Dose–volume effects link multiple cerebral substructures to cognitive decline. Neurocognitive toxicity reflects distributed network injury beyond the hippocampus.
@ESTRO_RT CNS focus group on @RO_GreenJournal https://t.co/JptGO6G4zu
1/ Tremendous thanks to the patients, coauthors and all who made the EXTEND trial possible. The primary aggregated analysis is now available online @JCO_ASCO with ctDNA correlatives presented synchronously at @ESTRO_RT#ESTRO26
My @ASTRO_org 2026 GU spring refresher extended "long-course" slide deck is available at
https://t.co/HND3LmzgZb
You can also watch the "short-course" 1.5 hour narrated version here:
https://t.co/GpDtfapF4K
@ZilliThomas highlights the progress made with SBRT in mCRPC. The OS benefit in ARTO by @GiulioFrancoli1 is very encouraging. All trials in this setting point in the same direction: benefit on all endpoints! #APCCC26
Check out our amazing meta analysis FIRE-STORM, showing PFS significantly better with DE-RT over 66 Gy in 33 for high grade meningioma. We hope this will help as we prepare to show for over 70 Gy improves control in future trial!!
https://t.co/ji3h0jv2jB
If I had to start over tomorrow with nothing but a laptop and Claude, here’s how I’d build a multi-million dollar business in 90 days.
I'd create a 5-person AI department that works 24/7.
Let me introduce you to the team…
Here is Version 2.0 of when to hold systemic tx during RT. Updated & w 3 additional drug categories (ADCs, CDK4/6 inhibitors, PARPi).
More details on newer drugs in 🧵 below.
Please use this version as reference & thanks for all input/experience crowdsourcing! (1/3)
Claude Cowork complete crash course from zero to expert in 12 minutes.
Installation, automations, connectors, plugins..all of it:
00:00 Intro
01:00 Installation & setup
02:08 Your first task
03:01 Global instructions (most skip this)
04:00 What Cowork can actually access
05:15 Skills feature
06:08 Connectors explained
07:04 Real workflow (Drive + Gmail)
07:46 Claude in Chrome
08:43 Scheduled tasks
09:52 Plugins (why $285B was wiped out)
11:41 Big picture
🚀 20 AI Tools That Make Work 20x Easier
Still doing things the hard way?
You’re already behind
These AI tools can completely change how you work
➡️ Write content in seconds (blogs, emails, posts)
➡️ Design stunning graphics without skills
➡️ Automate repetitive tasks on autopilot
➡️ Turn ideas into videos, slides, and visuals
➡️ Summarize long docs in 1 click
➡️ Transcribe meetings instantly
➡️ Fix grammar and improve writing tone
➡️ Research faster with AI-powered search
Power stack you should know:
➡️ ChatGPT for content + problem solving
➡️ Canva for design
➡️ Zapier for automation
➡️ Notion AI for organization
➡️ Grammarly for writing
➡️ Perplexity AI for research
➡️ Descript + Pictory for video
➡️ Tome for presentations
Reality check 👇
People who use AI will replace people who don’t
You don’t need all 20
You just need 4–5 tools mastered well
Start today
Stay ahead tomorrow
Which one are you using already? 👇
Follow @MeenakshiYACS for more such posts
#AI #Productivity #Automation #ChatGPT #FutureOfWork
BREAKING: MIT just mass released their Al library for free. (Links included)
I went through these and honestly... this is better than most paid courses I've seen.
Here's the full list of books:
Foundations
1. Foundations of Machine Learning Core algorithms explained. Theory meets practice.
2. Understanding Deep Learning Neural networks demystified. Visual explanations included.
3. Machine Learning Systems Production-ready architecture. System design principles.
Advanced Techniques
4. Algorithms for ML Computational thinking simplified. Decision-making frameworks.
5. Deep Learning The definitive textbook. Covers everything deeply.
Reinforcement Learning
6. RL Basics (Sutton & Barto) The classic. Agent training fundamentals.
7. Distributional RL Beyond expected rewards. Advanced theory.
8. Multi-Agent Systems Agents working together. Coordination and competition.
9. Long Game Al Strategic agent design. Future-focused thinking.
Ethics & Probability
10. Fairness in ML Bias detection. Responsible Al practices.
11. Probabilistic ML (Part 1 & 2)
Links: https://t.co/mAcm6ULC6D
Most people pay thousands for bootcamps that teach half of this.
Bookmark it. Start anywhere. Just start.
Repost for others Follow for more insights on Al Agents.
MIT's books on Al
Foundations
1. Foundations of Machine Learning - https://t.co/UifOgQK4dQ
2. Understanding Deep Learning - https://t.co/cgSSJ1U1d6
3. Machine Learning Systems - https://t.co/wKrA6Pyf45
Advanced Techniques
4. Algorithms for ML - https://t.co/2hjtFqUJUz
5. Deep Learning - https://t.co/SqcIe2c7mL
Reinforcement Learning
6. RL Basics (Sutton & Barto) - https://t.co/96zwuZB4ZB
7. Distributional RL - https://t.co/fZ1PW2UJjs
8. Multi-Agent Systems - https://t.co/uUXuOUseJp
9. Long Game Al - https://t.co/GzFQ8Irunw
Ethics & Probability
10. Fairness in ML - https://t.co/PjE4eHZBSY
11. Probabilistic ML (Part 1) - https://t.co/6v4AgT0Esd
12. Probabilistic ML (Part 2) - https://t.co/WICHaw7WXU
Dear MSc or PHD students,
Here are 10 AI Tools for Reading & Understanding Research Papers
1) ChatPDF
Lets you upload a research paper and interact with it like a chatbot. You can ask for summaries, explanations of methods, or clarification of results, making it ideal for quickly grasping key points without reading everything.
2) Humata AI
Analyzes long academic PDFs and allows you to ask detailed questions about specific sections. It’s especially useful for extracting insights and understanding dense or technical documents efficiently.
3) Paper Digest
Generates concise summaries of research papers, highlighting key findings and contributions. It’s a fast way to understand the main points of a paper without reading it fully.
4) Scholarcy
Transforms research papers into structured summaries by extracting key points such as findings, methodology, and limitations. This is particularly useful for literature reviews and quick evaluation of papers.
5) Explainpaper
Allows you to highlight difficult sentences or paragraphs and get simplified explanations instantly, helping you understand challenging academic writing without needing external resources.
6) NotebookLM
Enables you to upload multiple papers and generate summaries, insights, and connections between them. It helps build a deeper understanding across several sources rather than just one paper.
8) Scite
Shows whether a research paper is supported or contradicted by other studies. This helps you evaluate the credibility and reliability of what you’re reading.
9) Semantic Scholar
Highlights key insights, influential citations, and important sections of papers, allowing you to quickly assess relevance and importance without deep reading.
10) Mathpix
Converts complex equations and PDF content into readable and editable formats, making it especially useful for understanding technical or math-heavy research papers.
#EAU26@ChrisSweens1: the field is reaching a consensus in mHSPC.
ADT + ARPI for nearly all patients, then personalize intensification:
• SBRT for low-volume
• Prostate RT in synchronous disease
• Docetaxel if high-volume and chemofit
🕒 The hope for the future: biomarkers to guide therapy, global access, and drug prices coming down so evidence-based care becomes feasible worldwide.
@uroweb@UroToday
Thank you for the inspiration. I’m now going to look at our prospective SBRT data for the functional (continence and erectile) outcome. My guess is that 99% of previously continent and sexually functional men are still “whole” at 6mo.
Only 50% with #TULSA?!?
🚨BREAKING: GOODBYE POWERPOINT forever.
Claude just collapsed 5 hours of presentation building into 100 seconds completely free.
10 prompts to go from completely unprepared to completely untouchable in every meeting:
(Save this before it goes viral):
Continue TKI during RT — or hold?
The ESMO-ESTRO consensus provides practical guidance:
✅ Most high-dose RT → Major adaptation
⚠️ Skin toxicity signal strong with BRAF/MEK
🛑 Clear “Do NOT combine” scenarios defined
Data limited. Decisions must be multidisciplinary.
#RadOnc #ThoracicOncology #MedTwitter @OncoSKY@OncoAlert@oncodaily@OscarTahuahua@myESMO@ESMO_Open@sciqst @MedicalwatchHQ