•  

    SOURCE

    November 2016

    The disease is treatable but only if it is discovered in time.

    Diabetes is no joke, regardless of what Wilford Brimley memes you’ve seen. The disease’s associated foot ulcers can lead to amputation of the limb while diabetic retinopathy (DR) can rob people of their sight. Some 415 million diabetics worldwide are at risk of this visual affliction and many of those living with it in the developing world lack sufficient health care access to treat it. That’s why Google is training its deep learning AI to spot DR before it becomes a problem — and without the help of an on-site doctor.

    Since the disease is most readily diagnosed by examining a picture of the back of the eye, the Google team has spent the past few years developing a dataset of 128,000 individual images, each examined by 3-7 ophthalmologists from a panel of 54. By marking damaged areas of the eye — microaneurysms, hemorrhages and the like — and then feeding that data into a machine learning system, Google managed to build a highly reliable diagnostic tool. When tested with 12,000 images, the system’s diagnosis was “on-par with that of ophthalmologists” according to the Google Research Blog post.

    The team hopes to expand the scope of this system to be able to diagnose the disease from more complex 3D images (those generated from Optical Coherence Tomography) in addition to the conventional 2D fundus photographs that it currently uses. The team is also looking into automating the diagnostic process to better serve patients in remote locations who might otherwise not have access to trained specialists. But first, Google will need to conduct studies using larger clinical groups and, eventually, obtain FDA approval.

     
     

    No comments

    Be the first one to leave a comment.

    Post a Comment


     

     

    Latest Posts

    Latest Video

     
     

    LATEST POSTS

    Chan Zuckerberg Initiative’s AI Acquisition Will Make Science Free for All

    Dr. Priscilla Chan and mark Zuckerberg. Image Credit: Chan Zuckerberg SOURCE IN BRIEF The Chan Zuckerberg initiative has taken a huge first step toward their…

    Scientists create a 3-D bioprinter to print human skin (w/video)

    SOURCE (Nanowerk News) This research has recently been published in the electronic version of the scientific journal Biofabrication (“3D bioprinting of functional human skin: production…

    Single-cell epigenomic variability reveals functional cancer heterogeneity

    Abstract Background Cell-to-cell heterogeneity is a major driver of cancer evolution, progression, and emergence of drug resistance. Epigenomic variation at the single-cell level can rapidly…

    Artificial Intelligence Predicts when heart will Fail

    Image copyrightMRC LMS Image captionThe software creates a virtual heart to predict the risk of death Artificial intelligence can predict when patients with a heart…

    Chinese surgeons use 3D printing in two landmark paediatric heart surgeries

     SOURCE Chinese surgeons have utilised 3D printing technology to perform two different paediatric heart surgeries. The surgeries took place at the Second Xiangya Hospital of Central…

    How Apps are Changing the Medical Field

      Our last article about Catalia Health and the company’s use of social robots to provide a better healthcare experience to patients created a huge…

    IBM Watson finding its way into real-world image interpretation

    Posted by admin / January 23, 2017 / Edit post Photo: Twitter user Deborah DiSanzo SOURCE A large radiology practice in the Miami area is…

    IBM uses Smartphone to to help Diagnose Melanoma

    SOURCE The smartphone is on a collision course with your local dermatologist. IBM researchers have developed a computer system that early research shows is more…