Dataset Information

Do comprehensive deep learning algorithms suffer from hidden stratification? A retrospective study on pneumothorax detection in chest radiography.

ABSTRACT:

Objectives

To evaluate the ability of a commercially available comprehensive chest radiography deep convolutional neural network (DCNN) to detect simple and tension pneumothorax, as stratified by the following subgroups: the presence of an intercostal drain; rib, clavicular, scapular or humeral fractures or rib resections; subcutaneous emphysema and erect versus non-erect positioning. The hypothesis was that performance would not differ significantly in each of these subgroups when compared with the overall test dataset.

Design

A retrospective case-control study was undertaken.

Setting

Community radiology clinics and hospitals in Australia and the USA.

Participants

A test dataset of 2557 chest radiography studies was ground-truthed by three subspecialty thoracic radiologists for the presence of simple or tension pneumothorax as well as each subgroup other than positioning. Radiograph positioning was derived from radiographer annotations on the images.

Outcome measures

DCNN performance for detecting simple and tension pneumothorax was evaluated over the entire test set, as well as within each subgroup, using the area under the receiver operating characteristic curve (AUC). A difference in AUC of more than 0.05 was considered clinically significant.

Results

When compared with the overall test set, performance of the DCNN for detecting simple and tension pneumothorax was statistically non-inferior in all subgroups. The DCNN had an AUC of 0.981 (0.976-0.986) for detecting simple pneumothorax and 0.997 (0.995-0.999) for detecting tension pneumothorax.

Conclusions

Hidden stratification has significant implications for potential failures of deep learning when applied in clinical practice. This study demonstrated that a comprehensively trained DCNN can be resilient to hidden stratification in several clinically meaningful subgroups in detecting pneumothorax.

SUBMITTER: Seah J

PROVIDER: S-EPMC8655590 | biostudies-literature | 2021 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Do comprehensive deep learning algorithms suffer from hidden stratification? A retrospective study on pneumothorax detection in chest radiography.

Seah Jarrel J Tang Cyril C Buchlak Quinlan D QD Milne Michael Robert MR Holt Xavier X Ahmad Hassan H Lambert John J Esmaili Nazanin N Oakden-Rayner Luke L Brotchie Peter P Jones Catherine M CM

BMJ open 20211207 12

<h4>Objectives</h4>To evaluate the ability of a commercially available comprehensive chest radiography deep convolutional neural network (DCNN) to detect simple and tension pneumothorax, as stratified by the following subgroups: the presence of an intercostal drain; rib, clavicular, scapular or humeral fractures or rib resections; subcutaneous emphysema and erect versus non-erect positioning. The hypothesis was that performance would not differ significantly in each of these subgroups when compa ...[more]

PMID: 34876430

Similar Datasets

Project description:IntroductionUltrasonography is being increasingly utilized in acute care settings with expanding applications. Pneumothorax evaluation by ultrasonography is a fast, safe, easy and inexpensive alternative to chest radiographs. In this review, we provide a comprehensive analysis of the current literature comparing ultrasonography and chest radiography for the diagnosis of pneumothorax.MethodsWe searched English-language articles in MEDLINE, EMBASE and Cochrane Library dealing with both ultrasonography and chest radiography for diagnosis of pneumothorax. In eligible studies that met strict inclusion criteria, we conducted a meta-analysis to evaluate the diagnostic accuracy of pleural ultrasonography in comparison with chest radiography for the diagnosis of pneumothorax.ResultsWe reviewed 601 articles and selected 25 original research articles for detailed review. Only 13 articles met all of our inclusion criteria and were included in the final analysis. One study used lung sliding sign alone, 12 studies used lung sliding and comet tail signs, and 6 studies searched for lung point in addition to the other two signs. Ultrasonography had a pooled sensitivity of 78.6% (95% CI, 68.1 to 98.1) and a specificity of 98.4% (95% CI, 97.3 to 99.5). Chest radiography had a pooled sensitivity of 39.8% (95% CI, 29.4 to 50.3) and a specificity of 99.3% (95% CI, 98.4 to 100). Our meta-regression and subgroup analyses indicate that consecutive sampling of patients compared to convenience sampling provided higher sensitivity results for both ultrasonography and chest radiography. Consecutive versus nonconsecutive sampling and trauma versus nontrauma settings were significant sources of heterogeneity. In addition, subgroup analysis showed significant variations related to operator and type of probe used.ConclusionsOur study indicates that ultrasonography is more accurate than chest radiography for detection of pneumothorax. The results support the previous investigations in this field, add new valuable information obtained from subgroup analysis, and provide accurate estimates for the performance parameters of both bedside ultrasonography and chest radiography for pneumothorax evaluation.

Project description:BackgroundPneumothorax can precipitate a life-threatening emergency due to lung collapse and respiratory or circulatory distress. Pneumothorax is typically detected on chest X-ray; however, treatment is reliant on timely review of radiographs. Since current imaging volumes may result in long worklists of radiographs awaiting review, an automated method of prioritizing X-rays with pneumothorax may reduce time to treatment. Our objective was to create a large human-annotated dataset of chest X-rays containing pneumothorax and to train deep convolutional networks to screen for potentially emergent moderate or large pneumothorax at the time of image acquisition.Methods and findingsIn all, 13,292 frontal chest X-rays (3,107 with pneumothorax) were visually annotated by radiologists. This dataset was used to train and evaluate multiple network architectures. Images showing large- or moderate-sized pneumothorax were considered positive, and those with trace or no pneumothorax were considered negative. Images showing small pneumothorax were excluded from training. Using an internal validation set (n = 1,993), we selected the 2 top-performing models; these models were then evaluated on a held-out internal test set based on area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value (PPV). The final internal test was performed initially on a subset with small pneumothorax excluded (as in training; n = 1,701), then on the full test set (n = 1,990), with small pneumothorax included as positive. External evaluation was performed using the National Institutes of Health (NIH) ChestX-ray14 set, a public dataset labeled for chest pathology based on text reports. All images labeled with pneumothorax were considered positive, because the NIH set does not classify pneumothorax by size. In internal testing, our "high sensitivity model" produced a sensitivity of 0.84 (95% CI 0.78-0.90), specificity of 0.90 (95% CI 0.89-0.92), and AUC of 0.94 for the test subset with small pneumothorax excluded. Our "high specificity model" showed sensitivity of 0.80 (95% CI 0.72-0.86), specificity of 0.97 (95% CI 0.96-0.98), and AUC of 0.96 for this set. PPVs were 0.45 (95% CI 0.39-0.51) and 0.71 (95% CI 0.63-0.77), respectively. Internal testing on the full set showed expected decreased performance (sensitivity 0.55, specificity 0.90, and AUC 0.82 for high sensitivity model and sensitivity 0.45, specificity 0.97, and AUC 0.86 for high specificity model). External testing using the NIH dataset showed some further performance decline (sensitivity 0.28-0.49, specificity 0.85-0.97, and AUC 0.75 for both). Due to labeling differences between internal and external datasets, these findings represent a preliminary step towards external validation.ConclusionsWe trained automated classifiers to detect moderate and large pneumothorax in frontal chest X-rays at high levels of performance on held-out test data. These models may provide a high specificity screening solution to detect moderate or large pneumothorax on images collected when human review might be delayed, such as overnight. They are not intended for unsupervised diagnosis of all pneumothoraces, as many small pneumothoraces (and some larger ones) are not detected by the algorithm. Implementation studies are warranted to develop appropriate, effective clinician alerts for the potentially critical finding of pneumothorax, and to assess their impact on reducing time to treatment.

Project description:BackgroundPneumothorax can lead to a life-threatening emergency. The experienced radiologists can offer precise diagnosis according to the chest radiographs. The localization of the pneumothorax lesions will help to quickly diagnose, which will be benefit for the patients in the underdevelopment areas lack of the experienced radiologists. In recent years, with the development of large neural network architectures and medical imaging datasets, deep learning methods have become a methodology of choice for analyzing medical images. The objective of this study was to the construct convolutional neural networks to localize the pneumothorax lesions in chest radiographs.Methods and findingsWe developed a convolutional neural network, called CheXLocNet, for the segmentation of pneumothorax lesions. The SIIM-ACR Pneumothorax Segmentation dataset was used to train and validate CheXLocNets. The training dataset contained 2079 radiographs with the annotated lesion areas. We trained six CheXLocNets with various hyperparameters. Another 300 annotated radiographs were used to select parameters of these CheXLocNets as the validation set. We determined the optimal parameters by the AP50 (average precision at the intersection over union (IoU) equal to 0.50), a segmentation evaluation metric used by several well-known competitions. Then CheXLocNets were evaluated by a test set (1082 normal radiographs and 290 disease radiographs), based on the classification metrics: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value (PPV); segmentation metrics: IoU and Dice score. For the classification, CheXLocNet with best sensitivity produced an AUC of 0.87, sensitivity of 0.78 (95% CI 0.73-0.83), and specificity of 0.78 (95% CI 0.76-0.81). CheXLocNet with best specificity produced an AUC of 0.79, sensitivity of 0.46 (95% CI 0.40-0.52), and specificity of 0.92 (95% CI 0.90-0.94). For the segmentation, CheXLocNet with best sensitivity produced an IoU of 0.69 and Dice score of 0.72. CheXLocNet with best specificity produced an IoU of 0.77 and Dice score of 0.79. We combined them to form an ensemble CheXLocNet. The ensemble CheXLocNet produced an IoU of 0.81 and Dice score of 0.82. Our CheXLocNet succeeded in automatically detecting pneumothorax lesions, without any human guidance.ConclusionsIn this study, we proposed a deep learning network, called, CheXLocNet, for the automatic segmentation of chest radiographs to detect pneumothorax. Our CheXLocNets generated accurate classification results and high-quality segmentation masks for the pneumothorax at the same time. This technology has the potential to improve healthcare delivery and increase access to chest radiograph expertise for the detection of diseases. Furthermore, the segmentation results can offer comprehensive geometric information of lesions, which can benefit monitoring the sequential development of lesions with high accuracy. Thus, CheXLocNets can be further extended to be a reliable clinical decision support tool. Although we used transfer learning in training CheXLocNet, the parameters of CheXLocNet was still large for the radiograph dataset. Further work is necessary to prune CheXLocNet suitable for the radiograph dataset.

Dataset Information

Do comprehensive deep learning algorithms suffer from hidden stratification? A retrospective study on pneumothorax detection in chest radiography.

Objectives

Design

Setting

Participants

Outcome measures

Results

Conclusions

Publications

Do comprehensive deep learning algorithms suffer from hidden stratification? A retrospective study on pneumothorax detection in chest radiography.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets