Title | ||
---|---|---|
Automated Segmentation And Diagnosis Of Pneumothorax On Chest X-Rays With Fully Convolutional Multi-Scale Scse-Densenet: A Retrospective Study |
Abstract | ||
---|---|---|
Background: Pneumothorax (PTX) may cause a life-threatening medical emergency with cardio-respiratory collapse that requires immediate intervention and rapid treatment. The screening and diagnosis of pneumothorax usually rely on chest radiographs. However, the pneumothoraces in chest X-rays may be very subtle with highly variable in shape and overlapped with the ribs or clavicles, which are often difficult to identify. Our objective was to create a large chest X-ray dataset for pneumothorax with pixel-level annotation and to train an automatic segmentation and diagnosis framework to assist radiologists to identify pneumothorax accurately and timely.Methods: In this study, an end-to-end deep learning framework is proposed for the segmentation and diagnosis of pneumothorax on chest X-rays, which incorporates a fully convolutional DenseNet (FC-DenseNet) with multi-scale module and spatial and channel squeezes and excitation (scSE) modules. To further improve the precision of boundary segmentation, we propose a spatial weighted cross-entropy loss function to penalize the target, background and contour pixels with different weights.Results: This retrospective study are conducted on a total of eligible 11,051 front-view chest X-ray images (5566 cases of PTX and 5485 cases of Non-PTX). The experimental results show that the proposed algorithm outperforms the five state-of-the-art segmentation algorithms in terms of mean pixel-wise accuracy (MPA) with 0.93 +/- 0.13 and dice similarity coefficient (DSC) with 0.92 +/- 0.14, and achieves competitive performance on diagnostic accuracy with 93.45% and F1-score with 92.97%.Conclusion: This framework provides substantial improvements for the automatic segmentation and diagnosis of pneumothorax and is expected to become a clinical application tool to help radiologists to identify pneumothorax on chest X-rays. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1186/s12911-020-01325-5 | BMC MEDICAL INFORMATICS AND DECISION MAKING |
Keywords | DocType | Volume |
Chest X-ray, Pneumothorax segmentation and diagnosis, fully convolutional DenseNet, Spatial and channel squeezes and excitation, Spatial weighted cross-entropy loss | Journal | 20 |
Issue | ISSN | Citations |
14 | 1472-6947 | 1 |
PageRank | References | Authors |
0.37 | 0 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qingfeng Wang | 1 | 18 | 7.53 |
Qiyu Liu | 2 | 1 | 0.71 |
Guoting Luo | 3 | 1 | 0.37 |
Zhi-qin Liu | 4 | 12 | 4.93 |
jun huang | 5 | 90 | 13.64 |
Yuwei Zhou | 6 | 1 | 0.37 |
Ying Zhou | 7 | 95 | 18.36 |
Weiyun Xu | 8 | 1 | 1.39 |
Jie-Zhi Cheng | 9 | 102 | 13.00 |