August 28, 2026

The ARISTOTLE proposal to the Federal Ministry of Research, Technology and Space is approved. Over the next 3 years the group will work on it with the Technical University of Munich and the University Hospital of TUM.

August 26, 2026

RSNA published an interview with Soroosh on how cognitive biases mislead radiology language models. Read it

June 9, 2026

The group presented 6 abstracts at Baiosphere Medical 2026 in Erlangen.

"Does safety scale with accuracy? Stress-testing clinical LLMs in radiology", "Multi-step retrieval and reasoning improves radiology question answering with large language models", "Agreeing on the wrong answer: does shared evidence make an LLM panel reliable, or just unanimous?", "The signal is still there: why private chest X-ray models forget how to use it", "Cited but not read: teaching radiology AI to actually use the evidence it shows you", and "Fine-tuning more is not always better: a large-scale label-budget study of chest radiograph model adaptation".

June 8, 2026

Soroosh received an RWTH ERS Start grant for improving the reliability of evidence-aligned LLM-supported radiology.

May 6, 2026

Our commentary "When framing shapes the answer: cognitive bias and large language model reliability in radiology" is published in Radiology: Artificial Intelligence. Read it

April 14, 2026

Soroosh received the 2025 Editor's Recognition Award, with Distinction, from Radiology: Artificial Intelligence.

August 1, 2025

Soroosh has been appointed as an editorial board member of Communications Medicine!

July 1, 2025

Soroosh has been appointed as a trainee editorial board member of Radiology: Artificial Intelligence!

May 26, 2025

I just crossed 1,000 citations on Google Scholar!

Huge thanks to everyone I have collaborated with and learned from along the way, I couldn't have done it without you!

March 1, 2025

Thrilled to announce that I joined the Department of Urology at Stanford University as a Postdoctoral Scholar!

February 1, 2025

Soroosh has been appointed as an editorial board member of European Radiology Experimental!

Section Radiography

January 28, 2025

Soroosh received the 2024 Reviewer of the Year Award from European Radiology Experimental

Official journal of the European Society of Radiology

December 20, 2024

Soroosh officially obtained his doctorate #2

Dr.-Ing. in Computer Science from Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany

November 20, 2024

Soroosh just submitted his 100th journal peer review!

See Web of Science for more!

November 1, 2024

Soroosh will be joining Stanford Medicine as a postdoc!

July 31, 2024

Soroosh officially obtained his 1st doctoral degree

Dr. rer. medic. in Theoretical Medicine from RWTH Aachen University, Germany

July 24, 2024

Editorial comment on our Radiology article by RSNA is available online [Click here]

"Intraindividual Comparison of Different Methods for Automated BPE Assessment at Breast MRI: A Call for Standardization". By: G. Müller-Franzes, F. Khader, S. Tayebi Arasteh, et al. in Radiology

May 10, 2024

Soroosh had the opportunity to present 2 abstracts at the 105. Deutschen Röntgenkongress (105th German X-ray congress) in Wiesbaden, Germany:

"Tapping the Pool of Non-Medical Images for Enhanced AI-Based Chest Radiography Analysis" and "The Future is Collaborative: A Systematic Analysis of Federated Learning and Framework Parameters in the AI-Based Interpretation of Chest Radiographs"

March 14, 2024

Our journal papers 1, 2, 3, 4, and 5 on diagnostic deep learning using chest radiographs are published!

February 21, 2024

Our paper on streamlining clinical studies with LLMs is now published by Nature Communications!

By: S. Tayebi Arasteh, et al. in Nature Communications

February 1, 2024

Soroosh will be presenting the following 2 abstracts on May 10, 2024 at 105. Deutschen Röntgenkongress (105th German X-ray congress) in Wiesbaden, Germany!

"Tapping the Pool of Non-Medical Images for Enhanced AI-Based Chest Radiography Analysis" and "The Future is Collaborative: A Systematic Analysis of Federated Learning and Framework Parameters in the AI-Based Interpretation of Chest Radiographs"

January 17, 2024

Editorial comment on Soroosh's Radiology AI article by RSNA is available online [Click here]

"Securing Collaborative Medical AI by Using Differential Privacy: Domain Transfer for Classification of Chest Radiographs". By: S. Tayebi Arasteh, et al. in Radiology: Artificial Intelligence

December 16, 2023

Final version of the open-source article is now published! [Click here]

"Encrypted federated learning for secure decentralized collaboration in cancer image analysis". By: D. Truhn*, S. Tayebi Arasteh*, et al. in Medical Image Analysis

July 16, 2023

Our publications 1 and 2 on applying DDPMs on medical images are available in Scientific Reports!

Kudos to his colleagues Firas Khader and Gustav Müller-Franzes!

March 21, 2023

Editorial comment on our Radiology article by RSNA is available online [Click here]

"Using Machine Learning to Reduce the Need for Contrast Agents in Breast MRI through Synthetic Images". By: G. Müller-Franzes, L. Huck, S. Tayebi Arasteh, et al. in Radiology

February 1, 2023

Soroosh will be presenting the following 2 abstracts on May 13, 2023 in RÖKO 2023!

"Automatic Evaluation of Chest Radiographs, The Data Source Matters, But How Much Exactly?" and "Training of AI Models Beyond the Local Dataset Using Federated Learning with 695,000 Non-Identically-Labeled Chest Radiographs"

November 29, 2022

RSNA Annual Meeting 2022 in Chicago was amazing!

Soroosh had the opportunity to present his abstract on "Secure Federated Learning for Decentralized Collaboration in Development of AI Models"