• mustbe3to20signs@feddit.org
    link
    fedilink
    English
    arrow-up
    34
    arrow-down
    5
    ·
    1 month ago

    AI models can outmatch most oncologists and radiologists in recognition of early tumor stages in MRI and CT scans.
    Further developing this strength could lead to earlier diagnosis with less-invasive methods saving not only countless live and prolonging the remaining quality life time for the individual but also save a shit ton of money.

    • T156@lemmy.world
      link
      fedilink
      English
      arrow-up
      37
      arrow-down
      3
      ·
      1 month ago

      That is a different kind of machine learning model, though.

      You can’t just plug in your pathology images into their multimodal generative models, and expect it to pop out something usable.

      And those image recognition models aren’t something OpenAI is currently working on, iirc.

      • mustbe3to20signs@feddit.org
        link
        fedilink
        English
        arrow-up
        21
        arrow-down
        3
        ·
        1 month ago

        I’m fully aware that those are different machine learning models but instead of focussing on LLMs with only limited use for mankind, advancing on Image Recognition models would have been much better.

        • Grandwolf319@sh.itjust.works
          link
          fedilink
          English
          arrow-up
          6
          ·
          1 month ago

          I agree but I also like to point out that the AI craze started with LLMs and those MLs have been around before OpenAI.

          So if openAI never released chat GPT, it wouldn’t have become synonymous with crypto in terms of false promises.

      • Grandwolf319@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        3
        ·
        1 month ago

        Not only that, image analysis and statistical guesses have always been around and do not need ML to work. It’s just one more tool in the toolbox.

      • TFO Winder@lemmy.ml
        link
        fedilink
        English
        arrow-up
        6
        arrow-down
        4
        ·
        1 month ago

        Don’t know about image recognition but they released DALL-E , which is image generating and in painting model.

      • Petter1@lemm.ee
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        1 month ago

        Fun thing is, most of the things AI can, they never planned it to be able to do it. All they tried to achieve was auto completion tool.

    • msage@programming.dev
      link
      fedilink
      English
      arrow-up
      14
      ·
      1 month ago

      Wasn’t it proven that AI was having amazing results, because it noticed the cancer screens had doctors signature at the bottom? Or did they make another run with signatures hidden?

      • mustbe3to20signs@feddit.org
        link
        fedilink
        English
        arrow-up
        10
        ·
        edit-2
        1 month ago

        There were more than one system proven to “cheat” through biased training materials. One model used to tell duck and chicken apart because it was trained with pictures of ducks in the water and chicken on a sandy ground, if I remember correctly.
        Since multiple medical image recognition systems are in development, I can’t imagine they’re all this faulty trained with unsuitable materials.

        • msage@programming.dev
          link
          fedilink
          English
          arrow-up
          6
          ·
          1 month ago

          They are not ‘faulty’, they have been fed wrong training data.

          This is the most important aspect of any AI - it’s only as good as the training dataset is. If you don’t know the dataset, you know nothing about the AI.

          That’s why every claim of ‘super efficient AI’ need to be investigated deeper. But that goes against line-goes-up principle. So don’t expect that to happen a lot.