Deep learning-based bone suppression in chest radiographs using CT-derived features: a feasibility study

Ren, Ge; Xiao, Haonan; Lam, Sai Kit; Yang, Dongrong; Tian, Li; Teng, Xinzhi; Qin, Jing; Cai, Jing

doi:10.21037/qims-20-1230

Cited by 5 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides CXR, demographic information (e.g., age, sex) and other available modalities’ data will be also collected to conduct more comprehensive assessments. Further image synthesis method ( 51 , 52 ) and enhancement techniques ( 53 ) could be explored to improve the COVID-19 classification or severity assessment.…”

Section: Discussionmentioning

confidence: 99%

Deep learning attention-guided radiomics for COVID-19 chest radiograph classification

Yang¹,

Ren²,

Ni³

et al. 2023

Quant Imaging Med Surg

Self Cite

View full text Add to dashboard Cite

Background: Accurate assessment of coronavirus disease 2019 (COVID-19) lung involvement through chest radiograph plays an important role in effective management of the infection. This study aims to develop a two-step feature merging method to integrate image features from deep learning and radiomics to differentiate COVID-19, non-COVID-19 pneumonia and normal chest radiographs (CXR).Methods: In this study, a deformable convolutional neural network (deformable CNN) was developed and used as a feature extractor to obtain 1,024-dimensional deep learning latent representation (DLR) features.Then 1,069-dimensional radiomics features were extracted from the region of interest (ROI) guided by deformable CNN's attention. The two feature sets were concatenated to generate a merged feature set for classification. For comparative experiments, the same process has been applied to the DLR-only feature set for verifying the effectiveness of feature concatenation.Results: Using the merged feature set resulted in an overall average accuracy of 91.0% for three-class classification, representing a statistically significant improvement of 0.6% compared to the DLR-only classification. The recall and precision of classification into the COVID-19 class were 0.926 and 0.976, respectively. The feature merging method was shown to significantly improve the classification performance as compared to using only deep learning features, regardless of choice of classifier (P value <0.0001). Three classes' F1-score were 0.892, 0.890, and 0.950 correspondingly (i.e., normal, non-COVID-19 pneumonia, COVID-19).Conclusions: A two-step COVID-19 classification framework integrating information from both DLR and radiomics features (guided by deep learning attention mechanism) has been developed. The proposed feature merging method has been shown to improve the performance of chest radiograph classification as compared to the case of using only deep learning features.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning attention-guided radiomics for COVID-19 chest radiograph classification

Yang¹,

Ren²,

Ni³

et al. 2023

Quant Imaging Med Surg

Self Cite

View full text Add to dashboard Cite

show abstract

“…These values are listed from highest to lowest. The proposed research produced lung digital x-rays, bone digital x-rays, and bone-free digital x-rays from 59 high-resolution CT images of the lung [17]. These DRs were utilized for the purpose of the suggested cascade convolutional neural network's internal evaluation as well as its training (CCNN).…”

Section: Related Workmentioning

confidence: 99%

Suppressing Chest Radiograph Ribs for Improving Lung Nodule Visibility by using Circular Window Adaptive Median Outlier (CWAMO)

Kanade¹,

Helonde²

2023

IJACSA

View full text Add to dashboard Cite

Chest radiograph ribs obstruct lung nodules. To see the nodule under the chest radiograph ribs, remove or suppress them. The paper describes a circular median filter approach for finding outliers in chest radiographs. The method uses 147 Japanese Society of Radiological Technology x-ray pictures (JSRT). Pixels with intensities two standard deviations above the median are median outliers. Contrast-Limited Adaptive Histogram Equalization enhances nodule visibility (CLAHE). The method is tested on modest chest radiographs and compared to the Budapest University Bone Shadow Eliminated X-Ray Dataset methodology. The initial test uses 50 modest chest radiographs (Test 1). The proposed approach is applied after active shape modelling (ASM) lung segmentation. True positive nodules are seen on 89% of chest radiographs of various subtleties. Test-2 and Test-3 used 20 subtlety-level photos. In Test-2, the peak signal-to-noise ratio (PSNR), mean-to-standard deviation ratio (MSR), and universal image quality index (IQI) are evaluated for the full image and compared to the existing algorithm. For all three parameters, the suggested technique outperforms the algorithm. Test-3 computes nodule MSR and compares it to Budapest University's Bone Shadow Eliminated Dataset and original chest radiographs. The new algorithm improved nodule area contrast by 3.83% and 23.94% compared to the original chest radiograph. This approach improves chest radiograph nodule visualization.

show abstract

“…In recent years, deep learning models have made significant progress in medical image processing tasks. They have also been gradually applied to the study of bone signal suppression in CXR (28)(29)(30)(31)(32)(33). The above AI-based image processing methods can suppress the CXR bone signal.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification

Sun¹,

Ren²,

Teng³

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification. Methods: Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models.Results: Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images. Conclusions:The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.

show abstract

Deep learning-based bone suppression in chest radiographs using CT-derived features: a feasibility study

Cited by 5 publications

References 30 publications

Deep learning attention-guided radiomics for COVID-19 chest radiograph classification

Deep learning attention-guided radiomics for COVID-19 chest radiograph classification

Suppressing Chest Radiograph Ribs for Improving Lung Nodule Visibility by using Circular Window Adaptive Median Outlier (CWAMO)

Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification

Contact Info

Product

Resources

About