Chest x-ray generation and data augmentation for cardiovascular abnormality classification

Madani, Ali; Moradi, Mehdi; Karargyris, Alexandros; Syeda-Mahmood, Tanveer

doi:10.1117/12.2293971

Cited by 76 publications

(29 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other works have successfully applied DCGANs for dataset augmentation in various CXR classification tasks. Moradi et al focus on generating both normal and cardiac abnormality images, they find that GAN-based augmentation outperforms traditional training augmentation of flipping, cropping, or scaling images [30] . Salehinejad et al expand upon this concept by producing a per-class DCGAN and Fig.…”

Section: Synthetic Medical Datamentioning

confidence: 99%

Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs

Segal

Rubin

et al. 2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

Chest X-rays are a vital diagnostic tool in the workup of many patients. Similar to most medical imaging modalities, they are profoundly multi-modal and are capable of visualising a variety of combinations of conditions. There is an ever pressing need for greater quantities of labelled images to drive forward the development of diagnostic tools; however, this is in direct opposition to concerns regarding patient confidentiality which constrains access through permission requests and ethics approvals. Previous work has sought to address these concerns by creating class-specific generative adversarial networks (GANs) that synthesise images to augment training data. These approaches cannot be scaled as they introduce computational trade offs between model size and class number which places fixed limits on the quality that such generates can achieve. We address this concern by introducing latent class optimisation which enables efficient, multi-modal sampling from a GAN and with which we synthesise a large archive of labelled generates. We apply a Progressive Growing GAN (PGGAN) to the task of unsupervised X-ray synthesis and have radiologists evaluate the clinical realism of the resultant samples. We provide an in depth review of the properties of varying pathologies seen on generates as well as an overview of the extent of disease diversity captured by the model. We validate the application of the Fréchet Inception Distance (FID) to measure the quality of X-ray generates and find that they are similar to other high-resolution tasks. We quantify X-ray clinical realism by asking radiologists to distinguish between real and fake scans and find that generates are more likely to be classed as real than by chance, but there is still progress required to achieve true realism. We confirm these findings by evaluating synthetic classification model performance on real scans. We conclude by discussing the limitations of PGGAN generates and how to achieve controllable, realistic generates going forward. We release our source code, model weights, and an archive of labelled generates.

show abstract

Section: Synthetic Medical Datamentioning

confidence: 99%

Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs

Segal

Rubin

et al. 2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

show abstract

“…For example, Lahiri et al [39] and Madani et al [40] used the semi-supervised deep convolutional generative adversarial network (DCGAN) [41] for retinal vessel classification and cardiovascular abnormality classification in chest X-rays, respectively. Madani et al [42] also used two DCGANs to generate normal and abnormal chest X-rays separately, which achieved higher classification accuracy than traditional data augmentation methods. This may be due to the fact that traditional data augmentation methods cannot capture the biological variance of medical images, which may result in unrealistic images after augmentation.…”

Section: Accepted Articlementioning

confidence: 99%

COVID‐19 diagnosis on CT scan images using a generative adversarial network and concatenated feature pyramid network with an attention mechanism

Zhang

et al. 2021

Medical Physics

View full text Add to dashboard Cite

Objective: Coronavirus disease 2019 (COVID-19) has caused hundreds of thousands of infections and deaths. Efficient diagnostic methods could help curb its global spread. The purpose of this study was to develop and evaluate a method for accurately diagnosing COVID-19 based on computed tomography (CT) scans in real time. Methods: We propose an architecture named "concatenated feature pyramid network" ("Concat-FPN") with an attention mechanism, by concatenating feature maps of multiple. The proposed architecture is then used to form two networks, which we call COVID-CT-GAN and COVID-CT-DenseNet, the former for data augmentation and the latter for data classification. Results: The proposed method is evaluated on 3 different numbers of magnitude of COVID-19 CT datasets. Compared with the method without GANs for data augmentation or the original network auxiliary classifier generative adversarial network, COVID-CT-GAN increases the accuracy by 2% to 3%, the recall by 2% to 4%, the precision by 1% to 3%, the F1-score by 1% to 3%, and the area under the curve by 1% to 4%. Compared with the original network DenseNet-201, COVID-CT-DenseNet increases the accuracy by 1% to 3%, the recall by 4% to 9%, the precision by 1%, the F1-score by 1% to 3%, and the area under the curve by 2%. Conclusion: The experimental results show that our method improves the efficiency of diagnosing COVID-19 on CT images, and helps overcome the problem of limited training data when using deep learning methods to diagnose COVID-19. Significance: Our method can help clinicians build deep learning models using their private datasets to achieve automatic diagnosis of

show abstract

“…Deep learning has the potential to revolutionize the automation of chest radiography interpretation. More than 40,000 research articles have been published related to the use of deep learning in this topic including the establishment of referent data set [4], organ segmentation [5], artefact removal [6], multilabel classification [7], data augmentation [8], and grading of disease severity [9]. The key component in deep learning research is the availability of training and testing data set, whether or not it is accessible to allow reproducibility and comparability of the research.…”

Section: Introductionmentioning

confidence: 99%

COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings

Azemin

Hassan

Tamrin

et al. 2020

International Journal of Biomedical Imaging

120

View full text Add to dashboard Cite

The key component in deep learning research is the availability of training data sets. With a limited number of publicly available COVID-19 chest X-ray images, the generalization and robustness of deep learning models to detect COVID-19 cases developed based on these images are questionable. We aimed to use thousands of readily available chest radiograph images with clinical findings associated with COVID-19 as a training data set, mutually exclusive from the images with confirmed COVID-19 cases, which will be used as the testing data set. We used a deep learning model based on the ResNet-101 convolutional neural network architecture, which was pretrained to recognize objects from a million of images and then retrained to detect abnormality in chest X-ray images. The performance of the model in terms of area under the receiver operating curve, sensitivity, specificity, and accuracy was 0.82, 77.3%, 71.8%, and 71.9%, respectively. The strength of this study lies in the use of labels that have a strong clinical association with COVID-19 cases and the use of mutually exclusive publicly available data for training, validation, and testing.

show abstract

Chest x-ray generation and data augmentation for cardiovascular abnormality classification

Cited by 76 publications

References 5 publications

Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs

Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs

COVID‐19 diagnosis on CT scan images using a generative adversarial network and concatenated feature pyramid network with an attention mechanism

COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings

Contact Info

Product

Resources

About