Visibility Attribute Extraction and Anomaly Detection for Chinese Diagnostic Report Based on Cascade Networks
In the positron emission tomography/computed tomography (PET/CT) image diagnosis report, the semantic analysis of image findings section is an important part of the automatic diagnosis of medical image, which is an essential step for extracting keywords and abnormal sentences in the diagnostic repor...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8786226/ |
id |
doaj-1e53947bf9ec4d57af8a728054e7dbc5 |
---|---|
record_format |
Article |
spelling |
doaj-1e53947bf9ec4d57af8a728054e7dbc52021-04-05T17:29:01ZengIEEEIEEE Access2169-35362019-01-01711640211641210.1109/ACCESS.2019.29328428786226Visibility Attribute Extraction and Anomaly Detection for Chinese Diagnostic Report Based on Cascade NetworksJitong Zhang0Huiyan Jiang1https://orcid.org/0000-0003-1004-9986Liangliang Huang2Yu-Dong Yao3https://orcid.org/0000-0003-3868-0593Siqi Li4Northeastern University, Shenyang, ChinaSoftware College, Northeastern University, Shenyang, ChinaSoftware College, Northeastern University, Shenyang, ChinaDepartment of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USASoftware College, Northeastern University, Shenyang, ChinaIn the positron emission tomography/computed tomography (PET/CT) image diagnosis report, the semantic analysis of image findings section is an important part of the automatic diagnosis of medical image, which is an essential step for extracting keywords and abnormal sentences in the diagnostic report. To this end, this paper combines visibility attribute extraction network (VAE-Net) and bi-directional gated recurrent unit (BiGRU) into cascade networks to solve the tasks of attribute extraction and anomaly detection. First, a visibility attribute (VA) is defined to summary the vocabulary into 12 patterns based on the language characteristics in image findings. Second, a visibility attribute extraction network (VAE-Net) is developed to automatically extract VA from word embeddings, which is composed of residual convolutional neural network (residual CNN), BiGRU, and conditional random field (CRF). Finally, word embeddings and the corresponding VA are input into BiGRU and softmax to perform sentence-level anomaly detections. We evaluate the proposed method on a proprietary Chinese PET/CT diagnostic report dataset with an F1-score of 94.35% in the attribute extraction, an F1-score of 96.40% in sentence-level anomaly detection, and an F1-score of 96.77% in case-level anomaly detection. Besides, a publicity English national center for biotechnology information (NCBI) disease corpus dataset is used for externed validation with an F1-score of 95.81% in disease detection. The experimental results demonstrate the advantage of the proposed cascade networks as compared to other related methods.https://ieeexplore.ieee.org/document/8786226/Image diagnosis reportvisibility attributeanomaly detectionPET/CT imageCNNGRU |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jitong Zhang Huiyan Jiang Liangliang Huang Yu-Dong Yao Siqi Li |
spellingShingle |
Jitong Zhang Huiyan Jiang Liangliang Huang Yu-Dong Yao Siqi Li Visibility Attribute Extraction and Anomaly Detection for Chinese Diagnostic Report Based on Cascade Networks IEEE Access Image diagnosis report visibility attribute anomaly detection PET/CT image CNN GRU |
author_facet |
Jitong Zhang Huiyan Jiang Liangliang Huang Yu-Dong Yao Siqi Li |
author_sort |
Jitong Zhang |
title |
Visibility Attribute Extraction and Anomaly Detection for Chinese Diagnostic Report Based on Cascade Networks |
title_short |
Visibility Attribute Extraction and Anomaly Detection for Chinese Diagnostic Report Based on Cascade Networks |
title_full |
Visibility Attribute Extraction and Anomaly Detection for Chinese Diagnostic Report Based on Cascade Networks |
title_fullStr |
Visibility Attribute Extraction and Anomaly Detection for Chinese Diagnostic Report Based on Cascade Networks |
title_full_unstemmed |
Visibility Attribute Extraction and Anomaly Detection for Chinese Diagnostic Report Based on Cascade Networks |
title_sort |
visibility attribute extraction and anomaly detection for chinese diagnostic report based on cascade networks |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
In the positron emission tomography/computed tomography (PET/CT) image diagnosis report, the semantic analysis of image findings section is an important part of the automatic diagnosis of medical image, which is an essential step for extracting keywords and abnormal sentences in the diagnostic report. To this end, this paper combines visibility attribute extraction network (VAE-Net) and bi-directional gated recurrent unit (BiGRU) into cascade networks to solve the tasks of attribute extraction and anomaly detection. First, a visibility attribute (VA) is defined to summary the vocabulary into 12 patterns based on the language characteristics in image findings. Second, a visibility attribute extraction network (VAE-Net) is developed to automatically extract VA from word embeddings, which is composed of residual convolutional neural network (residual CNN), BiGRU, and conditional random field (CRF). Finally, word embeddings and the corresponding VA are input into BiGRU and softmax to perform sentence-level anomaly detections. We evaluate the proposed method on a proprietary Chinese PET/CT diagnostic report dataset with an F1-score of 94.35% in the attribute extraction, an F1-score of 96.40% in sentence-level anomaly detection, and an F1-score of 96.77% in case-level anomaly detection. Besides, a publicity English national center for biotechnology information (NCBI) disease corpus dataset is used for externed validation with an F1-score of 95.81% in disease detection. The experimental results demonstrate the advantage of the proposed cascade networks as compared to other related methods. |
topic |
Image diagnosis report visibility attribute anomaly detection PET/CT image CNN GRU |
url |
https://ieeexplore.ieee.org/document/8786226/ |
work_keys_str_mv |
AT jitongzhang visibilityattributeextractionandanomalydetectionforchinesediagnosticreportbasedoncascadenetworks AT huiyanjiang visibilityattributeextractionandanomalydetectionforchinesediagnosticreportbasedoncascadenetworks AT lianglianghuang visibilityattributeextractionandanomalydetectionforchinesediagnosticreportbasedoncascadenetworks AT yudongyao visibilityattributeextractionandanomalydetectionforchinesediagnosticreportbasedoncascadenetworks AT siqili visibilityattributeextractionandanomalydetectionforchinesediagnosticreportbasedoncascadenetworks |
_version_ |
1721539518025170944 |