Bettina Baeßler

@EuSoMII Award to the most cited papers in @InsightsImaging and @EurRadiology! Congratulations to the winners 🏆 🏆 @renatocuocolo @pintodrad

Using a convolutional neural network-based image conversion technique significantly improves the reproducibility of radiomic features in hepatocellular carcinomas. (Heejin Lee et al) #EuropeanRadiology 🔗 buff.ly/3PVyxPd

📣 Introducing this exciting new meta-research by Dr. Hameed et al (@MairaHameed_) from @UCLHresearch @DoM_UCL published in #EuropeanRadiology Follow the 🧵 for more insight by Dr. Hameed 1/6

📢 Just out! A leap in object segmentation using pre-trained latent diffusion models! Generate accurate foreground-background models from textual descriptions WITHOUT segmentation labels. 🚀 Surpasses prior methods and nears fully supervised training. 🩺#AIResearch @BorderlessSci

How prevalent is #burnout among #radiology residents and what are the risks? (Ziqi Wan et al.) #EuropeanRadiology Want to read more? Click the link below ⬇️ buff.ly/44MZxFY

Using the @Radiology_AI #CLAIM checklist is a crucial component in ensuring high-quality reporting of AI research in radiology According to the recently published CLAIM citation analysis: 🧵👇

The RQS has undoubtedly had an important role in raising awareness on #radiomics and #MachineLearning research. It's also showing limitations, as seen in the latest @EuSoMII Radiomics Auditing Group paper. Now available on @EurRadiology (#openaccess). doi.org/10.1007/s00330…

The RQS has undoubtedly had an important role in raising awareness on #radiomics and #MachineLearning research. It's also showing limitations, as seen in the latest @EuSoMII Radiomics Auditing Group paper. Now available on @EurRadiology (#openaccess). doi.org/10.1007/s00330…

Clinical Text Summarization: Adapting Large Language Models Can Outperform Human Experts paper page: huggingface.co/papers/2309.07… Sifting through vast textual data and summarizing key information imposes a substantial burden on how clinicians allocate their time. Although large language models (LLMs) have shown immense promise in natural language processing (NLP) tasks, their efficacy across diverse clinical summarization tasks has not yet been rigorously examined. In this work, we employ domain adaptation methods on eight LLMs, spanning six datasets and four distinct summarization tasks: radiology reports, patient questions, progress notes, and doctor-patient dialogue. Our thorough quantitative assessment reveals trade-offs between models and adaptation methods in addition to instances where recent advances in LLMs may not lead to improved results. Further, in a clinical reader study with six physicians, we depict that summaries from the best adapted LLM are preferable to human summaries in terms of completeness and correctness. Our ensuing qualitative analysis delineates mutual challenges faced by both LLMs and human experts. Lastly, we correlate traditional quantitative NLP metrics with reader study scores to enhance our understanding of how these metrics align with physician preferences. Our research marks the first evidence of LLMs outperforming human experts in clinical text summarization across multiple tasks. This implies that integrating LLMs into clinical workflows could alleviate documentation burden, empowering clinicians to focus more on personalized patient care and other irreplaceable human aspects of medicine.