CheXLocNet: Automatic localization of pneumothorax in chest radiographs using deep convolutional neural networks

Abstract

Background Pneumothorax 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 findings We 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. Conclusions In 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.

Detection of the location of pneumothorax in chest X-rays using small artificial neural networks and a simple training process

“…The framework's performance, as measured by the Dice factor in the study, was 0.8574. In another study, a CNN called CheXLocNet had an intersection over union of 0.81 and a Dice score of 0.82 for automatic pneumothorax localization 10 . In another recent paper, the pneumothorax found in chest X-rays was segmented using a CNN called a fully convolutional DenseNet, achieving a mean pixelwise accuracy (MPA) of 0.93 and a Dice similarity coefficient of 0.92 11 .…”

A Hybrid VDV Model for Automatic Diagnosis of Pneumothorax Using Class-Imbalanced Chest X-Rays Dataset

“…The performance comparison of our proposed model for SIIM Pneumothorax dataset is provided in Table XII. We can directly compare our result with [55], in which the same dataset and same testing set was used. It can be clearly seen that although their reported AUC is slightly greater than the AUC value achieved by our proposed model, however the sensitivity/ recall achieved by our proposed model is far greater than the value reported in [55].…”

“…We can directly compare our result with [55], in which the same dataset and same testing set was used. It can be clearly seen that although their reported AUC is slightly greater than the AUC value achieved by our proposed model, however the sensitivity/ recall achieved by our proposed model is far greater than the value reported in [55]. Since our aim is to increase the rate of correct classification of positive class samples, so we can safely claim that our proposed model surpasses the existing techniques.…”

Deep learning applied to automatic disease detection using chest X‐rays

“…In 2020, researchers started segmenting pneumothoraces using DDN models. Wang 103 developed CheXLocNet which demonstrated a classification performance of AUROC 0.87, and segmentation performance ranging from IoU 0.69–0.77 and Dice score 0.72–0.79. A different group, Wang 104 used a fully convolutional DenseNet (FC‐DenseNet) with multi‐scale module and spatial and channel squeezes and excitation modules in the detection and segmentation of pneumothoraces.…”