Warning! OUTDATED BROWSER DETECTED!   Please update your browser immediately for a better experience on this website. Learn More
21/xsl/MobileMenu.xsltmobileNave880e1541/WorkArea//http://www.rsna.org/RSNANewsDetailWireframe.aspx?pageid=15319&id=21813&utm_source=Informz&utm_medium=E-Mail&utm_campaign=RSNA+Home+Page&ekfxmen_noscript=1&ekfxmensel=falsefalsetruetruetruefalsefalse10-18.0.0.0730truefalse
  •  
     
  • Artificial Intelligence May Help Diagnose Tuberculosis in Remote Areas



    April 24, 2017

     

    Researchers are training artificial intelligence (AI) models to identify tuberculosis (TB) on chest x-rays, which may help screening and evaluation efforts in TB-prevalent areas with limited access to radiologists, according to a new study in Radiology.

    “An AI solution that could interpret radiographs for presence of TB in a cost-effective way could expand the reach of early identification and treatment in developing nations,” said study co-author Paras Lakhani, MD, from Thomas Jefferson University Hospital (TJUH) in Philadelphia.

    According to the World Health Organization, TB is one of the top 10 causes of death worldwide. In 2016, approximately 10.4 million people fell ill from TB, resulting in 1.8 million deaths. TB can be identified on chest imaging, however TB-prevalent areas typically lack the radiology interpretation expertise needed to screen and diagnose the disease.

    For the study, Dr. Lakhani and his colleague, Baskaran Sundaram, MD, obtained 1,007 x-rays of patients with and without active TB. The cases consisted of multiple chest x-ray datasets from the National Institutes of Health, the Belarus Tuberculosis Portal, and TJUH. The datasets were split into training (68.0 percent), validation (17.1 percent), and test (14.9 percent).

    The cases were used to train two different deep convolutional neural network (DCNN) models – AlexNet and GoogLeNet – which learned from TB-positive and TB-negative x-rays. The models’ accuracy was tested on 150 cases that were excluded from the training and validation datasets.

    The best performing AI model was a combination of the AlexNet and GoogLeNet, with a net accuracy of 96 percent.

    The two DCNN models had disagreement in 13 of the 150 test cases. For these cases, a cardiothoracic radiologist blindly interpreted the images, accurately diagnosing all 13 cases. This workflow had a greater net accuracy of close to 99 percent.

    Dr. Lakhani said that the team plans to further improve the models with more training cases and other deep learning methods.

    “We hope to prospectively apply this in a real world environment,” Dr. Lakhani said. “An AI solution using chest imaging can play a big role in tackling TB.”

     




    Lakhani
    Lakhani

    Lakhani x-ray
    (a) Posteroanterior chest radiograph shows upper lobe opacities with pathologic analysis–proven active TB. (b) Same posteroanterior chest radiograph, with a heat map overlay of one of the strongest activations obtained from the fifth convolutional layer after it was passed through the GoogLeNet-TA classifier. The red and light blue regions in the upper lobes represent areas activated by the deep neural network. The dark purple background represents areas that are not activated. This shows that the network is focusing on parts of the image where the disease is present (both upper lobes).

    Web Extras




    To:
    From:
    Subject:
    Comment:
    Link:
      
  •  
    comments powered by Disqus