Soroosh Tayebi Arasteh
@tayebiarasteh.bsky.social
Medical AI Researcher | Dr.-Ing., Dr. rer. medic. | @radiology-ai.bsky.social TEB | @europeanradiology.bsky.social EuRadEx Editorial Board
Peer review is one of the core mechanisms that sustains rigor and progress in science, even though much of it happens quietly. In 2025, I did 102 peer reviews across journals in AI and medicine. Sharing a brief year-in-review snapshot of this often unseen but essential work
December 21, 2025 at 1:54 PM
Peer review is one of the core mechanisms that sustains rigor and progress in science, even though much of it happens quietly. In 2025, I did 102 peer reviews across journals in AI and medicine. Sharing a brief year-in-review snapshot of this often unseen but essential work
🚨 Just published in #npj Artificial Intelligence!
💡 Speech data can be as sensitive as images.
✅ We successfully applied DP to DL training on medical speech data
⚖️ Utility tradeoff remains high, but fairness behavior is more complex
🔍 www.nature.com/articles/s44...
💡 Speech data can be as sensitive as images.
✅ We successfully applied DP to DL training on medical speech data
⚖️ Utility tradeoff remains high, but fairness behavior is more complex
🔍 www.nature.com/articles/s44...
Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data - npj Artificial Intelligence
npj Artificial Intelligence - Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data
www.nature.com
November 3, 2025 at 1:02 PM
🚨 Just published in #npj Artificial Intelligence!
💡 Speech data can be as sensitive as images.
✅ We successfully applied DP to DL training on medical speech data
⚖️ Utility tradeoff remains high, but fairness behavior is more complex
🔍 www.nature.com/articles/s44...
💡 Speech data can be as sensitive as images.
✅ We successfully applied DP to DL training on medical speech data
⚖️ Utility tradeoff remains high, but fairness behavior is more complex
🔍 www.nature.com/articles/s44...
📢 New #preprint: Agentic LLMs improve retrieval-based radiology QA
🧠 Our #agentic #RAG framework lets #LLMs iteratively retrieve & synthesize evidence.
✅ 25 models analyzed (500M→670B)
📈 Accuracy ↑ in mid/small models
🤖 Hallucinations ↓ ~9%
📖 arxiv.org/abs/2508.00743
🧠 Our #agentic #RAG framework lets #LLMs iteratively retrieve & synthesize evidence.
✅ 25 models analyzed (500M→670B)
📈 Accuracy ↑ in mid/small models
🤖 Hallucinations ↓ ~9%
📖 arxiv.org/abs/2508.00743
Agentic large language models improve retrieval-based radiology question answering
Clinical decision-making in radiology increasingly benefits from artificial intelligence (AI), particularly through large language models (LLMs). However, traditional retrieval-augmented generation (R...
arxiv.org
September 6, 2025 at 9:45 AM
📢 New #preprint: Agentic LLMs improve retrieval-based radiology QA
🧠 Our #agentic #RAG framework lets #LLMs iteratively retrieve & synthesize evidence.
✅ 25 models analyzed (500M→670B)
📈 Accuracy ↑ in mid/small models
🤖 Hallucinations ↓ ~9%
📖 arxiv.org/abs/2508.00743
🧠 Our #agentic #RAG framework lets #LLMs iteratively retrieve & synthesize evidence.
✅ 25 models analyzed (500M→670B)
📈 Accuracy ↑ in mid/small models
🤖 Hallucinations ↓ ~9%
📖 arxiv.org/abs/2508.00743
Reposted by Soroosh Tayebi Arasteh
#RadioRAG introduces real-time data retrieval to support the accuracy & factuality of LLMs in radiologic diagnosis https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #NLP #Radiopaedia #MachineLearning
September 2, 2025 at 7:15 PM
#RadioRAG introduces real-time data retrieval to support the accuracy & factuality of LLMs in radiologic diagnosis https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #NLP #Radiopaedia #MachineLearning
🚨 Just published in @radiology-ai.bsky.social!
#RadioRAG: Online Retrieval–Augmented Generation for #Radiology QA
💡Goes beyond static #LLMs by integrating live data from #Radiopaedia
🔓Open-source code & datasets!
📖 pubs.rsna.org/doi/10.1148/...
#AI #RAG #ChatGPT #LangChain #Mistral #Llama3
#RadioRAG: Online Retrieval–Augmented Generation for #Radiology QA
💡Goes beyond static #LLMs by integrating live data from #Radiopaedia
🔓Open-source code & datasets!
📖 pubs.rsna.org/doi/10.1148/...
#AI #RAG #ChatGPT #LangChain #Mistral #Llama3
RadioRAG: Online Retrieval–Augmented Generation for Radiology Question Answering | Radiology: Artificial Intelligence
RadioRAG uses online retrieval–augmented generation to potentially improve the accuracy and factuality of large language model–generated responses to case-based radiology questions by incorporating...
pubs.rsna.org
July 26, 2025 at 2:10 PM
🚨 Just published in @radiology-ai.bsky.social!
#RadioRAG: Online Retrieval–Augmented Generation for #Radiology QA
💡Goes beyond static #LLMs by integrating live data from #Radiopaedia
🔓Open-source code & datasets!
📖 pubs.rsna.org/doi/10.1148/...
#AI #RAG #ChatGPT #LangChain #Mistral #Llama3
#RadioRAG: Online Retrieval–Augmented Generation for #Radiology QA
💡Goes beyond static #LLMs by integrating live data from #Radiopaedia
🔓Open-source code & datasets!
📖 pubs.rsna.org/doi/10.1148/...
#AI #RAG #ChatGPT #LangChain #Mistral #Llama3
Reposted by Soroosh Tayebi Arasteh
#RadioRAG introduces real-time data retrieval to support the accuracy & factuality of LLMs in radiologic diagnosis https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #LLMs #NLP #Radiopaedia
July 25, 2025 at 3:15 AM
#RadioRAG introduces real-time data retrieval to support the accuracy & factuality of LLMs in radiologic diagnosis https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #LLMs #NLP #Radiopaedia
Reposted by Soroosh Tayebi Arasteh
#RadioRAG shows potential to improve LLM accuracy in radiology question answering by integrating real-time domain-specific data https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #DeepLearning #NLP #ML
July 24, 2025 at 3:15 AM
#RadioRAG shows potential to improve LLM accuracy in radiology question answering by integrating real-time domain-specific data https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #DeepLearning #NLP #ML
Reposted by Soroosh Tayebi Arasteh
#RadioRAG introduces real-time data retrieval to support the accuracy & factuality of LLMs in radiologic diagnosis https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #OHBM2025 #NeuroRad #brain #radiology
June 26, 2025 at 7:15 PM
#RadioRAG introduces real-time data retrieval to support the accuracy & factuality of LLMs in radiologic diagnosis https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #OHBM2025 #NeuroRad #brain #radiology
Reposted by Soroosh Tayebi Arasteh
RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #ESSR2025 #ESSR25 #MSKRad #radiology
June 22, 2025 at 3:15 AM
RadioRAG: Online Retrieval-augmented Generation for Radiology Question Answering https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #ESSR2025 #ESSR25 #MSKRad #radiology
Reposted by Soroosh Tayebi Arasteh
#LLMs using radiology retrieval-augmented generation (RadioRAG) showed variable performance in answering case-based radiology questions https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #SNMMI25 #NucMed #MolRad #radiology
June 23, 2025 at 3:15 AM
#LLMs using radiology retrieval-augmented generation (RadioRAG) showed variable performance in answering case-based radiology questions https://doi.org/10.1148/ryai.240476 @tayebiarasteh.bsky.social #SNMMI25 #NucMed #MolRad #radiology
Just crossed 1,000 citations on Google Scholar! Huge thanks to everyone I've collaborated with and learned from along the way, couldn’t have done it without you!
scholar.google.com/citations?hl...
scholar.google.com/citations?hl...
May 27, 2025 at 9:09 AM
Just crossed 1,000 citations on Google Scholar! Huge thanks to everyone I've collaborated with and learned from along the way, couldn’t have done it without you!
scholar.google.com/citations?hl...
scholar.google.com/citations?hl...