Simeng Zhu (@simengzhumd) 's Twitter Profile
Simeng Zhu

@simengzhumd

Radiation oncologist @OSUCCC_James. Medical AI reseacher.

ID: 814846321588924416

calendar_today30-12-2016 14:51:16

76 Tweet

263 Followers

606 Following

Raj Singh, MD (@raj_singh_md) 's Twitter Profile Photo

Excellent start today ⁦SNO⁩ with great talk by ⁦Joshua D. Palmer, MD⁩ on use of DOTATATE PET as a biomarker for response for meningiomas, improve RT target delineation, and optimize pt selection for surveillance ⁦OhioStateRadOnc⁩ ⁦⁦⁦The James at Ohio State

Excellent start today ⁦<a href="/NeuroOnc/">SNO</a>⁩ with great talk by ⁦<a href="/joshuapalmermd/">Joshua D. Palmer, MD</a>⁩ on use of DOTATATE PET as a biomarker for response for meningiomas, improve RT target delineation, and optimize pt selection for surveillance ⁦<a href="/OhioStateRadOnc/">OhioStateRadOnc</a>⁩ ⁦⁦⁦<a href="/OSUCCC_James/">The James at Ohio State</a>⁩
The James (@osuccc_james) 's Twitter Profile Photo

It's a great day for #cancer care in Columbus, where we've cut the ribbon on our proton therapy center at The James Outpatient Care. The state-of-the-art center brings effective, precision proton therapy to adult and pediatric cancer patients from The James and Nationwide Children's Hospital.

Lea Alhilali, MD (@teachplaygrub) 's Twitter Profile Photo

1/Does PTERYGOPALATINE FOSSA anatomy feel as confusing as its spelling? Does it seem to have as many openings as letters in its name? Are you pterrified of the pterygopalatine fossa (PPF)? Let this thread on PPF anatomy help you out!

1/Does PTERYGOPALATINE FOSSA anatomy feel as confusing as its spelling? 

Does it seem to have as many openings as letters in its name?

Are you pterrified of the pterygopalatine fossa (PPF)?

Let this thread on PPF anatomy help you out!
Joshua D. Palmer, MD (@joshuapalmermd) 's Twitter Profile Photo

Excited to see our 🔥 review challenging the dogma for treating brain metastasis. I hope to see more connectomics guided and memory avoiding treatments for our patients. academic.oup.com/neuro-oncology….

Susannah Ellsworth (@free_radical28) 's Twitter Profile Photo

Root causes of potato quality CTs in #radonc treatment planning: a thread about some things I've learned about optimizing simulation scans (with apologies to diagnostic radiologists everywhere).

Lea Alhilali, MD (@teachplaygrub) 's Twitter Profile Photo

1/Have some confusion about tumor perfusion? Do you go into a coma looking at scans for glioma? Never fear! Read on for this month's @theAJNR SCANtastic for what you need to know on the latest in brain tumor imaging! ajnr.org/content/45/4/4…

1/Have some confusion about tumor perfusion?

Do you go into a coma looking at scans for glioma?

Never fear! 

Read on for this month's @theAJNR SCANtastic for what you need to know on the latest in brain tumor imaging!

ajnr.org/content/45/4/4…
Lea Alhilali, MD (@teachplaygrub) 's Twitter Profile Photo

Tired of stressing whether a brain tumor is progressing? Wish you had some insurance about calling tumor recurrence? Here’s the cheat sheet you NEED for the best signs of tumor progression! Read on for the newest @theAJNR SCANtastic on tumor imaging: ajnr.org/content/45/4/4…

Tired of stressing whether a brain tumor is progressing?

Wish you had some insurance about calling tumor recurrence?

Here’s the cheat sheet you NEED for the best signs of tumor progression!

Read on for the newest @theAJNR SCANtastic on tumor imaging:

ajnr.org/content/45/4/4…
darren (@darrenangle) 's Twitter Profile Photo

why would I use a 200MB classifier when I can use a 40GB LLM named psiball-orpo-qdora-the-xplora-70B-int4-swiffer-sweeper-slerp-v0.02-(Taylor's version)

Gabriele Berton (@gabriberton) 's Twitter Profile Photo

This simple pytorch trick will cut in half your GPU memory use / double your batch size (for real). Instead of adding losses and then computing backward, it's better to compute the backward on each loss (which frees the computational graph). Results will be exactly identical

This simple pytorch trick will cut in half your GPU memory use / double your batch size (for real). Instead of adding losses and then computing backward, it's better to compute the backward on each loss (which frees the computational graph). Results will be exactly identical
TimDarcet (@timdarcet) 's Twitter Profile Photo

Bonus trick: you can remove the gradient reduction of the first backward (which is useless) by wrapping in no_sync() Remember to also include the forward pass in the no_sync context, else it does not work

Bonus trick: you can remove the gradient reduction of the first backward (which is useless) by wrapping in no_sync()

Remember to also include the forward pass in the no_sync context, else it does not work
Hamel Husain (@hamelhusain) 's Twitter Profile Photo

LLM bullshit knife, to cut through bs RAG -> Provide relevant context Agentic -> Function calls that work CoT -> Prompt model to think/plan FewShot -> Add examples PromptEng -> Someone w/good written comm skills. Prompt Optimizer -> For

Raj Singh, MD (@raj_singh_md) 's Twitter Profile Photo

Great time at brain mets PRO ⁦⁦⁦ASTRO⁩ w/ ⁦Stuart Burri, M.D.⁩ and ⁦William Breen⁩, reviewing prevention/diagnosis/management of radionecrosis and ⁦⁦OhioStateRadOnc experience w/ Boswellia! Thanks to⁩ ⁦Beant Gill⁩ and Avani Rao for organizing!

Great time at brain mets PRO  ⁦⁦⁦<a href="/ASTRO_org/">ASTRO</a>⁩ w/ ⁦<a href="/stuxrt/">Stuart Burri, M.D.</a>⁩ and ⁦<a href="/wgbreen/">William Breen</a>⁩, reviewing prevention/diagnosis/management of radionecrosis and ⁦⁦<a href="/OhioStateRadOnc/">OhioStateRadOnc</a> experience w/ Boswellia! Thanks to⁩ ⁦<a href="/BeantGill118/">Beant Gill</a>⁩ and Avani Rao for organizing!
The Nobel Prize (@nobelprize) 's Twitter Profile Photo

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”