Technology Detail


The Office of Technology Licensing was established in 1970 to transfer technologies developed at Stanford. Find out more about OTL's history, mission, staff, and statistics.



CheXbert: Radiologist-level Automated Radiology Report Labeler using Deep Learning


Stanford Reference:

20-295


Abstract


The CheXbert labeler accurately detects the presence or absence of 14 common medical conditions in radiology reports, converting unstructured radiology text into a structured format. Previous approaches to report labeling typically rely either on sophisticated engineering based on medical domain knowledge or manual annotations by experts. CheXbert uses a novel approach to medical image report labeling that leverages recent advances in natural language processing. CheXbert is developed using labels provided by both board-certified radiologists and the previous state-of-the-art automatic labeler.
In experiments, CheXbert performed comparably to a radiologist and is able to outperform the previous best automatic labeler with statistical significance, setting a new state-of-the-art for report labeling on one of the largest datasets of chest x-rays. Accurate labeling of radiology text reports can enable high-quality training of AI-based medical imaging interpretation models.

Stage of Development
  • Software has been trained on free text radiology report impressions and can be used to extract conditions from new radiology reports

  • Applications


    • Radiology report labeling of medical conditions from free text radiology reports
    • Aid in development of an automatic chest x-ray imaging model

    Advantages


    • Outperforms the previous best radiology report labelers with statistical significance, achieving the current state-of-the-art
    • Automatic and Accurate
    • Leverages recent advances in natural language processing (NPL)
    • Labeler can utilize both expert annotations and existing labelers’ outputs on radiology reports
    • No manual annotation or fine-tuning required for use with data from a different hospital
    • Unlike previous rules-based report labelers, further fine-tuning and improvement is possible with more data, if available, without coding expertise

    Publications



    Related Web Links



    Innovators & Portfolio



    Date Released

     10/23/2020 12:00
     

    Licensing Contact


    Imelda Oropeza, Senior Licensing Associate
    650-725-9039 (Business)
    Request Info

    04-235 Scintillation Crystal Detection Arrays for Radiation Imaging Devices
    05-051 Scatter Correction Algorithm for X-ray and Volumetric CT
    07-120 Laser-driven deflection structure for charged particle beams

    more technologies »

    Related Keywords


    x-Ray analysis   imaging: x-ray   healthcare: X-Ray   healthcare: Radiology Information Systems   AI: medical imaging