Dataset Information

Chest X-ray pneumothorax segmentation using U-Net with EfficientNet and ResNet architectures.

ABSTRACT: Medical imaging refers to visualization techniques to provide valuable information about the internal structures of the human body for clinical applications, diagnosis, treatment, and scientific research. Segmentation is one of the primary methods for analyzing and processing medical images, which helps doctors diagnose accurately by providing detailed information on the body's required part. However, segmenting medical images faces several challenges, such as requiring trained medical experts and being time-consuming and error-prone. Thus, it appears necessary for an automatic medical image segmentation system. Deep learning algorithms have recently shown outstanding performance for segmentation tasks, especially semantic segmentation networks that provide pixel-level image understanding. By introducing the first fully convolutional network (FCN) for semantic image segmentation, several segmentation networks have been proposed on its basis. One of the state-of-the-art convolutional networks in the medical image field is U-Net. This paper presents a novel end-to-end semantic segmentation model, named Ens4B-UNet, for medical images that ensembles four U-Net architectures with pre-trained backbone networks. Ens4B-UNet utilizes U-Net's success with several significant improvements by adapting powerful and robust convolutional neural networks (CNNs) as backbones for U-Nets encoders and using the nearest-neighbor up-sampling in the decoders. Ens4B-UNet is designed based on the weighted average ensemble of four encoder-decoder segmentation models. The backbone networks of all ensembled models are pre-trained on the ImageNet dataset to exploit the benefit of transfer learning. For improving our models, we apply several techniques for training and predicting, including stochastic weight averaging (SWA), data augmentation, test-time augmentation (TTA), and different types of optimal thresholds. We evaluate and test our models on the 2019 Pneumothorax Challenge dataset, which contains 12,047 training images with 12,954 masks and 3,205 test images. Our proposed segmentation network achieves a 0.8608 mean Dice similarity coefficient (DSC) on the test set, which is among the top one-percent systems in the Kaggle competition.

SUBMITTER: Abedalla A

PROVIDER: S-EPMC8279140 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

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.

Project description:BackgroundIn patients with multiple trauma, a supine chest radiography [chest X-ray (CXR)] is preferred over a erect CXR. However, this method has limitations in detecting post-traumatic pneumothorax. The use of chest computed tomography (CT) to detect traumatic pneumothorax is well known. However, pneumothorax that is not detected before a chest CT scan is known as an occult pneumothorax (OP), and it can cause serious complications in the patient. This study sought to evaluate the frequency and risk factors for OP in trauma patients.MethodsPatients who suffered thoracic trauma at the Level 1 Regional Trauma Center of Wonju Severance Christian Hospital between 2015 and 2022 were included in this study. All patients were at least 18 years old. The study reviewed all patients' supine CXR and chest CT images and classified them into five radiographic diagnoses: pneumothorax, rib fracture, subcutaneous emphysema, lung contusion, and pneumomediastinum.ResultsThe study included 1,284 patients, all with diagnoses of pneumothorax, rib fracture, subcutaneous emphysema, lung contusion, and pneumomediastinum following supine CXR and chest CT. The patient's average age was 58.3±15.2 years. Pneumothorax diagnosis on supine CXR had the lowest accuracy, at 46.7%, and the lowest sensitivity, at 12.7%. In univariate analysis, rib fracture, lung contusion, and subcutaneous emphysema on supine CXR were all found to be statistically significant regarding traumatic OP. In multivariate analysis, the risk factors for OP were lung contusion [odds ratio (OR), 1.440; 95% confidence interval (CI): 1.115-1.860; P=0.005] and subcutaneous emphysema (OR, 25.883; 95% CI: 13.155-50.928; P<0.001) on supine CXR.ConclusionsThe lung contusion and subcutaneous emphysema in supine CXR of trauma patients indicate the presence of OP. Therefore, if chest CT cannot be performed immediately due to unstable vital signs or other circumstances, recognizing the above radiological findings of traumatic pneumothorax may be necessary.

Dataset Information

Chest X-ray pneumothorax segmentation using U-Net with EfficientNet and ResNet architectures.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets