A multi-label classification model for full slice brain computerised tomography image
Abstract Background Screening of the brain computerised tomography (CT) images is a primary method currently used for initial detection of patients with brain trauma or other conditions. In recent years, deep learning technique has shown remarkable advantages in the clinical practice. Researchers ha...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-11-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-020-3503-0 |
| _version_ | 1819160222793465856 |
|---|---|
| author | Jianqiang Li Guanghui Fu Yueda Chen Pengzhi Li Bo Liu Yan Pei Hui Feng |
| author_facet | Jianqiang Li Guanghui Fu Yueda Chen Pengzhi Li Bo Liu Yan Pei Hui Feng |
| author_sort | Jianqiang Li |
| collection | DOAJ |
| description | Abstract Background Screening of the brain computerised tomography (CT) images is a primary method currently used for initial detection of patients with brain trauma or other conditions. In recent years, deep learning technique has shown remarkable advantages in the clinical practice. Researchers have attempted to use deep learning methods to detect brain diseases from CT images. Methods often used to detect diseases choose images with visible lesions from full-slice brain CT scans, which need to be labelled by doctors. This is an inaccurate method because doctors detect brain disease from a full sequence scan of CT images and one patient may have multiple concurrent conditions in practice. The method cannot take into account the dependencies between the slices and the causal relationships among various brain diseases. Moreover, labelling images slice by slice spends much time and expense. Detecting multiple diseases from full slice brain CT images is, therefore, an important research subject with practical implications. Results In this paper, we propose a model called the slice dependencies learning model (SDLM). It learns image features from a series of variable length brain CT images and slice dependencies between different slices in a set of images to predict abnormalities. The model is necessary to only label the disease reflected in the full-slice brain scan. We use the CQ500 dataset to evaluate our proposed model, which contains 1194 full sets of CT scans from a total of 491 subjects. Each set of data from one subject contains scans with one to eight different slice thicknesses and various diseases that are captured in a range of 30 to 396 slices in a set. The evaluation results present that the precision is 67.57%, the recall is 61.04%, the F1 score is 0.6412, and the areas under the receiver operating characteristic curves (AUCs) is 0.8934. Conclusion The proposed model is a new architecture that uses a full-slice brain CT scan for multi-label classification, unlike the traditional methods which only classify the brain images at the slice level. It has great potential for application to multi-label detection problems, especially with regard to the brain CT images. |
| first_indexed | 2024-12-22T16:53:01Z |
| format | Article |
| id | doaj.art-4ab870329eb3463ca7fc1556d923af42 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-22T16:53:01Z |
| publishDate | 2020-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-4ab870329eb3463ca7fc1556d923af422022-12-21T18:19:32ZengBMCBMC Bioinformatics1471-21052020-11-0121S611810.1186/s12859-020-3503-0A multi-label classification model for full slice brain computerised tomography imageJianqiang Li0Guanghui Fu1Yueda Chen2Pengzhi Li3Bo Liu4Yan Pei5Hui Feng6School of Software Engineering, Beijing University of TechnologySchool of Software Engineering, Beijing University of TechnologyDepartment of Neurosurgery, Tianjin Huanhu HospitalSchool of Software Engineering, Beijing University of TechnologySchool of Software Engineering, Beijing University of TechnologyComputer Science Division, University of AizuSchool of Software Engineering, Beijing University of TechnologyAbstract Background Screening of the brain computerised tomography (CT) images is a primary method currently used for initial detection of patients with brain trauma or other conditions. In recent years, deep learning technique has shown remarkable advantages in the clinical practice. Researchers have attempted to use deep learning methods to detect brain diseases from CT images. Methods often used to detect diseases choose images with visible lesions from full-slice brain CT scans, which need to be labelled by doctors. This is an inaccurate method because doctors detect brain disease from a full sequence scan of CT images and one patient may have multiple concurrent conditions in practice. The method cannot take into account the dependencies between the slices and the causal relationships among various brain diseases. Moreover, labelling images slice by slice spends much time and expense. Detecting multiple diseases from full slice brain CT images is, therefore, an important research subject with practical implications. Results In this paper, we propose a model called the slice dependencies learning model (SDLM). It learns image features from a series of variable length brain CT images and slice dependencies between different slices in a set of images to predict abnormalities. The model is necessary to only label the disease reflected in the full-slice brain scan. We use the CQ500 dataset to evaluate our proposed model, which contains 1194 full sets of CT scans from a total of 491 subjects. Each set of data from one subject contains scans with one to eight different slice thicknesses and various diseases that are captured in a range of 30 to 396 slices in a set. The evaluation results present that the precision is 67.57%, the recall is 61.04%, the F1 score is 0.6412, and the areas under the receiver operating characteristic curves (AUCs) is 0.8934. Conclusion The proposed model is a new architecture that uses a full-slice brain CT scan for multi-label classification, unlike the traditional methods which only classify the brain images at the slice level. It has great potential for application to multi-label detection problems, especially with regard to the brain CT images.http://link.springer.com/article/10.1186/s12859-020-3503-0BioinformaticsBrain computerised tomographyMachine learningDeep learningComputer aided diagnosis |
| spellingShingle | Jianqiang Li Guanghui Fu Yueda Chen Pengzhi Li Bo Liu Yan Pei Hui Feng A multi-label classification model for full slice brain computerised tomography image BMC Bioinformatics Bioinformatics Brain computerised tomography Machine learning Deep learning Computer aided diagnosis |
| title | A multi-label classification model for full slice brain computerised tomography image |
| title_full | A multi-label classification model for full slice brain computerised tomography image |
| title_fullStr | A multi-label classification model for full slice brain computerised tomography image |
| title_full_unstemmed | A multi-label classification model for full slice brain computerised tomography image |
| title_short | A multi-label classification model for full slice brain computerised tomography image |
| title_sort | multi label classification model for full slice brain computerised tomography image |
| topic | Bioinformatics Brain computerised tomography Machine learning Deep learning Computer aided diagnosis |
| url | http://link.springer.com/article/10.1186/s12859-020-3503-0 |
| work_keys_str_mv | AT jianqiangli amultilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT guanghuifu amultilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT yuedachen amultilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT pengzhili amultilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT boliu amultilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT yanpei amultilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT huifeng amultilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT jianqiangli multilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT guanghuifu multilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT yuedachen multilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT pengzhili multilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT boliu multilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT yanpei multilabelclassificationmodelforfullslicebraincomputerisedtomographyimage AT huifeng multilabelclassificationmodelforfullslicebraincomputerisedtomographyimage |