Top Tweets for #computationalPathology
Call for Abstracts
the 15th World Digital Pathology, Diagnostics & AI UCG Congress & Exhibition,February 01–02, 2027, Dubai, UAE.
Submit Abstract: https://t.co/JYID6rqUSF
WhatsApp : https://t.co/V96gdQV3YA
#DigitalPathology #PathologyAI #AIDiagnostics #ComputationalPathology
🌏 Connect with global experts
🎟️ Secure your place early and join us in shaping the future of pathology.
📩 https://t.co/l1C3pzkDil
#ASDP2026Singapore #DigitalPathology #AI #ComputationalPathology #EarlyBirdRegistration #Pathology
@ACaputoMD @barbamat2 @MattiaBarbares1 @KMirza @drdoubleb @VLimperioMD AI continues to transform #Pathology. This issue includes AI for cervical cancer screening on whole-slide images, advances in long-read sequencing technologies, and novel approaches to molecular pathology. #ArtificialIntelligence applied to #DigitalPath, #ComputationalPathology
💥Excited for the publication: "AI-Powered Spectral Imaging for Virtual Pathology Staining"
🔗https://t.co/rAodowSQda
📌 #DigitalPathology #MedicalImaging #ArtificialIntelligence #ComputationalPathology #DeepLearning #Histopathology #BiomedicalEngineering #ClinicalAI
GLP isn't anti-AI's pro-accountability.
Document your assumptions, monitor performance, and define limitations.
Even good models need governance.
#DigitalPathology #PathologyAI #ComputationalPathology #AIGovernance #GLP
👇Exciting example of how a continuous state composition-based #TertiaryLymphoidStructure (TLS) score can provide more information than the collapsing of #TLS biology into simple “present/absent” dichotomies. 🔬#ComputationalPathology #Biomarkers #CancerImmunology #DeepLearning
1/ Thrilled to share our new paper, out today in @ScienceMagazine! We built a pan-cancer spatial atlas of tertiary lymphoid structures (TLSs) and developed computation and AI frameworks to study TLS biology at scale.
https://t.co/zgcBnnm7Rl
Have you seen our latest #YouTube video?
‘Computational pathology in NSCLC: From biomarker discovery to clinical integration'
Watch now: https://t.co/WxuivTTPkJ
#NSCLC #ComputationalPathology #DigitalPathology #PrecisionOncology #LungCancer
💡 Can #AI read a tissue slide as molecular data, not just an image? New in #FBL on #ComputationalPathology, #DeepLearning & #PrecisionOncology — from morphology to mechanism.
🧠 The latest work from @IEOufficiale by first author Dr. Nicola Fusco and his team is now featured in FBL!
👉: https://t.co/YCFDjl7r7q
#DigitalPathology #TROP2 #CancerResearch #MedicalAI #Grok
The June 2026 issue of #TheJournalOfPathology is online now! https://t.co/gUwPDTs8ex
Explore the latest research in #GutHealth, #LungCancer, #ComputationalPathology #CornealDystrophy and more
Cover image article: https://t.co/NhiCBYGrco
#NSCLC #PathSoc #Pathology #OpenAccess
Your model is only as generalizable as your data.
Cover tissue diversity, device differences,
and staining workflows.
Don’t train for one lab if you’ll deploy across five.
#DigitalPathology #AIValidation #ComputationalPathology
If AI sees patterns we cannot, what makes it clinically trustworthy? 🔬
Many models perform well on curated datasets. Real-world validation is harder.
DigiPath Digest #39. Mar 6, 6 AM EST.
#DigitalPathology #MedicalAI #ComputationalPathology
Links in the comments
Bias often hides in your training data.
Control for scanner type, staining variability,
and the source institution. Robust AI starts with representative input.
#DigitalPathology
#AIValidation
#BiasInAI
#ComputationalPathology
Dear Colleagues, #Pathologists #ComputerScientists, interested in #Digital/#ComputationalPathology, ESDIP needs people in the communication committee. This group is not only dedicated to communication but also to research/education
Please propose yourself: https://t.co/pRLxdcOfqt
Study across 45 institutions shows AI validity in TIL quantification for melanoma. Reproducible with prognostic validity and open-source. @tznaung 👉 https://t.co/CprLGJYH80
#AIinPathology #Melanoma #ComputationalPathology
The journal Radiology: Artificial Intelligence publishes high-quality research on #AI and medical imaging
➡️ https://t.co/RFrCO88d7j
@ESDIPatho #ECDP2025 #Pathology #DigitalPathology #computationalPathology #DeepLearning #Radiomics
Thrilled to share my latest PhD work exploring fundamental questions about the transferability of multiple instance learning models in #computationalpathology, accepted as a spotlight paper to @icmlconf ! Many thanks to @richardjchen @GreatAndrew90 @AI4Pathology and all coauthors
📣 Excited to share our new ICML 2025 Spotlight article, “Do Multiple Instance Learning Models Transfer?” – addressing a foundational question for building robust and generalizable MIL models.
Read the article: https://t.co/bF88UcYJeS
👉Enhanced Performance & Robustness: Pretrained MIL models consistently lead to improved performance even when the pre-training data comes from a different organ, site, disease model than the target task.
👉Aggregation Transfers: Transfer gains come from the MIL aggregation module, not just patch encoders. Resetting attention layers drops performance by 5–8%, showing they encode generalizable pooling logic.
👉Pancancer Generalization: Models pretrained on a more diverse and challenging data (e.g. 108-class pancancer classification task) achieve the stronger overall transfer performance.
👉Robust benefits across patch encoders: Benefits from MIL transfer are consistent across a wide range of patch encoders, from out-of-domain encoders such as ResNet50 pretrained on natural images, to in-domain encoders including Gigapath and UNIv2.
This research highlights supervised pretraining as a highly accessible path to generalizable MIL models, offering a data and compute-efficient route for developing slide level encoders with flexible combination of MIL method and patch encoder.
Congratulations to @Daniel__Shao @GreatAndrew90 @richardjchen and everyone else who contributed.
Stay tuned for an array of pre-trained MIL models ready to transfer to any task! Visit us at @icmlconf.
Check out our latest work on deriving crucial insights for transferability of multiple instance learning (MIL) models in #computationalpathology to be presented in @icmlconf (Spotlight)!
Kudos to @Daniel__Shao who led the study 😎
📣 Excited to share our new ICML 2025 Spotlight article, “Do Multiple Instance Learning Models Transfer?” – addressing a foundational questions for building robust and generalizable MIL models.
Read the article: https://t.co/bF88UcYJeS
👉Enhanced Performance & Robustness: Pretrained MIL models consistently lead to improved performance even when the pre-training data comes from a different organ, site, disease model than the target task.
👉Aggregation Transfers: Transfer gains come from the MIL aggregation module, not just patch encoders. Resetting attention layers drops performance by 5–8%, showing they encode generalizable pooling logic.
👉Pancancer Generalization: Models pretrained on a more diverse and challenging data (e.g. 108-class pancancer classification task) achieve the stronger overall transfer performance.
👉Robust benefits across patch encoders: Benefits from MIL transfer are consistent across a wide range of patch encoders, from out-of-domain encoders such as ResNet50 pretrained on natural images, to in-domain encoders including Gigapath and UNIv2.
This research highlights supervised pretraining as a highly accessible path to generalizable MIL models, offering a data and compute-efficient route for developing slide level encoders with flexible combination of MIL method and patch encoder.
Congratulations to @Daniel__Shao @GreatAndrew90 @richardjchen and everyone else who contributed.
Stay tuned for an array of pre-trained MIL models ready to transfer to any task! Visit us at @icmlconf.
🚨 New paper alert!
Our study in Eur J of Cancer introduces Pathogenomic Fingerprinting—linking tumor morphology to epigenetic states via #AI & #ComputationalPathology in Oral Cancer,
Read here 👉 https://t.co/KxaSnkMMUL
#Cancer #Epigenetics #PrecisionMedicine
Anyone interested in learning more about Computational Pathology? As promised we have organised a course with stellar speakers. Ideal for trainees and pathologists who want to be abreast of the future of pathology: register now as there are limited spaces
https://t.co/q1EoW4cv2D
Astract Submission for #ECDP2025 is NOW OPEN!
Join us in Barcelona for the leading event in #DigitalPathology, #ComputationalPathology, and #GenerativeAI!
New Deadline: February 28 – Don’t miss out!
Submit now: https://t.co/F1SxyFMxSo
Register here: https://t.co/c5BgmgiGfy
CID3
Most Popular Users
Elon Musk 
@elonmusk
240.5M followers
Barack Obama
@barackobama
119.3M followers
Donald J. Trump
@realdonaldtrump
111.7M followers
Cristiano Ronaldo
@cristiano
110.4M followers
Narendra Modi
@narendramodi
107M followers
Rihanna
@rihanna
97.6M followers
NASA
@nasa
92.1M followers
Justin Bieber
@justinbieber
90.9M followers
KATY PERRY
@katyperry
87.5M followers
Taylor Swift
@taylorswift13
81.4M followers
Lady Gaga
@ladygaga
72.9M followers
Kim Kardashian
@kimkardashian
69.7M followers
Virat Kohli
@imvkohli
69.7M followers
YouTube
@youtube
68.7M followers
Bill Gates
@billgates
63.8M followers
The Ellen Show
@theellenshow
62.5M followers
Neymar Jr
@neymarjr
62.4M followers
CNN
@cnn
61.9M followers
X
@x
60.8M followers
Selena Gomez
@selenagomez
60.6M followers