Support teaching, research, and patient care.
I am a scientist with a strong academic and technical backgrounds and diverse experiences in signal processing, image processing, and artificial intelligence. I earned my B.Sc. degree in Biomedical Engineering (EE major) in 2012, followed by an M.Sc. in Biomedical Imaging (image/signal processing major) from Åbo Akademi BioImaging Master's Degree Program. Later, I obtained a Ph.D. degree in Medical Physics and Engineering (Machine Learning and Health Sensing Major) from the University of Turku, Finland, in 2018, building a solid foundation in the field of computer science, health technology and medical imaging. I currently serve as an Adjunct Professor of Health AI within the Faculty of Medicine at the University of Turku, Finland. My current research interests encompass a wide range of topics, including generative AI for multi-dimensional medical image data, applied machine learning and deep learning, privacy-preserving ML, and bioinstrumentation. This diverse repertoire enables me to approach projects comprehensively and deliver high-quality results.My career journey has been enriched with valuable roles and positions. Prior to joining Stanford University, I served as a Principal Lecturer in Artificial Intelligence at Turku University of Applied Sciences (TUAS), where I honed my skills in teaching and mentoring. As a Senior Researcher at the University of Turku, I contributed to groundbreaking health sensing and machine learning research projects and explored novel aspects of biosignal processing and medical imaging for a range of applications. Additionally, I had the privilege of working as a Research Scientist at Precordior Oy, where I applied my expertise in health sensing using smartphones. As I continue my journey in the field of biomedical engineering and artificial intelligence, my goal remains to contribute significantly to scientific advancements and to make a positive impact on human health and well-being. I am eager to embrace new challenges, collaborate with exceptional minds, and further my exploration of innovative technologies and methodologies to push the boundaries of scientific understanding.
This project considers Microelectromechanical (MEMS) sensors for head motion tracking in clinical PET/MRI studies.
This project applies generative deep learning for accelerated direct normalization correction for a brain dedicated MR-compatible PET insert which is under the development in MIIL lab.
This project considers using generative deep learning models coupled with attention mechanisms to correct for ring artifacts due to the detector efficiency variations.
This project considers using generative vision transformer GANs for attenuation and scatter correction in brain PET data.
This project considers using context-aware generative deep learning for the generation of cross-tracer synthetic PET images in biochemical recurrent prostate cancer patients.
This project considers using generative models, e.g. cGANs, for denoising non-gated low dose PET as well as dual-gated cardiac PET images. This is a collaboration project with Turku PET Center, Finland.
Dr. Jafaritadi is working on signal processing and machine learning applications in cancer, cardiac, and brain PET imaging. His research focuses on generative AI for image correction, image-to-image translation, and image denoising. He is also interested in working on data- and device-driven motion tracking and correction systems for PET imaging using deep neural networks.