Principal Researcher @Microsoft. Ph.D. @WeillCornell. M.Eng. @Cornell. B.S. @Columbia. Machine Learning. Human Physiology. Opinions expressed are my own.
Seattle, WA
Joined December 2008
- Tweets528
- Following1.8K
- Followers489
- Likes3.9K
Dr. Noel Codella, Ph.D. retweeted
We are excited to release the weights of @MSFTResearch's COLIPRI, our 3D vision–language encoder for chest CT scans, on @huggingface🤗
Model: aka.ms/colipri
Demo: aka.ms/colipri-demo
Paper: aka.ms/colipri-paper
Why does COLIPRI matter?
🧵0/12 👇 – at Cambridge, England
Dr. Noel Codella, Ph.D. retweeted
1/🧵 Introducing CancerGUIDE: Cancer Guideline Understanding via Internal Disagreement Estimation. Can LLMs give guideline-concordant cancer treatment advice in data-sparse settings?
🏥Our new framework tests LLMs on guideline adherence in real cancer cases.
👇 #AIinHealthcare
Dr. Noel Codella, Ph.D. retweeted
We have seen many ways that generative AI can transform healthcare but over-stretched health-IT teams can’t deploy new software systems to surface the latest advancements fast enough.
But... what if developers could meet clinicians where they already work today, building, deploying, and testing AI capabilities that address challenging complex clinical tasks in minutes, not months?
Thats why today we’re announcing the launch of Healthcare Agent Orchestrator bringing the latest cutting edge AI into the hands of healthcare users leveraging Azure AI Foundry and surfacing into M365 enterprise software that health systems globally already use and trust - check out this blog to learn more: lnkd.in/gU9W-iVx
Dr. Noel Codella, Ph.D. retweeted
Excited to share our open-source code for cancer survival prediction using radiology (MRI) and pathology (H&E) images - this walkthrough uses our lightweight domain specific multimodal medical imaging embedding models + adapters to produce hazard scores and survival probabilities. Trainable on CPU in minutes!
Details and code: lnkd.in/gGydrAjF
Blog post: lnkd.in/gJg-zwpQ
Dr. Noel Codella, Ph.D. retweeted
Due in part to the large number of runaway takes in medical AI, I'm launching a regular thread to spotlight noteworthy and more leveled research papers in the space and/or related fields with promising applications in healthcare.
RTs appreciated. Let's begin!
Dr. Noel Codella, Ph.D. retweeted
🔥 Our new preprint on biomedical self-supervised learning with images only is out! 🔥
Rᴀᴅ-DINO: Exploring Scalable Medical Image Encoders Beyond Text Supervision
by @MSFTResearch
We show that:
0/3 🧵
Check out our latest research work
"Rad-DINO: Exploring Scalable Medical Image Encoders Beyond Text Supervision"
arxiv.org/pdf/2401.10815.pdf
We investigate whether text supervision (e.g. CLIP) is an essential component for learning rich visual embeddings to encode biomedical images
Dr. Noel Codella, Ph.D. retweeted
Microsoft partnership has been one of OpenAI's secrets to success — we work very closely with Azure to produce AI training & serving infrastructure that can scale to our cutting-edge (& entirely unprecedented!) needs.
Dr. Noel Codella, Ph.D. retweeted
microsoft, and particularly azure, don’t get nearly enough credit for the stuff openai launches. they do an amazing amount of work to make it happen; we are deeply grateful for the partnership. 🙏 they have built by far the best AI infra out there.
Dr. Noel Codella, Ph.D. retweeted
A reminder to all interested in this work. Our work has been accepted by CVPR 2022 and the code has been released at: github.com/microsoft/RegionC…. It achieves the SoTA open vocabulary object detection for novel categories on both CoCo and LVIS, check it out!
RegionCLIP: Region-based Language-Image Pretraining
abs: arxiv.org/abs/2112.09106
When transferring pretrained model to the open-vocabulary object detection task, method outperforms the sota by 3.8 AP50 and 2.2 AP for novel categories on COCO and LVIS datasets
Dr. Noel Codella, Ph.D. retweeted
The wait is over. Meet the black hole at the center of our galaxy.
#OurBlackHole
Dr. Noel Codella, Ph.D. retweeted
#CVPR2022 reviewers: Before entering your paper discussions, check out @Michael_J_Black’s blog post about novelty.
perceiving-systems.blog/en/n…
Dr. Noel Codella, Ph.D. retweeted
Self-Supervised Learning with Swin Transformers
pdf: arxiv.org/pdf/2105.04553.pdf
abs: arxiv.org/abs/2105.04553
github: github.com/SwinTransformer/T…
a self-supervised learning approach called MoBY, with Vision Transformers as its backbone architecture
Dr. Noel Codella, Ph.D. retweeted
After many months of planning and hard work by so many (incl. @hmkyale @Dianaberrent @wade_schulz @CharleszYaleMed @Aaronmring @DaisySMassey @JeffGehlhausen), today, we are launching our research study to understand how vaccination may help improve #longcovid. 🧵 (1/n)
Pls RT🙏🏼
Dr. Noel Codella, Ph.D. retweeted
May is ALS Awareness Month in the US.
There are A LOT of people we need to make aware that it is a 100% fatal disease that kills quickly and can, like cancer, strike anyone.
If we are going to change that patients like me need you.
Here’s my ask: RT. Please. #ItsTime
Dr. Noel Codella, Ph.D. retweeted
CvT: Introducing Convolutions to Vision Transformers
Achieves SotA over other Vision Transformers and ResNets on ImageNet-1k, with fewer parameters and lower FLOPs by adding a hierarchy of Transformers.
abs: arxiv.org/abs/2103.15808
code: github.com/leoxiaobin/CvT
Dr. Noel Codella, Ph.D. retweeted
CvT: Introducing Convolutions to Vision Transformers
deepai.org/publication/cvt-i…
by Haiping Wu et al. including @NoelCodella
#ImageNet #ConvolutionalNeuralNetwork
Dr. Noel Codella, Ph.D. retweeted
I am co-organizing a #CVPR2021 workshop on dynamic neural nets. Call for papers is below, consider submitting! 👇
Dr. Noel Codella, Ph.D. retweeted
Deep Nostalgia is how it begins myheritage.com/deep-nostalgi… nothing fundamentally in way to make this very high fidelity, including interactivity and ability to talk to them
Dr. Noel Codella, Ph.D. retweeted
NEW: Tocilizumab, an anti–interleukin-6 receptor monoclonal antibody, reduces risk of death in patients hospitalized with #COVID19. This drug has been among the most promising and controversial in COVID medicine.
NEWS: #RECOVERYtrial demonstrates that tocilizumab reduces the risk of death in patients hospitalized with #COVID19
Read more ➡️ recoverytrial.net/news/tocil…
@NIHRresearch @The_MRC @OxfordMedSci
Dr. Noel Codella, Ph.D. retweeted
What is the relevance of viral load in #COVID19 disease severity? A very talented @YaleMSTP student @SilvaJ_C found that saliva viral load to be a better predictor of disease than nasopharyngeal viral load. Here is a thread to explain the findings. (1/n)
medrxiv.org/content/10.1101/…
