Quality Control for Radiology Report Generation Models via Auxiliary Auditing Components
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910548793229312 |
|---|---|
| author | Warr, Hermione Ibrahim, Yasin McGowan, Daniel R. Kamnitsas, Konstantinos |
| author_facet | Warr, Hermione Ibrahim, Yasin McGowan, Daniel R. Kamnitsas, Konstantinos |
| contents | Automation of medical image interpretation could alleviate bottlenecks in diagnostic workflows, and has become of particular interest in recent years due to advancements in natural language processing. Great strides have been made towards automated radiology report generation via AI, yet ensuring clinical accuracy in generated reports is a significant challenge, hindering deployment of such methods in clinical practice. In this work we propose a quality control framework for assessing the reliability of AI-generated radiology reports with respect to semantics of diagnostic importance using modular auxiliary auditing components (AC). Evaluating our pipeline on the MIMIC-CXR dataset, our findings show that incorporating ACs in the form of disease-classifiers can enable auditing that identifies more reliable reports, resulting in higher F1 scores compared to unfiltered generated reports. Additionally, leveraging the confidence of the AC labels further improves the audit's effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21638 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quality Control for Radiology Report Generation Models via Auxiliary Auditing Components Warr, Hermione Ibrahim, Yasin McGowan, Daniel R. Kamnitsas, Konstantinos Artificial Intelligence Computer Vision and Pattern Recognition Automation of medical image interpretation could alleviate bottlenecks in diagnostic workflows, and has become of particular interest in recent years due to advancements in natural language processing. Great strides have been made towards automated radiology report generation via AI, yet ensuring clinical accuracy in generated reports is a significant challenge, hindering deployment of such methods in clinical practice. In this work we propose a quality control framework for assessing the reliability of AI-generated radiology reports with respect to semantics of diagnostic importance using modular auxiliary auditing components (AC). Evaluating our pipeline on the MIMIC-CXR dataset, our findings show that incorporating ACs in the form of disease-classifiers can enable auditing that identifies more reliable reports, resulting in higher F1 scores compared to unfiltered generated reports. Additionally, leveraging the confidence of the AC labels further improves the audit's effectiveness. |
| title | Quality Control for Radiology Report Generation Models via Auxiliary Auditing Components |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.21638 |