Soroosh Tayebi Arasteh

Dr.-Ing. Dr. rer. medic. Soroosh Tayebi Arasteh

Postdoctoral Researcher

Department of Computer Science
Chair of Computer Science 5 (Pattern Recognition)

Room: Room 10.137
Martensstr. 3
91058 Erlangen

Open Student Positions:

There some open positions. Please check below

Academic CV

  • Since 2024: Postdoctoral Researcher at the Pattern Recognition Lab
  • 2024: Doctor of Theoretical Medicine (Dr. rer. medic.), RWTH Aachen University, Aachen, Germany
  • 2024: Doctor of Engineering (Dr.-Ing.) in Computer Science, FAU Erlangen-Nürnberg, Erlangen, Germany
  • 2021: M.Sc. Thesis in Medical Image and Data Processing, Harvard Medical School, Boston, MA, USA
  • 2021: M.Sc. in Communications and Multimedia Engineering, FAU Erlangen-Nürnberg, Erlangen, Germany
  • 2017: B.Sc. in Electrical Engineering, Bu-Ali Sina University, Hamedan, Iran

Publications

Please visit my website for an up-to-date list of journals.

Selected Journal Publications

Open Student Positions

Current Journal Roles

Editorial Board Member

  • European Radiology Experimental

Peer-Reviewer

Please visit my website for an up-to-date list of journals.

  • Nature Communications
  • npj Digital Medicine
  • Eurosurveillance
  • Medical Image Analysis
  • IEEE Transactions on Medical Imaging
  • View
  • npj Precision Oncology
  • Respirology
  • IEEE Journal of Biomedical and Health Informatics
  • Archives of Computational Methods in Engineering
  • Scientific Data
  • Scientific Reports
  • BMC Medicine
  • Journal of Medical Internet Research
  • Computerized Medical Imaging and Graphics

Talks

Please visit my website for an up-to-date list of talks.

2024

  • S. Tayebi Arasteh, A. Ziller, D. Truhn, G. Kaissis. “Differential Privacy in Large-Scale AI Models: Ensuring Fairness and Diagnostic Accuracy in Medical Imaging.” TPDP 2024 – Theory and Practice of Differential Privacy, Boston, MA, USA, August 2024
  • Keynote Speech. “Encrypted Federated Learning: Next-Level Privacy in Decentralized Collaborative Medical AI.” Pattern Recognition Conference Summer 2024, Obertrum am See, Austria, July 2024
  • S. Tayebi Arasteh, C. Kuhl, D. Truhn, S. Nebelung. “The Future is Collaborative: A Systematic Analysis of Federated Learning and Framework Parameters in the AI-Based Interpretation of Chest Radiographs.” 105. Deutscher Röntgenkongress (105th German X-ray Congress), Wiesbaden, Germany, May 2024
  • S. Tayebi Arasteh, C. Kuhl, S. Nebelung, D. Truhn. “Tapping the Pool of Non-Medical Images for Enhanced AI-Based Chest Radiography Analysis.” 105. Deutscher Röntgenkongress, Wiesbaden, Germany, May 2024

2023

  • G. Mueller-Franzes, S. Tayebi Arasteh, F. Khader, S. Nebelung, C. Kuhl, D. Truhn. “Standardizing Qualitative and Quantitative Breast Parenchymal Enhancement Assessment in Breast MRI.” 109th Radiological Society of North America (RSNA) annual meeting, Chicago, IL, USA, 2023
  • S. Tayebi Arasteh, P. Isfort, C. Kuhl, S. Nebelung, D. Truhn. “Automatic Evaluation of Chest Radiographs – The Data Source Matters, But How Much Exactly?” 104. Deutscher Röntgenkongress, Wiesbaden, Germany, 2023
  • S. Tayebi Arasteh P. Isfort, Marwin Saehn, C. Kuhl, D. Truhn, S. Nebelung. “Training of AI Models Beyond the Local Dataset Using Federated Learning with 695,000 NonIdentically-Labeled Chest Radiographs.” 104. Deutscher Röntgenkongress, Wiesbaden, Germany, May 2023

2022

  • S. Tayebi Arasteh, J.N. Kather, F. Khader, G. Mueller-Franzes, C. Kuhl, P. Isfort, S. Nebelung, P. Bruners, D. Truhn. “Secure Federated Learning for Decentralized Collaboration in Development of AI Models.” 108th RSNA annual meeting, Chicago, IL, USA, Nov-Dec 2022

Lectures

Supervised Student Theses/Projects

Student Title Type Status
Ahmad Hegazy From Prompt to Command: Adaptation of LLMs for Robotic Task Execution in Manufacturing MA thesis running
Shouvik Chattopadhyay Evaluating the Effectiveness of Large Language Models in Named Entity Recognition in Specialized Industrial Domain MA thesis running
Shubham Gupta Vision-Language Models for Pathology Report Generation from Gigapixel Whole-Slide Images MA thesis running
Nitish Joshi Exploring RNN-Transducers for Named Entity Recognition in Biomedical Literature MA thesis running
Parisa Fathian Boroujeni Benchmarking Automatic Speaker Anonymization Methods for Healthy Speech Project running
Behnam Norouzi Online Retrieval Augmented Generation for Accurate Medical Question Answering MA thesis running
Vicky Vicky LLM-Centric Framework for Ontology-Driven SPARQL Query Generation in RAG for DICOM Databases MA thesis running
Mahtab Ranji Differential privacy for securing speech-based deep learning models against gradient inversion attacks Project finished
Nellie Anne Reichmann Differentially Private Federated Learning for Multilabel Classification of Chest Radiographs MA thesis running
Muhammad Shafiq Bin Bazalanul Azam Generation of IEC 61131-3 SFCs conditioned on textual user intents and existing sequences MA thesis finished
Arpita Halder Retrieval Augmented Generation for Medical Question Answering Project running
Ravindu Rathugama Automatic speaker anonymization using diffusion models Project running
Pavan Bolisetty Assessing the Impact of LLMs on Reduction of Supplier-Related Warranty Costs of Siemens Healthineers’ Global Supply Chain MA thesis finished