Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder
Abstract Objective In this paper, we aim to investigate the effect of computer-aided triage system, which is implemented for the health checkup of lung lesions involving tens of thousands of chest X-rays (CXRs) that are required for diagnosis. Therefore, high accuracy of diagnosis by an automated sy...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-05-01
|
| Series: | BioMedical Engineering OnLine |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12938-018-0496-2 |
| _version_ | 1818966449036722176 |
|---|---|
| author | Changmiao Wang Ahmed Elazab Fucang Jia Jianhuang Wu Qingmao Hu |
| author_facet | Changmiao Wang Ahmed Elazab Fucang Jia Jianhuang Wu Qingmao Hu |
| author_sort | Changmiao Wang |
| collection | DOAJ |
| description | Abstract Objective In this paper, we aim to investigate the effect of computer-aided triage system, which is implemented for the health checkup of lung lesions involving tens of thousands of chest X-rays (CXRs) that are required for diagnosis. Therefore, high accuracy of diagnosis by an automated system can reduce the radiologist’s workload on scrutinizing the medical images. Method We present a deep learning model in order to efficiently detect abnormal levels or identify normal levels during mass chest screening so as to obtain the probability confidence of the CXRs. Moreover, a convolutional sparse denoising autoencoder is designed to compute the reconstruction error. We employ four publicly available radiology datasets pertaining to CXRs, analyze their reports, and utilize their images for mining the correct disease level of the CXRs that are to be submitted to a computer aided triaging system. Based on our approach, we vote for the final decision from multi-classifiers to determine which three levels of the images (i.e. normal, abnormal, and uncertain cases) that the CXRs fall into. Results We only deal with the grade diagnosis for physical examination and propose multiple new metric indices. Combining predictors for classification by using the area under a receiver operating characteristic curve, we observe that the final decision is related to the threshold from reconstruction error and the probability value. Our method achieves promising results in terms of precision of 98.7 and 94.3% based on the normal and abnormal cases, respectively. Conclusion The results achieved by the proposed framework show superiority in classifying the disease level with high accuracy. This can potentially save the radiologists time and effort, so as to allow them to focus on higher-level risk CXRs. |
| first_indexed | 2024-12-20T13:33:04Z |
| format | Article |
| id | doaj.art-0651ceb9a36e483794499d2f0818af09 |
| institution | Directory Open Access Journal |
| issn | 1475-925X |
| language | English |
| last_indexed | 2024-12-20T13:33:04Z |
| publishDate | 2018-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BioMedical Engineering OnLine |
| spelling | doaj.art-0651ceb9a36e483794499d2f0818af092022-12-21T19:39:02ZengBMCBioMedical Engineering OnLine1475-925X2018-05-0117111910.1186/s12938-018-0496-2Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoderChangmiao Wang0Ahmed Elazab1Fucang Jia2Jianhuang Wu3Qingmao Hu4Shenzhen Institutes of Advanced Technology, Chinese Academy of SciencesGuangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Health Science Center, Shenzhen UniversityShenzhen Institutes of Advanced Technology, Chinese Academy of SciencesShenzhen Institutes of Advanced Technology, Chinese Academy of SciencesShenzhen Institutes of Advanced Technology, Chinese Academy of SciencesAbstract Objective In this paper, we aim to investigate the effect of computer-aided triage system, which is implemented for the health checkup of lung lesions involving tens of thousands of chest X-rays (CXRs) that are required for diagnosis. Therefore, high accuracy of diagnosis by an automated system can reduce the radiologist’s workload on scrutinizing the medical images. Method We present a deep learning model in order to efficiently detect abnormal levels or identify normal levels during mass chest screening so as to obtain the probability confidence of the CXRs. Moreover, a convolutional sparse denoising autoencoder is designed to compute the reconstruction error. We employ four publicly available radiology datasets pertaining to CXRs, analyze their reports, and utilize their images for mining the correct disease level of the CXRs that are to be submitted to a computer aided triaging system. Based on our approach, we vote for the final decision from multi-classifiers to determine which three levels of the images (i.e. normal, abnormal, and uncertain cases) that the CXRs fall into. Results We only deal with the grade diagnosis for physical examination and propose multiple new metric indices. Combining predictors for classification by using the area under a receiver operating characteristic curve, we observe that the final decision is related to the threshold from reconstruction error and the probability value. Our method achieves promising results in terms of precision of 98.7 and 94.3% based on the normal and abnormal cases, respectively. Conclusion The results achieved by the proposed framework show superiority in classifying the disease level with high accuracy. This can potentially save the radiologists time and effort, so as to allow them to focus on higher-level risk CXRs.http://link.springer.com/article/10.1186/s12938-018-0496-2Chest screeningComputer aided diagnosisDeep learningAutoencoderReceiver operating characteristic |
| spellingShingle | Changmiao Wang Ahmed Elazab Fucang Jia Jianhuang Wu Qingmao Hu Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder BioMedical Engineering OnLine Chest screening Computer aided diagnosis Deep learning Autoencoder Receiver operating characteristic |
| title | Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder |
| title_full | Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder |
| title_fullStr | Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder |
| title_full_unstemmed | Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder |
| title_short | Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder |
| title_sort | automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder |
| topic | Chest screening Computer aided diagnosis Deep learning Autoencoder Receiver operating characteristic |
| url | http://link.springer.com/article/10.1186/s12938-018-0496-2 |
| work_keys_str_mv | AT changmiaowang automatedchestscreeningbasedonahybridmodeloftransferlearningandconvolutionalsparsedenoisingautoencoder AT ahmedelazab automatedchestscreeningbasedonahybridmodeloftransferlearningandconvolutionalsparsedenoisingautoencoder AT fucangjia automatedchestscreeningbasedonahybridmodeloftransferlearningandconvolutionalsparsedenoisingautoencoder AT jianhuangwu automatedchestscreeningbasedonahybridmodeloftransferlearningandconvolutionalsparsedenoisingautoencoder AT qingmaohu automatedchestscreeningbasedonahybridmodeloftransferlearningandconvolutionalsparsedenoisingautoencoder |