Discover and read the best of Twitter Threads about #wsi

Most recents (4)

What are the #histopathology image #WSI patterns associated with gene expression in cancer? Can we discover them with #AI and use them for spatial profiling and #precision medicine?
Our preprint explores limitations & possibilities of #cpath for this.
biorxiv.org/content/10.110… Image
Existing methods aim to predict expression of individual genes from #WSIs but ignore any inter-dependencies in expression across genes. We show that it is typically not possible to predict expression of a single gene due to such codependencies as shown in fig for a group of genes ImageImage
To formalize this, we first used mutual information to identify groups of genes whose expression in breast cancer patients are significantly inter-dependent and form the basis of important cancer and biological pathways and can be used for precision medicine. ImageImage
Read 12 tweets
1/N Zakładając iż #tomaszl jako #ruski #agent działał już w Komisji Likwidacyjnej #WSI @Cenckiewicz to jakie zadania mógł dostać od swojego oficera prowadzącego? Według mnie następujące: 🧵natemat.pl/454804,kim-jes…
2/N Na pewno dostał zadania wejście w środowisko interesujące rosyjskie służby co jak wiemy udało się pod legendą zainteresowań "Żołnierze Wyklęci" Jak dla mnie to mało by dobrze się uplasować i wejść do Komisji Likwidacyjnej więc musiał go ktoś "wprowadzić" Pytanie jest KTO?🧵
3/N Po wejściu w skład KL @Cenckiewicz zapewne następnym zadaniem było pisanie charakterystyk swoich przełożonych i innych członków komisji w tym na pewno likwidacyjnej jak i weryfikacyjnej. czyli @Macierewicz_A @Cenckiewicz Piotr Woyciechowski @PiotrW1966 Bączek Utracki itd 🧵
Read 6 tweets
[1/5] How can we improve pathologist efficiency in screening of normal colon biopsies? Take a look at our new #preprint that tackles this issue using #interpretable #AI 🔬 🚀 @PathLAKE_CoE

medrxiv.org/content/10.110…
@PathLAKE_CoE @jnkath @AI4Pathology @NormanZerbe @anantm @mitkoveta @olkazuraw @GuillaumeJaume @pushpak_pati @jana_lipkova @nadeem_lab [2/5] Our approach, named #IGUANA, uses #pathologist-derived #interpretable features within a geometric learning framework to categorise biopsies as normal or abnormal (containing both non-neoplastic and neoplastic conditions).
[3/5] IGUANA achieves 0.98 AUC-ROC on an internal cohort and 0.97 AUC-ROC on three external cohorts. Our analysis shows that at a high sensitivity threshold of 99%, the proposed model can, on average, reduce the number of normal slides to be reviewed by a pathologist by 55%.
Read 5 tweets
I want to again express my concern to my senators @SenJohnHoeven and @kevincramer about the lack of transparency by the @CDCDirector @CDCInjury in the revising of the #OpioidGuidelines. Great harm has been done to those w #chronicpain in our state. @SanfordHealth 1/
cut all #patients off of #opioids at once due to what administration stated was because of ‘national standard’ (#CDC Guidelines). So many harmed. How are actions like this ok? Three weeks prior to my son being removed from #opioid #pain medications we had met with his 2/
#pain physician & had a long talk about #opioid #pain #medications being best option for him. Removing individuals w #chronicpain from #opioid pain medication was not a decision based on individual care of #patients BUT @SanfordHealth taking care of own needs. Multiple 3/
Read 12 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!