Comment on Breast Cancer

• Johanno@feddit.org ⁨2⁩ ⁨months⁩ ago

  That’s why I hate the term AI. Say it is a predictive llm or a pattern recognition model.

  source

  • PM_ME_VINTAGE_30S@lemmy.sdf.org ⁨2⁩ ⁨months⁩ ago

    Say it is a predictive llm

    According to the paper cited by the article OP posted, there is no LLM in the model. If I read it correctly, the paper says that it uses PyTorch’s implementation of ResNet18, a deep convolutional neural network that isn’t specifically designed to work on text. So this term would be inaccurate.

    or a pattern recognition model.

    Much better term IMO, especially since it uses a convolutional network. But since the article is a news publication, not a serious academic paper, the author knows the term “AI” gets clicks and positive impressions (which is what their job actually is) and we wouldn’t be here talking about it.

    source

    • BeliefPropagator@discuss.tchncs.de ⁨2⁩ ⁨months⁩ ago

      That performance curve seems terrible for any practical use.

      Image

      source

      • loonsun@sh.itjust.works ⁨2⁩ ⁨months⁩ ago

        Yeah that’s an unacceptably low ROC curve for a medical usecase

        source
      • PM_ME_VINTAGE_30S@lemmy.sdf.org ⁨2⁩ ⁨months⁩ ago

        Good catch!

        source
    • FierySpectre@lemmy.world ⁨2⁩ ⁨months⁩ ago

      Well, this is very much an application of AI… Having more examples of recent AI development that aren’t ‘chatgpt’(/transformers-based) is probably a good thing.

      source

      • wewbull@feddit.uk ⁨2⁩ ⁨months⁩ ago

        Op is not saying this isn’t using the techniques associated with the term AI. They’re saying that the term AI is misleading, broad, and generally not desirable in a technical publication.

        source

        • -> View More Comments
  • steventhedev@lemmy.world ⁨2⁩ ⁨months⁩ ago

    The correct term is “Computational Statistics”

    source

    • spechter@lemmy.ml ⁨2⁩ ⁨months⁩ ago

      Stop calling it that, you’re scaring venture capital

      source
  • 0laura@lemmy.world ⁨2⁩ ⁨months⁩ ago

    it’s a good term, it refers to lots of thinks. there are many terms like that.

    source

    • wewbull@feddit.uk ⁨2⁩ ⁨months⁩ ago

      it refers to lots of thinks

      So it’s a bad term.

      source

      • GetOffMyLan@programming.dev ⁨2⁩ ⁨months⁩ ago

        It’s literally the name of the field of study. Chances are this uses the same thing as LLMs. Aka a neutral network, which are some of the oldest AIs around.

        source

        • -> View More Comments
      • 0laura@lemmy.world ⁨2⁩ ⁨months⁩ ago

        the word program refers to even more things and no one says it’s a bad word.

        source
    • Ephera@lemmy.ml ⁨2⁩ ⁨months⁩ ago

      The problem is that it refers to so many and constantly changing things that it doesn’t refer to anything specific in the end. You can replace the word “AI” in any sentence with the word “magic” and it basically says the same thing…

      source
• PM_ME_VINTAGE_30S@lemmy.sdf.org ⁨2⁩ ⁨months⁩ ago

  Haven’t read any article about this specific ‘discovery’ but usually this uses a completely different technique than the AI that comes to mind when people think of AI these days.

  From the conclusion of the actual paper:

  Deep learning models that use full-field mammograms yield substantially improved risk discrimination compared with the Tyrer-Cuzick (version 8) model.

  If I read this paper correctly, the novelty is in the model, which is a deep learning model that works on mammogram images + traditional risk factors.

  source

  • FierySpectre@lemmy.world ⁨2⁩ ⁨months⁩ ago

    For the image-only DL model, we implemented a deep convolutional neural network (ResNet18 [13]) with PyTorch (version 0.31; pytorch.org). Given a 1664 × 2048 pixel view of a breast, the DL model was trained to predict whether or not that breast would develop breast cancer within 5 years.

    The only “innovation” here is feeding full view mammograms to a ResNet18(2016 model). The traditional risk factors regression is nothing special (barely machine learning). They don’t go in depth about how they combine the two for the hybrid model, so it’s probably safe to assume it is something simple (merely combining the results, so nothing special in the training step)

    source

    • errer@lemmy.world ⁨2⁩ ⁨months⁩ ago

      ResNet18 is ancient and tiny…I don’t understand why they didn’t go with a deeper network. ResNet50 is usually the smallest I’ll use.

      source
    • PM_ME_VINTAGE_30S@lemmy.sdf.org ⁨2⁩ ⁨months⁩ ago

      They don’t go in depth about how they combine the two for the hybrid model

      Actually they did, it’s in Appendix E (PDF warning) . A GitHub repo would have been nice, but I think there would be enough info to replicate this if we had the data.

      Yeah it’s not the most interesting paper in the world. But it’s still a cool use IMO even if it might not be novel novel enough to deserve a news article.

      source
  • llothar@lemmy.ml ⁨2⁩ ⁨months⁩ ago

    I skimmed the paper. As you said, they made a ML model that takes images and traditional risk factors (TCv8).

    I would love to see comparison against risk factors + human image evaluation.

    Nevertheless, this is the AI that will really help humanity.

    source