Leveraging Multi-Annotator Label Uncertainties as Privileged Information for Acute Respiratory Distress Syndrome Detection in Chest X-ray Images
Acute Respiratory Distress Syndrome (ARDS) is a life-threatening lung injury for which early diagnosis and evidence-based treatment can improve patient outcomes. Chest X-rays (CXRs) play a crucial role in the identification of ARDS; however, their interpretation can be difficult due to non-specific...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/11/2/133 |
| _version_ | 1827344110861680640 |
|---|---|
| author | Zijun Gao Emily Wittrup Kayvan Najarian |
| author_facet | Zijun Gao Emily Wittrup Kayvan Najarian |
| author_sort | Zijun Gao |
| collection | DOAJ |
| description | Acute Respiratory Distress Syndrome (ARDS) is a life-threatening lung injury for which early diagnosis and evidence-based treatment can improve patient outcomes. Chest X-rays (CXRs) play a crucial role in the identification of ARDS; however, their interpretation can be difficult due to non-specific radiological features, uncertainty in disease staging, and inter-rater variability among clinical experts, thus leading to prominent label noise issues. To address these challenges, this study proposes a novel approach that leverages label uncertainty from multiple annotators to enhance ARDS detection in CXR images. Label uncertainty information is encoded and supplied to the model as privileged information, a form of information exclusively available during the training stage and not during inference. By incorporating the Transfer and Marginalized (TRAM) network and effective knowledge transfer mechanisms, the detection model achieved a mean testing AUROC of 0.850, an AUPRC of 0.868, and an F1 score of 0.797. After removing equivocal testing cases, the model attained an AUROC of 0.973, an AUPRC of 0.971, and an F1 score of 0.921. As a new approach to addressing label noise in medical image analysis, the proposed model has shown superiority compared to the original TRAM, Confusion Estimation, and mean-aggregated label training. The overall findings highlight the effectiveness of the proposed methods in addressing label noise in CXRs for ARDS detection, with potential for use in other medical imaging domains that encounter similar challenges. |
| first_indexed | 2024-03-07T22:41:16Z |
| format | Article |
| id | doaj.art-0c8a5129f6164cffbd16fe7351f2aeb4 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-07T22:41:16Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-0c8a5129f6164cffbd16fe7351f2aeb42024-02-23T15:07:54ZengMDPI AGBioengineering2306-53542024-01-0111213310.3390/bioengineering11020133Leveraging Multi-Annotator Label Uncertainties as Privileged Information for Acute Respiratory Distress Syndrome Detection in Chest X-ray ImagesZijun Gao0Emily Wittrup1Kayvan Najarian2Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USADepartment of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USADepartment of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USAAcute Respiratory Distress Syndrome (ARDS) is a life-threatening lung injury for which early diagnosis and evidence-based treatment can improve patient outcomes. Chest X-rays (CXRs) play a crucial role in the identification of ARDS; however, their interpretation can be difficult due to non-specific radiological features, uncertainty in disease staging, and inter-rater variability among clinical experts, thus leading to prominent label noise issues. To address these challenges, this study proposes a novel approach that leverages label uncertainty from multiple annotators to enhance ARDS detection in CXR images. Label uncertainty information is encoded and supplied to the model as privileged information, a form of information exclusively available during the training stage and not during inference. By incorporating the Transfer and Marginalized (TRAM) network and effective knowledge transfer mechanisms, the detection model achieved a mean testing AUROC of 0.850, an AUPRC of 0.868, and an F1 score of 0.797. After removing equivocal testing cases, the model attained an AUROC of 0.973, an AUPRC of 0.971, and an F1 score of 0.921. As a new approach to addressing label noise in medical image analysis, the proposed model has shown superiority compared to the original TRAM, Confusion Estimation, and mean-aggregated label training. The overall findings highlight the effectiveness of the proposed methods in addressing label noise in CXRs for ARDS detection, with potential for use in other medical imaging domains that encounter similar challenges.https://www.mdpi.com/2306-5354/11/2/133acute respiratory distress syndromechest X-raylearning using privileged informationlabel uncertaintylabel noise |
| spellingShingle | Zijun Gao Emily Wittrup Kayvan Najarian Leveraging Multi-Annotator Label Uncertainties as Privileged Information for Acute Respiratory Distress Syndrome Detection in Chest X-ray Images Bioengineering acute respiratory distress syndrome chest X-ray learning using privileged information label uncertainty label noise |
| title | Leveraging Multi-Annotator Label Uncertainties as Privileged Information for Acute Respiratory Distress Syndrome Detection in Chest X-ray Images |
| title_full | Leveraging Multi-Annotator Label Uncertainties as Privileged Information for Acute Respiratory Distress Syndrome Detection in Chest X-ray Images |
| title_fullStr | Leveraging Multi-Annotator Label Uncertainties as Privileged Information for Acute Respiratory Distress Syndrome Detection in Chest X-ray Images |
| title_full_unstemmed | Leveraging Multi-Annotator Label Uncertainties as Privileged Information for Acute Respiratory Distress Syndrome Detection in Chest X-ray Images |
| title_short | Leveraging Multi-Annotator Label Uncertainties as Privileged Information for Acute Respiratory Distress Syndrome Detection in Chest X-ray Images |
| title_sort | leveraging multi annotator label uncertainties as privileged information for acute respiratory distress syndrome detection in chest x ray images |
| topic | acute respiratory distress syndrome chest X-ray learning using privileged information label uncertainty label noise |
| url | https://www.mdpi.com/2306-5354/11/2/133 |
| work_keys_str_mv | AT zijungao leveragingmultiannotatorlabeluncertaintiesasprivilegedinformationforacuterespiratorydistresssyndromedetectioninchestxrayimages AT emilywittrup leveragingmultiannotatorlabeluncertaintiesasprivilegedinformationforacuterespiratorydistresssyndromedetectioninchestxrayimages AT kayvannajarian leveragingmultiannotatorlabeluncertaintiesasprivilegedinformationforacuterespiratorydistresssyndromedetectioninchestxrayimages |