Krzysztof Geras

@kjgeras

Deep learning researcher. Assistant professor at NYU. Interested in the methodology of machine learning and its applications to healthcare.

New York, NY
Vrijeme pridruživanja: veljača 2012.

Tweetovi

Blokirali ste korisnika/cu @kjgeras

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @kjgeras

  1. Prikvačeni tweet
    17. lis 2019.

    Great news! Our paper "Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening" has been published at ! This marks the end of a 3-year long endeavor, at and , to demonstrate the potential of CNNs on this task. (1/8)

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    3. velj

    Come work with us as an intern on and at ! We have exciting research, a great team, and a very cute dog!

    Poništi
  3. proslijedio/la je Tweet
    29. sij

    fastMRI: A Publicly Available k-Space and DICOM Dataset of Knee MRI Images for Accelerated Image Reconstruction Using .

    Poništi
  4. proslijedio/la je Tweet
    26. sij

    Picard management tip: If you never fail, you aren't going boldly enough.

    Poništi
  5. proslijedio/la je Tweet

    This month in NYU research news you can use: 🔬 How AI can help detect breast cancer 🤤 What sea slugs can teach us about food comas and long-term memory 🧠 Which phone games are actually good for your brain Learn more on this episode of "Brainiacs":

    Poništi
  6. 23. sij
    Prikaži ovu nit
    Poništi
  7. 23. sij

    A very nice video about our work on deep learning for breast cancer screening by and !

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    23. sij

    Announcing new medical imaging dataset for an important clinical use case - and our first for ultrasound/ cardiac echo. Hope this release will help ML researchers engage in medical applications and improve diagnostics for patients worldwide. More to come in 2020 🤖

    Poništi
  9. proslijedio/la je Tweet
    17. sij

    will have a special issue in MELBA (The Journal of Machine Learning for Biomedical Imaging), a new, web-based open-access journal for medical imaging. The best papers of the conference will be invited to submit an extended version of their work there!

    Poništi
  10. proslijedio/la je Tweet
    16. sij

    Cows make milk. They milk themselves. Other cows check the milk (for free). Cows - get this - PAY THE FARMER to take the milk away. Then the farmer (you won't believe this, honestly) sells the milk *back to the cows.*

    Prikaži ovu nit
    Poništi
  11. 2. sij

    Ultimately, we should remember what the final goal of our research is, which is to decrease the effect that breast cancer has on millions of women and their families. We have an obligation to work towards this goal as a team. 10/N

    Prikaži ovu nit
    Poništi
  12. 2. sij

    Finally, breast cancer screening is the first step. There are fascinating challenges ahead: explainability, robustness, utilizing other imaging modalities, longer-term diagnosis, prognosis, discovery of new biomarkers… There is work to be done by many groups for years. 9/N

    Prikaži ovu nit
    Poništi
  13. 2. sij

    Ours and Google’s work on breast cancer screening is just the beginning. We both have shown that there is a potential of using neural networks in this context, but neither of the papers are showing any prospective evaluation in a clinically realistic setting. 8/N

    Prikaži ovu nit
    Poništi
  14. 2. sij

    Our code and the weights of trained networks are publicly available for that reason. I hope that sharing the code will become a standard in the future. I believe that journals, especially the big ones, should require it. 7/N

    Prikaži ovu nit
    Poništi
  15. 2. sij

    The greatest shortcoming of G’s paper is the lack of publicly available code reproducing their results. It’s very hard for anyone to build upon their work without it, especially for smaller groups that could potentially also contribute to the progress of the field. 6/N

    Prikaži ovu nit
    Poništi
  16. 2. sij

    I believe when multiple groups show similar results with similar methods, it’s a good thing. It co-validates our approaches and it’s showing that the toolbox that we use (in this case, deep neural networks) is robust and works in different scenarios. 5/N

    Prikaži ovu nit
    Poništi
  17. 2. sij

    Having said that, the strength of G’s paper is in careful analysis of the results. I appreciate that. We will use some of their ideas for evaluations in future papers. Our paper also has extensive evaluations, but the methods are its more important part. 4/N

    Prikaži ovu nit
    Poništi
  18. 2. sij

    “Novelty” is difficult to quantify. There are already multiple papers that show similar results. Some of them even precede ours. You can find many examples in the “related work” section of our paper or in a review that we wrote around the same time. 3/N

    Prikaži ovu nit
    Poništi
  19. 2. sij

    First of all, I would like to congratulate the authors of that paper for its acceptance and the attention it got. Overall, I think it’s an excellent paper. 2/N

    Prikaži ovu nit
    Poništi
  20. 2. sij

    Today there was a lot of discussion regarding the novelty of Google’s new paper on using AI for breast cancer screening in comparison to our earlier work (in the tweet below). Let me offer my take on this. 1/N

    Prikaži ovu nit
    Poništi
  21. proslijedio/la je Tweet
    19. pro 2019.

    Decisions released 🎉 Congratulations to accepted papers; to those who we could not accommodate, we wish you success in your ongoing research. See our blog for the first of our reflections. See you soon in Ethiopia. 🇪🇹🌍

    Poništi

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.

    Možda bi vam se svidjelo i ovo:

    ·