Dr. Sadegh Mohammadi
Head of Computer Vision and Sound Analysis
Greetings! Welcome to my personal website. I'm Sadegh Mohammadi, leading the Computer Vision and Sound Analysis team at Bayer Pharmaceutical Company. It's my pleasure to invite you on my journey through cutting-edge Artificial Intelligence (AI) and biomedical research that has the potential to transform the healthcare landscape.
​
Join me as I navigate the fascinating intersection of technology and healthcare, crafting innovative solutions that have the power to transform patient care and outcomes.
Let's embark together on this exciting adventure of discovery and innovation!
Links: Email | Linkedin | Google Scholar

Research Interest
My research lies at the intersection of Medical Imaging, Computer Vision, and Sound Analysis, where I am driven by a passion for developing innovative solutions to transform healthcare. A core area of focus is Generative AI for Medical Imaging, where I work on generating high-quality Synthetic Medical Imaging to tackle challenges like data scarcity and privacy concerns.
​
Beyond visual data, my research extends into Sound Analysis, particularly the extraction of voice biomarkers from patient-collected sound data. By analyzing acoustic patterns, I aim to uncover potential indicators of medical conditions, offering a non-invasive and accessible diagnostic tool.
These interdisciplinary endeavors are united by a common goal: to push the frontiers of AI-driven healthcare solutions, enhance patient care, and accelerate the drug development process.
News
-
Jan. 2025: Featured in Innovation Powered by People Series, "Future of Generative AI in Medical Imaging"
-
Jan 2025: Paper Accepted at ICASSP-Workshop-2025: "Investigating the Effect of Diffusion-based Conditional Generative based Speech Models Used for Speech Enhancement Dysarthric Speech"
-
Dec. 2024: Published a blog and infographic titled "Synthetic Data in Medical Imaging"
-
Nov. 2024: Panelist @ DACH CDO Network
-
Oct 2024: Presenter @ BiotechX 2024 title"Synthetic Data for Medical Imaging"
-
Sep 2024: Paper Accepted at MDPI-Sensors: "Fused Audio Instance and Representation for Respiratory Disease Detection"
-
Sep 2024: Paper Submitted to ICLR-2025: "DiNO-Diffusion. Scaling Medical Diffusion via Self-Supervised Pre-Training"​
-
July 2024: Paper Accepted at MDPI-Diagnostics: Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology
-
July 2024: Paper Accepted at MICCAI 2024: Panoptic Segmentation of Mammograms with Text-to-Image Diffusion Model