Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @JeffreyDeFauw
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @JeffreyDeFauw
-
Prikvačeni tweet
Very excited to share https://www.nature.com/articles/s41586-019-1799-6 … where we show an AI system that outperforms specialists at detecting breast cancer during screening in both the UK and US. Joint work with
@GoogleHealth and@CR_UK published in@Nature today!pic.twitter.com/SL6NV6KyuY
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Jeffrey De Fauw proslijedio/la je Tweet
Teaching Deep Unsupervised Learning (2nd edition) at
@UCBerkeley this semester. You can follow along here: https://sites.google.com/view/berkeley-cs294-158-sp20/home … Instructor Team:@peterxichen ,@Aravind7694 ,@hojonathanho , Wilson Yan, Alex Li,@pabbeel YouTube, PDF, and Google Slides for ease of re-usepic.twitter.com/VTvffsEjHf
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Jeffrey De Fauw proslijedio/la je TweetPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Jeffrey De Fauw proslijedio/la je Tweet
We have 2 papers published in
@nature today!
One describes AlphaFold, which uses deep neural networks to predict protein structures with high accuracy. AlphaFold made the most accurate predictions at the 2018 scientific community assessment CASP13. 1/4https://deepmind.com/blog/article/AlphaFold-Using-AI-for-scientific-discovery …Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Jeffrey De Fauw proslijedio/la je Tweet
The fact it generalize in this way has promising implications for the eventual use of such systems in the real world.http://bit.ly/2SOzT2f
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Jeffrey De Fauw proslijedio/la je Tweet
For insights on why the
@nature paper is a step forward, see@JeffreyDeFauw's excellent thread on tuples, delving deep, and all the complexities of this work:https://twitter.com/JeffreyDeFauw/status/1212436262889484288 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Open access link is now available at https://rdcu.be/bZMTy https://twitter.com/JeffreyDeFauw/status/1212436262889484288 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Some slightly less technical summary of our mammography work in our author notes:https://twitter.com/DeepMind/status/1212456994029871104 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Jeffrey De Fauw proslijedio/la je Tweet
In
@nature today, a large UK/US retrospective study of deep learning#AI for improving accuracy of mammography/breast#cancer diagnosis c/w radiologists https://www.nature.com/articles/s41586-019-1799-6 … by@DeepMindAI@google@JeffreyDeFauw and collaborators@NatureNV by@etpisano https://www.nature.com/articles/d41586-019-03822-8 …pic.twitter.com/TLAIcM1n6A
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Even given all these nuances, I’m still convinced that AI will have a strong positive impact on our lives, of which health will be an important aspect. I hope our work can contribute to that in the longer-term! 16/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
In the end, for AI health we need well-designed clinical trials to validate performance but this takes time. Note that these clinical trials _still_ have to think about a very similar (dataset, metric, baseline). 15/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We also show a reader study on the US dataset -- performed by an external research organization, which is specialized to do clinical trials and evaluations. There is plenty more detail that is obfuscated by the technical language of a paper, I’ve tried to uncover some. 14/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Note a subtlety: the radiologists are “gatekeepers” for further investigation. This means that if they don’t follow up, there is no possibility to confirm any malicious mass. We discuss this more in e.g. Extended Data Fig 4. 13/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We can basically compare directly by putting the AI system in the exact same part of the clinical pathway: woman comes for screening, radiologist(s) decide if follow-up is needed vs AI decides if follow-up is needed. It’s similar for the US but we also provide another eval. 12/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
… it’s the result of countless hours of discussions with both ML and clinical collaborators. 3. Baseline performance: for the UK we have the _original_ decisions from the radiologists, together with the results of arbitration if relevant. 11/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
2. Metric: we look at biopsy proven cancer within 39 months (UK) and 27 months (US). We say it’s not cancer when we have at least one follow-up visit confirming this. These definitions are not trivial -- and there is a lot of nuance -- …. 10/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The US dataset represents a different type of screening program (1-2 years screening, single reader). The supplementary data has plenty of tables and statistics to reveal the level of detail that is hidden away. 9/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Concretely about this for our paper: 1. Datasets: the UK dataset (from
@CR_UK) is a representative sample directly from breast screening, we have spent a very large amount of time doing this thoroughly. 8/16Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
… dataset has unreasonable exclusion criteria, dataset is not randomly sampled from a clinical pathway, baseline performance is post-hoc, ground truth for metric is biased, etc. There are loads and, some can be very subtle. 7/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Unfortunately that means to fully understand work in AI health, you need to delve quite deep. Examples of what invalidates the mapping for my interpretation (things I look out for): dataset is artificially constructed (“let’s find 100 examples of cancer”), … 6/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Each of (dataset, metric, baseline) is critical in understanding the actual clinical impact of results. Seemingly small details can completely change the impact to the point where many feel the summary is invalid (will not translate in practice). 5/16
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.