T2. Unlike decoder transformers like GPT, BERT is not good at generating text. #RadAIchat

T3. BERT is excellent for the classification of large amounts of text, such as the labeling of radiology reports. doi.org/10.1148/ryai.2… #RadAIchat

T3. BERT can be used to detect names in medical reports, which helps with anonymization. #RadAIchat

T4. Fine-tuning is required if you want to use BERT for specific labels. That is, before using BERT, you must label some data and train the model. #RadAIchat

T4. BERT models can help classify text for common diseases, but will struggle with edge cases. #RadAIChat

T4. Keeping BERT models up to date with the latest clinical guidelines and research requires ongoing maintenance and retraining. #RadAIChat

T5. A great resource for learning about BERT and AI in general is fast.ai by Jeremy Howard. I highly recommend it to anyone starting out in AI (course.fast.ai). #RadAIchat

T5. If you want to understand the transformer architecture better, I recommend "The Illustrated Transformer" by Jay Alammar. jalammar.github.io/illustrated-tr… #RadAIchat

#DeepLearning model highly accurate at classifying cardiac implants chest xrays doi.org/10.1148/ryai.2… Felix Busch Keno Bressem Lisa Adams #CXR #CVRad #DICOM

Felix Busch Hugo Aerts Keno Bressem Lisa Adams present a #DeepLearning model to classify implants on chest xrays doi.org/10.1148/ryai.2… Heart_SCCT #SCCT2024 #CVRad

New article! Read Navigating the European Union Artificial Intelligence Act for Healthcare dlvr.it/TBpgMn in npj Digital Med

An excellent reference point for the key elements of the European Commission's ground breaking #ArtificialInteligence Act and its relevance to healthcare. Don't forget to bookmark this resource too for easy to access references to the relevant chapters. nature.com/articles/s4174…

Chest Radiographs as Biological Clocks: Implications for Risk Stratification and Personalized Care doi.org/10.1148/ryai.2… Lisa Adams Keno Bressem #DeepLearning #AI #MachineLearning

#DeepLearning model highly accurate at classifying cardiac implants chest xrays doi.org/10.1148/ryai.2… Felix Busch Hugo Aerts Keno Bressem #ChestRad #AI #MachineLearning

Exciting news! 🚀 We've just launched our innovative solution to one of the biggest #challenges in medical research: extracting critical information from free-text data using our #LLM-based pipeline! Jakob Nikolas Kather Dykex Matthias Ebert Keno Bressem Heiko Böhme medrxiv.org/content/10.110…