Kicking off a new season of the @IEEE EMBS “Frontiers of Biomedical Imaging & Analysis” webinar series ✨ 🎙️ Prof. Mattias Paul Heinrich Topic: Implicit Neural Representations (INRs) for MRI reconstruction, shape-informed registration & privacy-preservation 📅 Oct 1, 2025 | 9am ET / 3pm CEST 🔗 us06web.zoom.us/j/8377806733…

🚨 New Paper Alert! 🚀Instead of training a deep network for 𝗺𝗲𝗱𝗶𝗰𝗮𝗹 𝗶𝗺𝗮𝗴𝗲 𝗿𝗲𝗴𝗶𝘀𝘁𝗿𝗮𝘁𝗶𝗼𝗻, authors use 𝘃𝗶𝘀𝗶𝗼𝗻 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹 𝗗𝗜𝗡𝗢𝘃𝟮 to extract features for deformable 3D medical image registration! 🔗ieeexplore.ieee.org/document…

Please join us in welcoming the new leadership of IEEE EMBS TC on Biomedical Imaging & Image Processing (BIIP)! Appointed to leadership is: Chair - Dr. Pingkun Yan of the Rensselaer Polytechnic Institute Vice Chair - Dr. Shuo Li of Case Western Reserve University Curious about BIIP? Visit embs.org/biip/.

Dr. Pingkun Yan has been named as an IEEE EMBS Distinguished Lecturer for 2025/26 @pingkunyan @IEEEembs

Just spent 30 hours reviewing for an NIH study section set for Thurs—now postponed indefinitely. 20 other scientists did the same X multiple sections. Huge waste of time, resources, and funding, with real costs for science and economy. @realDonaldTrump admin is bad for everyone.

We have to take the LLMs to school. When you open any textbook, you'll see three major types of information: 1. Background information / exposition. The meat of the textbook that explains concepts. As you attend over it, your brain is training on that data. This is equivalent to pretraining, where the model is reading the internet and accumulating background knowledge. 2. Worked problems with solutions. These are concrete examples of how an expert solves problems. They are demonstrations to be imitated. This is equivalent to supervised finetuning, where the model is finetuning on "ideal responses" for an Assistant, written by humans. 3. Practice problems. These are prompts to the student, usually without the solution, but always with the final answer. There are usually many, many of these at the end of each chapter. They are prompting the student to learn by trial & error - they have to try a bunch of stuff to get to the right answer. This is equivalent to reinforcement learning. We've subjected LLMs to a ton of 1 and 2, but 3 is a nascent, emerging frontier. When we're creating datasets for LLMs, it's no different from writing textbooks for them, with these 3 types of data. They have to read, and they have to practice.

Announcement: We are pleased to announce the appointment of Professor Ge Wang as the next Editor-in-Chief of IEEE Transactions on Medical Imaging, effective January 1, 2025. Click here to read the full announcement: ieeetmi.org/new-eic

Dr. Faisal Mahmood of Harvard University will present his seminar, "Multimodal, Generative and Agentic AI for Pathology" this Thursday, November 14th at 1pm in the CBIS Auditorium.

Early Access Papers Just Posted: How can pretrained medical Vision-Language Models quickly master the concepts of new diseases? Here is a novel method of Disease-informed Contextual Prompting and Disease Prototype Learning for this task! Read the paper: ieeexplore.ieee.org/document…