COVID-19 pneumonia diagnosis using chest x-ray radiograph and deep learning

Griner, Dalton; Zhang, Ran; Tie, Xin; Zhang, Chengzhu; Garrett, John W.; Li, Ké; Chen, Guang-Hong

doi:10.1117/12.2581972

Cited by 5 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recent outbreak of COVID-19 disease has given an additional impetus to automated pneumonia diagnosis, especially to the recognition of various pneumonia types. The accuracy of COVID-19 diagnosis against healthy X-rays is around 0.76–0.90 AUC 57 , 59 – 62 , whereas the differentiation between COVID-19 and non-COVID-19 pneumonia reaches the accuracy of 0.92 AUC 63 , 64 . The proposed framework achieved the AUC of 0.842 and correctly labeled as pathological a 95% of X-rays with pneumonia.…”

Section: Discussionmentioning

confidence: 97%

A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis

Ibragimov

Arzamasov

Maksudov

et al. 2023

Sci Rep

View full text Add to dashboard Cite

In 2020, an experiment testing AI solutions for lung X-ray analysis on a multi-hospital network was conducted. The multi-hospital network linked 178 Moscow state healthcare centers, where all chest X-rays from the network were redirected to a research facility, analyzed with AI, and returned to the centers. The experiment was formulated as a public competition with monetary awards for participating industrial and research teams. The task was to perform the binary detection of abnormalities from chest X-rays. For the objective real-life evaluation, no training X-rays were provided to the participants. This paper presents one of the top-performing AI frameworks from this experiment. First, the framework used two EfficientNets, histograms of gradients, Haar feature ensembles, and local binary patterns to recognize whether an input image represents an acceptable lung X-ray sample, meaning the X-ray is not grayscale inverted, is a frontal chest X-ray, and completely captures both lung fields. Second, the framework extracted the region with lung fields and then passed them to a multi-head DenseNet, where the heads recognized the patient’s gender, age and the potential presence of abnormalities, and generated the heatmap with the abnormality regions highlighted. During one month of the experiment from 11.23.2020 to 12.25.2020, 17,888 cases have been analyzed by the framework with 11,902 cases having radiological reports with the reference diagnoses that were unequivocally parsed by the experiment organizers. The performance measured in terms of the area under receiving operator curve (AUC) was 0.77. The AUC for individual diseases ranged from 0.55 for herniation to 0.90 for pneumothorax.

show abstract

Section: Discussionmentioning

confidence: 97%

A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis

Ibragimov

Arzamasov

Maksudov

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…For prediction at test stage, region proposal task was still an issue that required further improvements. A segmentation and classification model proposed to compare with radiologist cohort Private [82] A CNN model proposed for identification of abnormal CXRs and localization of abnormalities Private [83] Localizing COVID-19 opacity and severity detection on CXRs Private [84] Use of Lung cropped CXR in DenseNet for cardiomegaly detection Open-I, PadChest [85] Applied multiple models and combinations of CXR datasets to detect COVID-19 ChestX-ray14 JSRT + SCR, COVID-CXR [86] Multiple architectures evaluated for two-stage classification of pneumonia Ped-pneumonia [87] Inception-v3 based pneumoconiosis detection and evaluation against two radiologists Private [88] VGG-16 architecture adapted for classification of pediatric pneumonia types Ped-pneumonia [89] Used ResNet-50 as backbone for segmentation model to detect healthy, pneumonia, and COVID-19 COVID-CXR [90] CNN employed to detect the presence of subphrenic free air from CXR Private [91] Binary classification vs One-class identification of viral pneumonia cases Private [92] Applied a weighting scheme to improve abnormality for classification ChestX-ray14 [93] To improve image-level classification, a Lesion detection network has been employed Private [94] An ensemble scheme has been used for DenseNet-121 networks for COVID-19 classification ChestX-ray14…”

Section: Fast R-cnnmentioning

confidence: 99%

A Survey on Tools and Techniques for Localizing Abnormalities in X-ray Images Using Deep Learning

et al. 2022

View full text Add to dashboard Cite

Deep learning is expanding and continues to evolve its capabilities toward more accuracy, speed, and cost-effectiveness. The core ingredients for getting its promising results are appropriate data, sufficient computational resources, and best use of a particular algorithm. The application of these algorithms in medical image analysis tasks has achieved outstanding results compared to classical machine learning approaches. Localizing the area-of-interest is a challenging task that has vital importance in computer aided diagnosis. Generally, radiologists interpret the radiographs based on their knowledge and experience. However, sometimes, they can overlook or misinterpret the findings due to various reasons, e.g., workload or judgmental error. This leads to the need for specialized AI tools that assist radiologists in highlighting abnormalities if exist. To develop a deep learning driven localizer, certain alternatives are available within architectures, datasets, performance metrics, and approaches. Informed decision for selection within the given alternative can lead to batter outcome within lesser resources. This paper lists the required components along-with explainable AI for developing an abnormality localizer for X-ray images in detail. Moreover, strong-supervised vs weak-supervised approaches have been majorly discussed in the light of limited annotated data availability. Likewise, other correlated challenges have been presented along-with recommendations based on a relevant literature review and similar studies. This review is helpful in streamlining the development of an AI based localizer for X-ray images while extendable for other radiological reports.

show abstract

“…Saha et al [48] has proposed ensembles of binary classifiers and developed a deep learning model EMCNet, producing instant detection with a low false-negative rate. Many pieces of research [49] [50] [51] in automated COVID-19 detection involves feature extraction followed by the traditional classification algorithms or deep learning models.…”

Section: Background Studymentioning

confidence: 99%

Automatic diagnosis of COVID-19 from Chest X-ray images using transfer learning-based deep features and machine learning models

Kumar

Gupta

Hazarika

et al. 2022

Preprint

View full text Add to dashboard Cite

The novel Coronavirus, declared as a pandemic by WHO, has caused a health crisis and disrupted the daily course of the people globally. The effectiveness of Chest X-ray (CXR) in the differentiation of COVID from non-COVID has exhorted us to propose a diagnostic model based on deep features. This paper proposes a diagnostic framework to diagnose COVID-19 from Chest X-rays (CXR). Further Grad-CAM visualizations are shown to get a visual interpretation for the predicted images. We validated the performance of the proposed diagnostic model using the area under the curve (AUC), accuracy, precision, recall, F1-score and geometric mean (G-mean). Few popular machine learning models such as random forest, dense neural network, support vector machine (SVM), twin SVM (TWSVM), extreme learning machine (ELM), random vector functional link (RVFL) and kernel ridge regression (KRR) have been selected for diagnosing the COVID cases. The deep features are extracted by transfer learning. Grad-CAM visualizations are presented for the predicted images. We have achieved the best AUC score of 0.98 on TWSVM classifier on the feature vector extracted by ResNet50 architecture. The feature vector extracted from ResNet50 outperforms all other CNN architecture rank wise based on AUC. The experimental outcome indicates the efficiency of the proposed diagnostic framework.

show abstract

COVID-19 pneumonia diagnosis using chest x-ray radiograph and deep learning

Cited by 5 publications

References 0 publications

A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis

A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis

A Survey on Tools and Techniques for Localizing Abnormalities in X-ray Images Using Deep Learning

Automatic diagnosis of COVID-19 from Chest X-ray images using transfer learning-based deep features and machine learning models

Contact Info

Product

Resources

About