Identifying stroke diagnosis-related features from medical imaging reports to improve clinical decision-making support
Abstract Background Medical imaging reports play an important role in communication of diagnostic information between radiologists and clinicians. Head magnetic resonance imaging (MRI) reports can provide evidence that is widely used in the diagnosis and treatment of ischaemic stroke. The high-signa...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-10-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-022-02012-3 |
| _version_ | 1828217870686879744 |
|---|---|
| author | Xiaowei Xu Lu Qin Lingling Ding Chunjuan Wang Meng Wang Zixiao Li Jiao Li |
| author_facet | Xiaowei Xu Lu Qin Lingling Ding Chunjuan Wang Meng Wang Zixiao Li Jiao Li |
| author_sort | Xiaowei Xu |
| collection | DOAJ |
| description | Abstract Background Medical imaging reports play an important role in communication of diagnostic information between radiologists and clinicians. Head magnetic resonance imaging (MRI) reports can provide evidence that is widely used in the diagnosis and treatment of ischaemic stroke. The high-signal regions of diffusion-weighted imaging (DWI) images in MRI reports are key evidence. Correctly identifying high-signal regions of DWI images is helpful for the treatment of ischaemic stroke patients. Since most of the multiple signals recorded in head MRI reports appear in the same part, it is challenging to identify high-signal regions of DWI images from MRI reports. Methods We developed a deep learning model to automatically identify high-signal regions of DWI images from head MRI reports. We proposed a fine-grained entity typing model based on machine reading comprehension that transformed the traditional two-step fine-grained entity typing task into a question-answering task. Results To prove the validity of the model proposed, we compared it with the fine-grained entity typing model, of which the F1 measure was 5.9% and 3.2% higher than the F1 measures of the models based on LSTM and BERT, respectively. Conclusion In this study, we explore the automatic identification of high-signal regions of DWI images from the description part of a head MRI report. We transformed the identification of high-signal regions of DWI images to an FET task and proposed an MRC-FET model. Compared with the traditional two-step FET method, the model we proposed not only simplifies the task but also has better performance. The comparable result shows that the work in this study can contribute to improving the clinical decision support system. |
| first_indexed | 2024-04-12T15:54:46Z |
| format | Article |
| id | doaj.art-161afaf2471940e3bff387a3a29c8da1 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-04-12T15:54:46Z |
| publishDate | 2022-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-161afaf2471940e3bff387a3a29c8da12022-12-22T03:26:24ZengBMCBMC Medical Informatics and Decision Making1472-69472022-10-012211910.1186/s12911-022-02012-3Identifying stroke diagnosis-related features from medical imaging reports to improve clinical decision-making supportXiaowei Xu0Lu Qin1Lingling Ding2Chunjuan Wang3Meng Wang4Zixiao Li5Jiao Li6Institute of Medical Information, Chinese Academy of Medical Sciences, Peking Union Medical CollegeInstitute of Medical Information, Chinese Academy of Medical Sciences, Peking Union Medical CollegeBeijing Tiantan Hospital, Capital Medical UniversityBeijing Tiantan Hospital, Capital Medical UniversityBeijing Tiantan Hospital, Capital Medical UniversityBeijing Tiantan Hospital, Capital Medical UniversityInstitute of Medical Information, Chinese Academy of Medical Sciences, Peking Union Medical CollegeAbstract Background Medical imaging reports play an important role in communication of diagnostic information between radiologists and clinicians. Head magnetic resonance imaging (MRI) reports can provide evidence that is widely used in the diagnosis and treatment of ischaemic stroke. The high-signal regions of diffusion-weighted imaging (DWI) images in MRI reports are key evidence. Correctly identifying high-signal regions of DWI images is helpful for the treatment of ischaemic stroke patients. Since most of the multiple signals recorded in head MRI reports appear in the same part, it is challenging to identify high-signal regions of DWI images from MRI reports. Methods We developed a deep learning model to automatically identify high-signal regions of DWI images from head MRI reports. We proposed a fine-grained entity typing model based on machine reading comprehension that transformed the traditional two-step fine-grained entity typing task into a question-answering task. Results To prove the validity of the model proposed, we compared it with the fine-grained entity typing model, of which the F1 measure was 5.9% and 3.2% higher than the F1 measures of the models based on LSTM and BERT, respectively. Conclusion In this study, we explore the automatic identification of high-signal regions of DWI images from the description part of a head MRI report. We transformed the identification of high-signal regions of DWI images to an FET task and proposed an MRC-FET model. Compared with the traditional two-step FET method, the model we proposed not only simplifies the task but also has better performance. The comparable result shows that the work in this study can contribute to improving the clinical decision support system.https://doi.org/10.1186/s12911-022-02012-3Ischaemic strokeHigh-Signal intensity regionsDWIMRI reportsFine-grained entity typing |
| spellingShingle | Xiaowei Xu Lu Qin Lingling Ding Chunjuan Wang Meng Wang Zixiao Li Jiao Li Identifying stroke diagnosis-related features from medical imaging reports to improve clinical decision-making support BMC Medical Informatics and Decision Making Ischaemic stroke High-Signal intensity regions DWI MRI reports Fine-grained entity typing |
| title | Identifying stroke diagnosis-related features from medical imaging reports to improve clinical decision-making support |
| title_full | Identifying stroke diagnosis-related features from medical imaging reports to improve clinical decision-making support |
| title_fullStr | Identifying stroke diagnosis-related features from medical imaging reports to improve clinical decision-making support |
| title_full_unstemmed | Identifying stroke diagnosis-related features from medical imaging reports to improve clinical decision-making support |
| title_short | Identifying stroke diagnosis-related features from medical imaging reports to improve clinical decision-making support |
| title_sort | identifying stroke diagnosis related features from medical imaging reports to improve clinical decision making support |
| topic | Ischaemic stroke High-Signal intensity regions DWI MRI reports Fine-grained entity typing |
| url | https://doi.org/10.1186/s12911-022-02012-3 |
| work_keys_str_mv | AT xiaoweixu identifyingstrokediagnosisrelatedfeaturesfrommedicalimagingreportstoimproveclinicaldecisionmakingsupport AT luqin identifyingstrokediagnosisrelatedfeaturesfrommedicalimagingreportstoimproveclinicaldecisionmakingsupport AT linglingding identifyingstrokediagnosisrelatedfeaturesfrommedicalimagingreportstoimproveclinicaldecisionmakingsupport AT chunjuanwang identifyingstrokediagnosisrelatedfeaturesfrommedicalimagingreportstoimproveclinicaldecisionmakingsupport AT mengwang identifyingstrokediagnosisrelatedfeaturesfrommedicalimagingreportstoimproveclinicaldecisionmakingsupport AT zixiaoli identifyingstrokediagnosisrelatedfeaturesfrommedicalimagingreportstoimproveclinicaldecisionmakingsupport AT jiaoli identifyingstrokediagnosisrelatedfeaturesfrommedicalimagingreportstoimproveclinicaldecisionmakingsupport |