Skip to content
By using Twitter’s services you agree to our Cookies Use. We and our partners operate globally and use cookies, including for analytics, personalisation, and ads.
  • Home Home Home, current page.
  • About

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @
  • Language: English
    • Bahasa Indonesia
    • Bahasa Melayu
    • Català
    • Čeština
    • Dansk
    • Deutsch
    • English UK
    • Español
    • Filipino
    • Français
    • Hrvatski
    • Italiano
    • Magyar
    • Nederlands
    • Norsk
    • Polski
    • Português
    • Română
    • Slovenčina
    • Suomi
    • Svenska
    • Tiếng Việt
    • Türkçe
    • Ελληνικά
    • Български език
    • Русский
    • Српски
    • Українська мова
    • עִבְרִית
    • العربية
    • فارسی
    • मराठी
    • हिन्दी
    • বাংলা
    • ગુજરાતી
    • தமிழ்
    • ಕನ್ನಡ
    • ภาษาไทย
    • 한국어
    • 日本語
    • 简体中文
    • 繁體中文
  • Have an account? Log in
    Have an account?
    · Forgot password?

    New to Twitter?
    Sign up
fchollet's profile
François Chollet
François Chollet
François Chollet
Verified account
@fchollet

Tweets

François CholletVerified account

@fchollet

Deep learning @google. Creator of Keras. Author of 'Deep Learning with Python'. Opinions are my own.

United States
fchollet.com
Joined August 2009

Tweets

  • © 2021 Twitter
  • About
  • Help Center
  • Terms
  • Privacy policy
  • Cookies
  • Ads info
Dismiss
Previous
Next

Go to a person's profile

Saved searches

  • Remove
  • In this conversation
    Verified accountProtected Tweets @
Suggested users
  • Verified accountProtected Tweets @
  • Verified accountProtected Tweets @

Promote this Tweet

Block

  • Tweet with a location

    You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more

    Your lists

    Create a new list


    Under 100 characters, optional

    Privacy

    Copy link to Tweet

    Embed this Tweet

    Embed this Video

    Add this Tweet to your website by copying the code below. Learn more

    Add this video to your website by copying the code below. Learn more

    Hmm, there was a problem reaching the server.

    By embedding Twitter content in your website or app, you are agreeing to the Twitter Developer Agreement and Developer Policy.

    Preview

    Why you're seeing this ad

    Log in to Twitter

    · Forgot password?
    Don't have an account? Sign up »

    Sign up for Twitter

    Not on Twitter? Sign up, tune into the things you care about, and get updates as they happen.

    Sign up
    Have an account? Log in »

    Two-way (sending and receiving) short codes:

    Country Code For customers of
    United States 40404 (any)
    Canada 21212 (any)
    United Kingdom 86444 Vodafone, Orange, 3, O2
    Brazil 40404 Nextel, TIM
    Haiti 40404 Digicel, Voila
    Ireland 51210 Vodafone, O2
    India 53000 Bharti Airtel, Videocon, Reliance
    Indonesia 89887 AXIS, 3, Telkomsel, Indosat, XL Axiata
    Italy 4880804 Wind
    3424486444 Vodafone
    » See SMS short codes for other countries

    Confirmation

     

    Welcome home!

    This timeline is where you’ll spend most of your time, getting instant updates about what matters to you.

    Tweets not working for you?

    Hover over the profile pic and click the Following button to unfollow any account.

    Say a lot with a little

    When you see a Tweet you love, tap the heart — it lets the person who wrote it know you shared the love.

    Spread the word

    The fastest way to share someone else’s Tweet with your followers is with a Retweet. Tap the icon to send it instantly.

    Join the conversation

    Add your thoughts about any Tweet with a Reply. Find a topic you’re passionate about, and jump right in.

    Learn the latest

    Get instant insight into what people are talking about now.

    Get more of what you love

    Follow more accounts to get instant updates about topics you care about.

    Find what's happening

    See the latest conversations about any topic instantly.

    Never miss a Moment

    Catch up instantly on the best stories happening as they unfold.

    François Chollet‏Verified account @fchollet 23 Jan 2020

    Reading CT scans is incredibly hard. I have no doubt that with sufficient training data, deep learning will eventually be better at it than trained specialists.

    10:22 PM - 23 Jan 2020
    • 43 Retweets
    • 246 Likes
    • María J. Díaz Candamio Elif Daneel 🐂 Wear Your Mask Devendra Sethia Bojan Tunguz Jaime Sanchez Ali Syed Halal Trader Michal Belak
    22 replies 43 retweets 246 likes
      1. François Chollet‏Verified account @fchollet 23 Jan 2020

        That is, until the model encounters something it hasn't quite seen before. Hence the need to keep humans in the loop...

        9 replies 14 retweets 141 likes
        Show this thread
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. IlNumeroUno‏ @TheNerazzurro 24 Jan 2020
        Replying to @fchollet

        In my thesis I worked on segmenting both liver & hepatic tumor using NN. It took me weeks to learn how to recognize liver in a CT. On the other hand, a FCN model learned to recognize liver using 30 training images in few seconds 😅

        0 replies 0 retweets 5 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. Lynoure Braakman‏ @Lynoure 24 Jan 2020
        Replying to @fchollet

        The humans reading them currently seem to focus purely on the things they are asked to look for

        4 replies 1 retweet 3 likes
      3. فيصل السالم‏ @falsalem76 24 Jan 2020
        Replying to @Lynoure @fchollet

        فيصل السالم Retweeted فيصل السالم

        ditto.https://twitter.com/falsalem76/status/1220638691313451010 …

        فيصل السالم added,

        فيصل السالم @falsalem76
        Replying to @fchollet
        imagine a 1000-slice scan of the abdomen, for example. Do we really expect the doctor would carefully examine every little corner of every slice? I can envision the following scenario as being the future of AI-diagonistics: a doctor looks at the scan, makes a tentative diagnosis,
        0 replies 0 retweets 2 likes
      4. End of conversation
      1. Alexander Morgan‏ @lexandermorgan 24 Jan 2020
        Replying to @fchollet

        What ground truth do you use to surpass human performance for this specific task?

        2 replies 0 retweets 1 like
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo
      1. New conversation
      2. (((Anthony Samir)))‏ @anthonysamir 24 Jan 2020
        Replying to @fchollet

        I have been reading CT scans for 20 years, wrote several textbooks, and am a professor at a little Boston hospital. I see something I have never seen before *every day*. Replacement is a massive engineering challenge that lacks commercial logic for the foreseeable future.

        4 replies 1 retweet 56 likes
      3. Seth Stafford‏ @seth_stafford 24 Jan 2020
        Replying to @anthonysamir @fchollet

        Do you see potential for "assistive" intelligence in your work? Tech that would highlight interesting spots in a CT scan and let you annotate scans or otherwise "teach" it to recognize things you would want to be sure to notice?

        1 reply 0 retweets 0 likes
      4. Show replies
      1. New conversation
      2. Jonathan Judge‏ @bachlaw 24 Jan 2020
        Replying to @fchollet

        Yes. Or preferably, to give a strong recommendation that can be overruled only with cause.

        1 reply 0 retweets 1 like
      3. “Dr. Modazzle”‏ @LucyModahlMD 25 Jan 2020
        Replying to @bachlaw @fchollet

        That to me is antithetical to good medical practice. We function in a complex environment with lots of nuance. The quickest way to alienate a referrer is to make hard recommendations based on imaging alone.

        0 replies 0 retweets 3 likes
      4. End of conversation
      1. Declan O'Regan‏ @DrDeclanORegan 24 Jan 2020
        Replying to @fchollet

        Agree with the first sentence. A good report answers a clinical question and recommends further management - integrating available multi-modality imaging/clinical information. ML may well have a role but not in the simplistic way you suggest. Join me for a reporting list anytime!

        0 replies 0 retweets 9 likes
        Thanks. Twitter will use this to make your timeline better. Undo
        Undo

    Loading seems to be taking a while.

    Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

      Promoted Tweet

      false

      • © 2021 Twitter
      • About
      • Help Center
      • Terms
      • Privacy policy
      • Cookies
      • Ads info