scholarly journals Automatic Lung Segmentation Algorithm on Chest X-ray Images Based on Fusion Variational Auto-Encoder and Three-Terminal Attention Mechanism

Symmetry ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 814
Author(s):  
Feidao Cao ◽  
Huaici Zhao
Keyword(s):  
Automatic Segmentation ◽  
Attention Mechanism ◽  
Segmentation Algorithm ◽  
Target Area ◽  
Lung Segmentation ◽  
X Ray ◽  
Chest X Ray ◽  
Left And Right ◽  
High Level ◽  
Better Than

Automatic segmentation of the lungs in Chest X-ray images (CXRs) is a key step in the screening and diagnosis of related diseases. There are many opacities in the lungs in the CXRs of patients, which makes the lungs difficult to segment. In order to solve this problem, this paper proposes a segmentation algorithm based on U-Net. This article introduces variational auto-encoder (VAE) in each layer of the decoder-encoder. VAE can extract high-level semantic information, such as the symmetrical relationship between the left and right thoraxes in most cases. The fusion of the features of VAE and the features of convolution can improve the ability of the network to extract features. This paper proposes a three-terminal attention mechanism. The attention mechanism uses the channel and spatial attention module to automatically highlight the target area and improve the performance of lung segmentation. At the same time, the three-terminal attention mechanism uses the advanced semantics of high-scale features to improve the positioning and recognition capabilities of the attention mechanism, suppress background noise, and highlight target features. Experimental results on two different datasets show that the accuracy (ACC), recall (R), F1-Score and Jaccard values of the algorithm proposed in this paper are the highest on the two datasets, indicating that the algorithm in this paper is better than other state-of-the-art algorithms.

Diagnosis of Lung segmentation for Chest X Ray images using XGBoost

2021 ◽  
Author(s):  
Preeti Arora ◽  
Saksham Gera ◽  
Vinod M Kapse
Keyword(s):  
Lung Segmentation ◽  
X Ray ◽  
Chest X Ray

scholarly journals Automated segmentation and diagnosis of pneumothorax on chest X-rays with fully convolutional multi-scale ScSE-DenseNet: a retrospective study

2020 ◽  
Vol 20 (S14) ◽  
Author(s):  
Qingfeng Wang ◽  
Qiyu Liu ◽  
Guoting Luo ◽  
Zhiqin Liu ◽  
Jun Huang ◽  
...  
Keyword(s):  
Retrospective Study ◽  
Automatic Segmentation ◽  
Medical Emergency ◽  
Dice Similarity Coefficient ◽  
X Rays ◽  
X Ray ◽  
Learning Framework ◽  
Multi Scale ◽  
Life Threatening ◽  
Chest X Ray

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 $$0.93\pm 0.13$$ 0.93 ± 0.13 and dice similarity coefficient (DSC) with $$0.92\pm 0.14$$ 0.92 ± 0.14 , and achieves competitive performance on diagnostic accuracy with 93.45% and $$F_1$$ F 1 -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.

scholarly journals Comparison between the molecular diagnostic test and chest X-ray combined with multi-slice spiral CT in the diagnosis of lobar pneumonia

2021 ◽  
Vol 67 (3) ◽  
pp. 129-132
Author(s):  
Huiping Zhu ◽  
Jianjun Dong ◽  
Xufeng Xie ◽  
Lei Wang
Keyword(s):  
Streptococcus Pneumoniae ◽  
Klebsiella Pneumoniae ◽  
Diagnostic Test ◽  
Spiral Ct ◽  
Molecular Diagnostic ◽  
X Ray ◽  
Lobar Pneumonia ◽  
Chest X Ray ◽  
Molecular Diagnostic Test ◽  
Better Than

Lobar pneumonia is an inflammatory condition of the lung that mainly affects the lobes of the lungs and the alveoli, and it is usually caused by a bacterial infection. There are many ways to diagnosis this disease. But an early and accurate method for lobar pneumonia diagnosis has an important role in its treatment. Therefore, in this study, a comparison between the molecular diagnostic test and chest x-ray combined with multi-slice spiral CT was done to find out better diagnosis of lobar pneumonia. For this purpose, 122 individuals suspected of lobar pneumonia were studied by clinical examination, chest X-ray, and multi-slice spiral CT. For the molecular diagnosis test, the multiplex PCR was used for two main causes of the disease, Streptococcus pneumoniae and Klebsiella pneumoniae. Results showed that the specificity for Chest X-ray + Multi-slice Spiral CT had the highest amount (82.8%), but high sensitivity (100%) belonged to a molecular diagnostic test for both bacteria. On the other hand, the sensitivity and specificity of Streptococcus pneumoniae were better than Klebsiella pneumoniae and the possibility of error in Streptococcus pneumoniae was lower than Klebsiella pneumoniae. In general, although the Chest X-ray + Multi-slice Spiral CT method was better than the molecular diagnosis test, it could not identify the causative agent and did not show a difference between pathogens for better antibiotic treatment, and also the possibility of diagnosis is low at the beginning of the disease. Therefore, according to the results of the current study, the best way to diagnose lobar pneumonia is to use both methods, simultaneously.

scholarly journals Impact of Lung Segmentation on the Diagnosis and Explanation of COVID-19 in Chest X-ray Images

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7116
Author(s):  
Lucas O. Teixeira ◽  
Rodolfo M. Pereira ◽  
Diego Bertolini ◽  
Luiz S. Oliveira ◽  
Loris Nanni ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Image Database ◽  
Dice Coefficient ◽  
Lung Segmentation ◽  
X Ray ◽  
Explainable Artificial Intelligence ◽  
Segmented Images ◽  
Chest X Ray ◽  
The Impact ◽  
Different Sources

COVID-19 frequently provokes pneumonia, which can be diagnosed using imaging exams. Chest X-ray (CXR) is often useful because it is cheap, fast, widespread, and uses less radiation. Here, we demonstrate the impact of lung segmentation in COVID-19 identification using CXR images and evaluate which contents of the image influenced the most. Semantic segmentation was performed using a U-Net CNN architecture, and the classification using three CNN architectures (VGG, ResNet, and Inception). Explainable Artificial Intelligence techniques were employed to estimate the impact of segmentation. A three-classes database was composed: lung opacity (pneumonia), COVID-19, and normal. We assessed the impact of creating a CXR image database from different sources, and the COVID-19 generalization from one source to another. The segmentation achieved a Jaccard distance of 0.034 and a Dice coefficient of 0.982. The classification using segmented images achieved an F1-Score of 0.88 for the multi-class setup, and 0.83 for COVID-19 identification. In the cross-dataset scenario, we obtained an F1-Score of 0.74 and an area under the ROC curve of 0.9 for COVID-19 identification using segmented images. Experiments support the conclusion that even after segmentation, there is a strong bias introduced by underlying factors from different sources.

An automatic method for lung segmentation and reconstruction in chest X-ray using deep neural networks

2019 ◽  
Vol 177 ◽  
pp. 285-296 ◽  
Author(s):  
Johnatan Carvalho Souza ◽  
João Otávio Bandeira Diniz ◽  
Jonnison Lima Ferreira ◽  
Giovanni Lucca França da Silva ◽  
Aristófanes Corrêa Silva ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Automatic Method ◽  
Lung Segmentation ◽  
X Ray ◽  
Chest X Ray

scholarly journals Development of a lung segmentation algorithm for analog imaged chest X-Ray: preliminary results

2021 ◽  
Author(s):  
Matheus A. Renzo ◽  
Natália Fernandez ◽  
André A. Baceti ◽  
Natanael Nunes Moura Junior ◽  
André Anjos
Keyword(s):  
Semantic Segmentation ◽  
X Rays ◽  
Computer Aided Detection ◽  
Segmentation Evaluation ◽  
Lung Segmentation ◽  
X Ray ◽  
Chest X Ray ◽  
Digitized Images ◽  
Public Datasets ◽  
The Impact

Analog X-Ray radiography is still used in many underdeveloped regions around the world. To allow these populations to benefit from advances in automatic computer-aided detection (CAD) systems, X-Ray films must be digitized. Unfortunately, this procedure may introduce artefacts which may severely impair the performance of such systems. This work investigates the impact digitized images may cause to deep neural networks trained for lung (semantic) segmentation on digital x-ray samples. While three public datasets for lung segmentation evaluation exist for digital samples, none are available for digitized data. To this end, a U-Net architecture was trained on publicly available data, and used to predict lung segmentation on a newly annotated set of digitized images. Our results show that the model is capable to effectively identify lung segmentation at digital X-Rays with a high intra-dataset (PR AUC: 0.99) and cross-dataset (PR AUC: 0.99) performances on unseen test data. When challenged against analog imaged films, the performance is substantially degraded (PR AUC: 0.90). Our analysis further suggests that the use of maximum F1 and precision-recall AUC (PR AUC) measures are not informative to identify segmentation problems in images.

scholarly journals Two-stream collaborative network for multi-label chest X-ray Image classification with lung segmentation

2020 ◽  
Vol 135 ◽  
pp. 221-227 ◽  
Author(s):  
Bingzhi Chen ◽  
Zheng Zhang ◽  
Jianyong Lin ◽  
Yi Chen ◽  
Guangming Lu
Keyword(s):  
Image Classification ◽  
Collaborative Network ◽  
Lung Segmentation ◽  
X Ray ◽  
Chest X Ray

scholarly journals A Robust Automated Lung Segmentation System for Chest X-ray (CXR) Images

2017 ◽  
Vol V6 (04) ◽  
Author(s):  
Akhila K J ◽  
Ajitha M ◽  
Ashy V Daniel ◽  
Ashwin Singerji ◽  
Keyword(s):  
Lung Segmentation ◽  
X Ray ◽  
Chest X Ray
Sign in / Sign up

Export Citation Format

Share Document