Disease probability-enhanced follow-up chest X-ray radiology report summary generation
Abstract A chest X-ray radiology report describes abnormal findings not only from X-ray obtained at a given examination, but also findings on disease progression or change in device placement with reference to the X-ray from previous examination. Majority of the efforts on automatic generation of ra...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-12684-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849235408004579328 |
|---|---|
| author | Zhichuan Wang Qiao Deng Tiffany Y. So Wan Hang Chiu Kinhei Lee Edward S. Hui |
| author_facet | Zhichuan Wang Qiao Deng Tiffany Y. So Wan Hang Chiu Kinhei Lee Edward S. Hui |
| author_sort | Zhichuan Wang |
| collection | DOAJ |
| description | Abstract A chest X-ray radiology report describes abnormal findings not only from X-ray obtained at a given examination, but also findings on disease progression or change in device placement with reference to the X-ray from previous examination. Majority of the efforts on automatic generation of radiology report pertain to reporting the former, but not the latter, type of findings. To the best of the authors’ knowledge, there is only one work dedicated to generating summary of the latter findings, i.e., follow-up radiology report summary. In this study, we propose a transformer-based framework to tackle this task. Motivated by our observations on the significance of medical lexicon on the fidelity of report summary generation, we introduce two mechanisms to bestow clinical insight to our model, namely disease probability soft guidance and masked entity modeling loss. The former mechanism employs a pretrained abnormality classifier to guide the presence level of specific abnormalities, while the latter directs the model’s attention toward medical lexicon. Extensive experiments were conducted to demonstrate that the performance of our model exceeded the state-of-the-art. |
| format | Article |
| id | doaj-art-d1db4f32f63c4b0aabc78aaa07fecf8b |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-d1db4f32f63c4b0aabc78aaa07fecf8b2025-08-20T04:02:46ZengNature PortfolioScientific Reports2045-23222025-07-0115111210.1038/s41598-025-12684-2Disease probability-enhanced follow-up chest X-ray radiology report summary generationZhichuan Wang0Qiao Deng1Tiffany Y. So2Wan Hang Chiu3Kinhei Lee4Edward S. Hui5Department of Imaging and Interventional Radiology, The Chinese University of Hong KongDepartment of Imaging and Interventional Radiology, The Chinese University of Hong KongDepartment of Imaging and Interventional Radiology, The Chinese University of Hong KongHospital AuthorityDepartment of Imaging and Interventional Radiology, The Chinese University of Hong KongDepartment of Imaging and Interventional Radiology, The Chinese University of Hong KongAbstract A chest X-ray radiology report describes abnormal findings not only from X-ray obtained at a given examination, but also findings on disease progression or change in device placement with reference to the X-ray from previous examination. Majority of the efforts on automatic generation of radiology report pertain to reporting the former, but not the latter, type of findings. To the best of the authors’ knowledge, there is only one work dedicated to generating summary of the latter findings, i.e., follow-up radiology report summary. In this study, we propose a transformer-based framework to tackle this task. Motivated by our observations on the significance of medical lexicon on the fidelity of report summary generation, we introduce two mechanisms to bestow clinical insight to our model, namely disease probability soft guidance and masked entity modeling loss. The former mechanism employs a pretrained abnormality classifier to guide the presence level of specific abnormalities, while the latter directs the model’s attention toward medical lexicon. Extensive experiments were conducted to demonstrate that the performance of our model exceeded the state-of-the-art.https://doi.org/10.1038/s41598-025-12684-2 |
| spellingShingle | Zhichuan Wang Qiao Deng Tiffany Y. So Wan Hang Chiu Kinhei Lee Edward S. Hui Disease probability-enhanced follow-up chest X-ray radiology report summary generation Scientific Reports |
| title | Disease probability-enhanced follow-up chest X-ray radiology report summary generation |
| title_full | Disease probability-enhanced follow-up chest X-ray radiology report summary generation |
| title_fullStr | Disease probability-enhanced follow-up chest X-ray radiology report summary generation |
| title_full_unstemmed | Disease probability-enhanced follow-up chest X-ray radiology report summary generation |
| title_short | Disease probability-enhanced follow-up chest X-ray radiology report summary generation |
| title_sort | disease probability enhanced follow up chest x ray radiology report summary generation |
| url | https://doi.org/10.1038/s41598-025-12684-2 |
| work_keys_str_mv | AT zhichuanwang diseaseprobabilityenhancedfollowupchestxrayradiologyreportsummarygeneration AT qiaodeng diseaseprobabilityenhancedfollowupchestxrayradiologyreportsummarygeneration AT tiffanyyso diseaseprobabilityenhancedfollowupchestxrayradiologyreportsummarygeneration AT wanhangchiu diseaseprobabilityenhancedfollowupchestxrayradiologyreportsummarygeneration AT kinheilee diseaseprobabilityenhancedfollowupchestxrayradiologyreportsummarygeneration AT edwardshui diseaseprobabilityenhancedfollowupchestxrayradiologyreportsummarygeneration |