Please use this identifier to cite or link to this item:
https://doi.org/10.1148/ryai.2021200190
DC Field | Value | |
---|---|---|
dc.title | Deep Learning Systems for Pneumothorax Detection on Chest Radiographs: A Multicenter External Validation Study | |
dc.contributor.author | Thian, Yee Liang | |
dc.contributor.author | Ng, Dianwen | |
dc.contributor.author | Hallinan, James Thomas Patrick Decourcy | |
dc.contributor.author | Jagmohan, Pooja | |
dc.contributor.author | Sia, Soon Yiew | |
dc.contributor.author | Tan, Cher Heng | |
dc.contributor.author | Ting, Yong Han | |
dc.contributor.author | Kei, Pin Lin | |
dc.contributor.author | Pulickal, Geoiphy George | |
dc.contributor.author | Tiong, Vincent Tze Yang | |
dc.contributor.author | Quek, Swee Tian | |
dc.contributor.author | Feng, Mengling | |
dc.date.accessioned | 2023-06-01T05:05:08Z | |
dc.date.available | 2023-06-01T05:05:08Z | |
dc.date.issued | 2021-07 | |
dc.identifier.citation | Thian, Yee Liang, Ng, Dianwen, Hallinan, James Thomas Patrick Decourcy, Jagmohan, Pooja, Sia, Soon Yiew, Tan, Cher Heng, Ting, Yong Han, Kei, Pin Lin, Pulickal, Geoiphy George, Tiong, Vincent Tze Yang, Quek, Swee Tian, Feng, Mengling (2021-07). Deep Learning Systems for Pneumothorax Detection on Chest Radiographs: A Multicenter External Validation Study. Radiology: Artificial Intelligence 3 (4). ScholarBank@NUS Repository. https://doi.org/10.1148/ryai.2021200190 | |
dc.identifier.issn | 2638-6100 | |
dc.identifier.uri | https://scholarbank.nus.edu.sg/handle/10635/241517 | |
dc.description.abstract | Purpose: To assess the generalizability of a deep learning pneumothorax detection model on datasets from multiple external institutions and examine patient and acquisition factors that might influence performance. Materials and Methods: In this retrospective study, a deep learning model was trained for pneumothorax detection by merging two large open-source chest radiograph datasets: ChestX-ray14 and CheXpert. It was then tested on six external datasets from multiple independent institutions (labeled A–F) in a retrospective case-control design (data acquired between 2016 and 2019 from institutions A–E; institution F consisted of data from the MIMIC–CXR dataset). Performance on each dataset was evaluated by using area under the receiver operating characteristic curve (AUC) analysis, sensitivity, specificity, and positive and negative predictive values, with two radiologists in consensus being used as the reference standard. Patient and acquisition factors that influenced performance were analyzed. Results: The AUCs for pneumothorax detection for external institutions A–F were 0.91 (95% CI: 0.88, 0.94), 0.97 (95% CI: 0.94, 0.99), 0.91 (95% CI: 0.85, 0.97), 0.98 (95% CI: 0.96, 1.0), 0.97 (95% CI: 0.95, 0.99), and 0.92 (95% CI: 0.90, 0.95), respectively, compared with the internal test AUC of 0.93 (95% CI: 0.92, 0.93). The model had lower performance for small compared with large pneumothoraces (AUC, 0.88 [95% CI: 0.85, 0.91] vs AUC, 0.96 [95% CI: 0.95, 0.97]; P = .005). Model performance was not different when a chest tube was present or absent on the radiographs (AUC, 0.95 [95% CI: 0.92, 0.97] vs AUC, 0.94 [95% CI: 0.92, 0.05]; P > .99). Conclusion: A deep learning model trained with a large volume of data on the task of pneumothorax detection was able to generalize well to multiple external datasets with patient demographics and technical parameters independent of the training data. | |
dc.language.iso | en | |
dc.publisher | RADIOLOGICAL SOC NORTH AMERICA (RSNA) | |
dc.source | Elements | |
dc.subject | Computer Applications-Detection/Diagnosis | |
dc.subject | Thorax | |
dc.type | Article | |
dc.date.updated | 2023-05-31T14:37:00Z | |
dc.contributor.department | DIAGNOSTIC RADIOLOGY | |
dc.contributor.department | DUKE-NUS MEDICAL SCHOOL | |
dc.contributor.department | SAW SWEE HOCK SCHOOL OF PUBLIC HEALTH | |
dc.description.doi | 10.1148/ryai.2021200190 | |
dc.description.sourcetitle | Radiology: Artificial Intelligence | |
dc.description.volume | 3 | |
dc.description.issue | 4 | |
dc.published.state | Published | |
Appears in Collections: | Staff Publications Elements |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
Deep Learning Systems for Pneumothorax Detection on Chest Radiographs A Multicenter External Validation Study.pdf | Published version | 1.41 MB | Adobe PDF | OPEN | Published | View/Download |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.