Image from article in Radiology: Artificial Intelligence
Explore approaches to mitigate bias in #AI applications! https://pubs.rsna.org/page/ai/mitigating_bias #DeepLearning #Radiomics #ArtificialIntelligence
Image from article in Radiology: Artificial Intelligence
Check out today's #FreeFriday @radiology-ai.bsky.social article from #PubMedCentral!
Challenges of Implementing Artificial Intelligence–enabled Programs in the Clinical Practice of Radiology
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11427920 #ML #MachineLearning #ArtificialIntelligence
Time to 3D (bio)print with GRACE! @natureportfolio.nature.com
Excited to share a new #3dprinting approach, to automatically create designs and prints that conform to living cells, particles or any object embedded within a printable resin for light based printing.
www.nature.com/articles/s41...
Image from article in Radiology: Artificial Intelligence
The Checklist for AI in Medical Imaging addresses #AI applications that include classification, segmentation, and reconstruction of medical images
https://pubs.rsna.org/page/ai/claim #ML #DeepLearning #Radiomics
Image from article in Radiology: Artificial Intelligence
Unlocking Robust Segmentation: Decoding Domain Randomization for Radiologists https://doi.org/10.1148/ryai.250384 #ICML2025 #MachineLearning #AI
Sedation-Free Pediatric Neuroimaging with Deep Learning-Reconstructed Deep Resolve 3D MR Sequences by Bac Nguyen (Oslo Universitetssykehus, Rikshospitalet, Oslo, Norway). In pediatric neuroimaging, sedation or general anesthesia are often used during MRI exams to help young patients stay still. However, emerging AI-based techniques — such as deep-learning (DL)-based image reconstruction — contribute to faster scans, reducing the need for sedation. Faster scans reduce motion artifacts, improve image quality, and increase the likelihood of successful awake MRI scans. Deep Resolve is currently available for 2D sequences, and has been highly beneficial. Yet, most neuro protocols include both 2D and 3D sequences. The two most commonly used and time-consuming 3D sequences are T1w 3D MPRAGE and T2w 3D SPACE FLAIR. Applying DL-based reconstruction to these 3D sequences holds great promise for cases where patients struggle to tolerate longer scan times. In this article, Bac Nguyen shares early insights using research versions of 3D MPRAGE and 3D FLAIR with Deep Resolve. Please note: These 3D Deep Resolve sequences are currently under development and are not for sale in the U.S. and in other countries. Their future availability cannot be ensured.
Sedation-free Pediatric #MRI is becoming a reality with DL-reconstructed Deep Resolve 3D sequences.
Bac Nguyen (Oslo University Hospital, Norway) shares early insights on Deep Resolve 3D MPRAGE + 3D FLAIR.
🔗 marketing.webassets.siemens-healthineers.com/455f53e40101...
#NeuroSky #RadSky #PedSky
🚀 Just launched: DLinRT.eu – a community-led platform to explore commercial deep learning tools in radiotherapy!
🛠️ First listings are live, tailored for European #radiotherapy.
Launched to reach the #ESTRO2025 community.
Clinics, researchers, vendors: join us!
#DLinRT #deeplearning #medicalphysics
Honored to speak at #ESTRO25 on "Physics-informed neural networks for sCT and beyond" — a still underexplored area in #radiotherapy.
Slides: doi.org/10.5281/zeno...
Hoping this sparks more fusion of data- and physics-driven approaches!
🚀 Just launched: DLinRT.eu – a community-led platform to explore commercial deep learning tools in radiotherapy!
🛠️ First listings are live, tailored for European #radiotherapy.
Launched to reach the #ESTRO2025 community.
Clinics, researchers, vendors: join us!
#DLinRT #deeplearning #medicalphysics
SynthRAD2025 has a website, and we invite you to get ready to participate, check synthrad2025.grand-challenge.org for more details
Science is a process of discovering how our minds work.. of figuring out what we're drawn to.. there are things that if I force myself to read, I don't retain very well. And other things, I read the first word and I'm riveted, and I just soak it up. – Martin Schwartz on the Night Science Podcast
MRI models are truly needed, great to see -> MRISegmenter: A Fully Accurate and Robust Automated Multiorgan and Structure Segmentation Tool for T1-weighted Abdominal MRI, Yan Zhuang et al. 2025-04-23/2 doi.org/10.1148/radi...
@radiology-ai.bsky.social
Submissions are OPEN for #SASHIMI2025 at #MICCAI2025! ✨
sashimiworkshop.org/submission/
There is a clean >2 month-gap until the deadline on June 25th, which is ample time to get your simulation and synthesis papers ready for publication! We are looking forward to meeting you in Daejeon! 🌏
European Commission: European Health and Digital Executive Agency, Analysis on workforce availability, education and training needs for the quality and safety of medical applications involving ionising radiation in the EU – Status and recommendations, 2025, data.europa.eu/doi/10.2925/...
As a spin-off of the #SynthRAD grand challenge, it is a pleasure to present #TrackRAD trackrad2025.grand-challenge.org.
The first challenge for real time tumor tracking for #MRI guided #radiotherapy. The dataset is open since 15-03. Participate for a cash prize and to present @miccai.bsky.social
What a pleasant two days with old and new friends in Utrecht for #DLinRT dlinrt.org. Monday a full educational day and yesterday for a full blown jump. It is impressive to see the step forward in the field of #AI and how they have been declined in #Radiotherapy and even within a national community
Bye Bye X!
‼️We are so excited to announce #SASHIMI2025 at #MICCAI2025 in Daejeon! 🇰🇷 🌏
This year marks a DECADE of Simulation and Synthesis in Medical Imaging! It's never been more exciting to work in this field than now. Important dates and call for papers here: sashimiworkshop.org/call_for_pap...
Great review! Yinghui, W., Haonan, X., Jing, W. et al. Artificial intelligence in four-dimensional #imaging for #motion management in #radiation therapy. Artif Intell Rev 58, 103 (2025). doi.org/10.1007/s104...
Join us for the 2 days educational and scientific workshop on #deeplearning in #radiotherapy
www.linkedin.com/posts/matteo...
Join us for the 2 days educational and scientific workshop on #deeplearning in #radiotherapy
www.linkedin.com/posts/matteo...
Great to be at ISMRM Benelux meeting today @ismrm-benelux.bsky.social. Enjoy the day, looking forward
First post, & first New Year's resolution kept!
I've just left X (read why there, but I guess, if you're here, you have the same issues☹️)
I hope that this space will become, (& remain!) the collegiate space we need to keep up with everyone's work, developments, GOOD news & so on
Happy new year all!
Figure: Randomised controlled trials of artificial intelligence in clinical practice across countries and specialties. Copyright: 2024 The Author(s). Open Access under CC BY-NC-ND 4.0 license
Artificial intelligence (AI) in health care has seen remarkable growth.
What is the potential of AI to improve care management, clinical decision-making efficiency, and more?
📑 Read this Review in The Lancet Digital Health: bit.ly/3DwAJtD
Artificial Intelligence-Empowered Multistep Integrated Radiation Therapy Workflow for Nasopharyngeal Carcinoma doi.org/10.1016/j.ij...
Data, notebooks, and articles associated with the RSNA AI Deep Learning Lab at RSNA 2024 github.com/RSNA/AI-Deep...
Mind-blowing what it has already been demonstrated with physics-informed #deep learning:
UltimateSynth: MRI Physics for Pan-Contrast AI
Rhea Adams, er al. 2024 doi.org/10.1101/2024...
Bioart, courtesy of the NIH. All images are in the public domain and available for download as high-quality SVGs.
bioart.niaid.nih.gov
NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. 1/3
For those of you who like your figures.
