0118111210.1186/s12938-019-0627-4Detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligenceWenjing Ye0Wen Gu1Xuejun Guo2Ping Yi3Yishuang Meng4Fengfeng Han5Lingwei Yu6Yi Chen7Guorui Zhang8Xueting Wang9Department of Respiratory Medicine, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversityDepartment of Respiratory Medicine, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversityDepartment of Respiratory Medicine, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversitySchool of Electronic Information and Electrical Engineering, Shanghai Jiao Tong UniversitySchool of Electronic Information and Electrical Engineering, Shanghai Jiao Tong UniversityDepartment of Respiratory Medicine, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversityDepartment of Radiology, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversityDepartment of Respiratory Medicine, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversityDepartment of Respiratory Medicine, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong UniversityShanghai Jiaotong University School of MedicineAbstract Background A deep learning computer artificial intelligence system is helpful for early identification of ground glass opacities (GGOs). Methods Images from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) database were used in AlexNet and GoogLeNet to detect pulmonary nodules, and 221 GGO images provided by Xinhua Hospital were used in ResNet50 for detecting GGOs. We used computed tomography image radial reorganization to create the input image of the three-dimensional features, and used the extracted features for deep learning, network training, testing, and analysis. Results In the final evaluation results, we found that the accuracy of identification of lung nodule could reach 88.0%, with an F-score of 0.891. In terms of performance and accuracy, our method was better than the existing solutions. The GGO nodule classification achieved the best F-score of 0.87805. We propose a preprocessing method of red, green, and blue (RGB) superposition in the region of interest to effectively increase the differentiation between nodules and normal tissues, and that is the innovation of our research. Conclusions The method of deep learning proposed in this study is more sensitive than other systems in recent years, and the average false positive is lower than that of others.http://link.springer.com/article/10.1186/s12938-019-0627-4Pulmonary noduleGround-glass opacityDeep learningArtificial intelligenceComputer-aided diagnosis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wenjing Ye Wen Gu Xuejun Guo Ping Yi Yishuang Meng Fengfeng Han Lingwei Yu Yi Chen Guorui Zhang Xueting Wang |
spellingShingle |
Wenjing Ye Wen Gu Xuejun Guo Ping Yi Yishuang Meng Fengfeng Han Lingwei Yu Yi Chen Guorui Zhang Xueting Wang Detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligence BioMedical Engineering OnLine Pulmonary nodule Ground-glass opacity Deep learning Artificial intelligence Computer-aided diagnosis |
author_facet |
Wenjing Ye Wen Gu Xuejun Guo Ping Yi Yishuang Meng Fengfeng Han Lingwei Yu Yi Chen Guorui Zhang Xueting Wang |
author_sort |
Wenjing Ye |
title |
Detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligence |
title_short |
Detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligence |
title_full |
Detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligence |
title_fullStr |
Detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligence |
title_full_unstemmed |
Detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligence |
title_sort |
detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligence |
publisher |
BMC |
series |
BioMedical Engineering OnLine |
issn |
1475-925X |
publishDate |
2019-01-01 |
description |
Abstract Background A deep learning computer artificial intelligence system is helpful for early identification of ground glass opacities (GGOs). Methods Images from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) database were used in AlexNet and GoogLeNet to detect pulmonary nodules, and 221 GGO images provided by Xinhua Hospital were used in ResNet50 for detecting GGOs. We used computed tomography image radial reorganization to create the input image of the three-dimensional features, and used the extracted features for deep learning, network training, testing, and analysis. Results In the final evaluation results, we found that the accuracy of identification of lung nodule could reach 88.0%, with an F-score of 0.891. In terms of performance and accuracy, our method was better than the existing solutions. The GGO nodule classification achieved the best F-score of 0.87805. We propose a preprocessing method of red, green, and blue (RGB) superposition in the region of interest to effectively increase the differentiation between nodules and normal tissues, and that is the innovation of our research. Conclusions The method of deep learning proposed in this study is more sensitive than other systems in recent years, and the average false positive is lower than that of others. |
topic |
Pulmonary nodule Ground-glass opacity Deep learning Artificial intelligence Computer-aided diagnosis |
url |
http://link.springer.com/article/10.1186/s12938-019-0627-4 |
work_keys_str_mv |
AT wenjingye detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence AT wengu detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence AT xuejunguo detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence AT pingyi detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence AT yishuangmeng detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence AT fengfenghan detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence AT lingweiyu detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence AT yichen detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence AT guoruizhang detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence AT xuetingwang detectionofpulmonarygroundglassopacitybasedondeeplearningcomputerartificialintelligence |
_version_ |
1724975211697143808 |