Multi-Task Learning for Lung Disease Classification and Report Generation via Prior Graph Structure and Contrastive Learning
Analyzing medical records takes a large amount of time and resources for medical workers. Therefore, the advancement of report generation technology is critical for saving doctors’ time while producing reports. Some diseases frequently exhibit co-occurrence interactions in the context of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10273709/ |
| _version_ | 1797660772555292672 |
|---|---|
| author | Kaifeng Guo Shihao Zheng Ri Huang Rongjian Gao |
| author_facet | Kaifeng Guo Shihao Zheng Ri Huang Rongjian Gao |
| author_sort | Kaifeng Guo |
| collection | DOAJ |
| description | Analyzing medical records takes a large amount of time and resources for medical workers. Therefore, the advancement of report generation technology is critical for saving doctors’ time while producing reports. Some diseases frequently exhibit co-occurrence interactions in the context of medical picture categorization and report creation, which necessitate hu-man-designed and added representation. To further capture this latent information, we propose creating a disease co-occurrence matrix from the existing dataset and training a graph neural network on it. We use multi-label contrastive learning to assist the model in distinguishing the mutual links between different diseases. Meanwhile, we incorporate report retrieval module and decoder model to complete the report generation task, and the multi-task learning of disease classification and report generation can improve the generalization ability of the target task. Experimental results show that our pro-posed combined method and multi-task learning approach have shown significant improvement compared to previous research. |
| first_indexed | 2024-03-11T18:35:44Z |
| format | Article |
| id | doaj.art-4c9d4d8e4f1c4dddbd8a22681a5a2f34 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T18:35:44Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4c9d4d8e4f1c4dddbd8a22681a5a2f342023-10-12T23:01:10ZengIEEEIEEE Access2169-35362023-01-011111088811089810.1109/ACCESS.2023.332242510273709Multi-Task Learning for Lung Disease Classification and Report Generation via Prior Graph Structure and Contrastive LearningKaifeng Guo0https://orcid.org/0009-0004-2484-1004Shihao Zheng1Ri Huang2Rongjian Gao3Maynooth International Engineering College, Fuzhou University, Fujian, Fuzhou, ChinaMaynooth International Engineering College, Fuzhou University, Fujian, Fuzhou, ChinaMaynooth International Engineering College, Fuzhou University, Fujian, Fuzhou, ChinaMaynooth International Engineering College, Fuzhou University, Fujian, Fuzhou, ChinaAnalyzing medical records takes a large amount of time and resources for medical workers. Therefore, the advancement of report generation technology is critical for saving doctors’ time while producing reports. Some diseases frequently exhibit co-occurrence interactions in the context of medical picture categorization and report creation, which necessitate hu-man-designed and added representation. To further capture this latent information, we propose creating a disease co-occurrence matrix from the existing dataset and training a graph neural network on it. We use multi-label contrastive learning to assist the model in distinguishing the mutual links between different diseases. Meanwhile, we incorporate report retrieval module and decoder model to complete the report generation task, and the multi-task learning of disease classification and report generation can improve the generalization ability of the target task. Experimental results show that our pro-posed combined method and multi-task learning approach have shown significant improvement compared to previous research.https://ieeexplore.ieee.org/document/10273709/Image classificationmulti-task learningcontrastive learninggraph structuredeep learning |
| spellingShingle | Kaifeng Guo Shihao Zheng Ri Huang Rongjian Gao Multi-Task Learning for Lung Disease Classification and Report Generation via Prior Graph Structure and Contrastive Learning IEEE Access Image classification multi-task learning contrastive learning graph structure deep learning |
| title | Multi-Task Learning for Lung Disease Classification and Report Generation via Prior Graph Structure and Contrastive Learning |
| title_full | Multi-Task Learning for Lung Disease Classification and Report Generation via Prior Graph Structure and Contrastive Learning |
| title_fullStr | Multi-Task Learning for Lung Disease Classification and Report Generation via Prior Graph Structure and Contrastive Learning |
| title_full_unstemmed | Multi-Task Learning for Lung Disease Classification and Report Generation via Prior Graph Structure and Contrastive Learning |
| title_short | Multi-Task Learning for Lung Disease Classification and Report Generation via Prior Graph Structure and Contrastive Learning |
| title_sort | multi task learning for lung disease classification and report generation via prior graph structure and contrastive learning |
| topic | Image classification multi-task learning contrastive learning graph structure deep learning |
| url | https://ieeexplore.ieee.org/document/10273709/ |
| work_keys_str_mv | AT kaifengguo multitasklearningforlungdiseaseclassificationandreportgenerationviapriorgraphstructureandcontrastivelearning AT shihaozheng multitasklearningforlungdiseaseclassificationandreportgenerationviapriorgraphstructureandcontrastivelearning AT rihuang multitasklearningforlungdiseaseclassificationandreportgenerationviapriorgraphstructureandcontrastivelearning AT rongjiangao multitasklearningforlungdiseaseclassificationandreportgenerationviapriorgraphstructureandcontrastivelearning |