English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Pneumothorax, a life threatening disease, needs to be diagnosed immediatelyand efficiently. The prognosis in this case is not only time consuming but alsoprone to human errors. So an automatic way of accurate diagnosis using chestX-rays is the utmost requirement. To-date, most of the available medical imagesdatasets have class-imbalance issue. The main theme of this study is to solvethis problem along with proposing an automated way of detecting pneumothorax.We first compare the existing approaches to tackle the class-imbalance issueand find that data-level-ensemble (i.e. ensemble of subsets of dataset)outperforms other approaches. Thus, we propose a novel framework named as VDVmodel, which is a complex model-level-ensemble of data-level-ensembles and usesthree convolutional neural networks (CNN) including VGG16, VGG-19 andDenseNet-121 as fixed feature extractors. In each data-level-ensemble featuresextracted from one of the pre-defined CNN are fed to support vector machine(SVM) classifier, and output from each data-level-ensemble is calculated usingvoting method. Once outputs from the three data-level-ensembles with threedifferent CNN architectures are obtained, then, again, voting method is used tocalculate the final prediction. Our proposed framework is tested on SIIM ACRPneumothorax dataset and Random Sample of NIH Chest X-ray dataset (RS-NIH). Forthe first dataset, 85.17% Recall with 86.0% Area under the Receiver OperatingCharacteristic curve (AUC) is attained. For the second dataset, 90.9% Recallwith 95.0% AUC is achieved with random split of data while 85.45% recall with77.06% AUC is obtained with patient-wise split of data. For RS-NIH, theobtained results are higher as compared to previous results from literatureHowever, for first dataset, direct comparison cannot be made, since thisdataset has not been used earlier for Pneumothorax classification.

A Hybrid VDV Model for Automatic Diagnosis of Pneumothorax using Class-Imbalanced Chest X-rays Dataset