Dr. Saeed Seyyedi is a Data Scientist, AI and Deep Learning Specialist and Research Fellow in the Center for Artificial Intelligence in Medicine & Imaging (AIMI) at Stanford University. Dr. Seyyedi is a computer scientist and biomedical engineer and has specialized in artificial intelligence applications including Deep Learning, Computer Vision and NLP techniques for analysis of multi-modality real world datasets, Generative Adversarial (GAN) models, digital signal and data processing techniques including image classification, segmentation and radiomics, image reconstruction and low-dose imaging.
Dr. Seyyedi received his Master of Science in Biomedical Engineering where he studied techniques for processing and analysis of digital breast tomosynthesis data. He obtained his PhD in Computer Science, Medical Imaging and Informatics from Technical University of Munich in Germany where he was the recipient of an E.U. research fellowship supporting his research and studies in the field of computer science, medical imaging and informatics. During his PhD studies, he was a visiting scholar at Johns Hopkins University where he was involved in development of advanced models for multi-modality imaging problems.
Prior to joining AIMI, he was investigating image and data analysis techniques at Definiens AG - subsidiary of AstraZeneca PLC - where he led multiple projects and collaborations with several academic and industrial research partners focusing on AI based applications for analysis of big medical and biological datasets including digital pathologic and radiologic imaging data. He also worked with the British Columbia Cancer Agency of Canada as a part of PanCan lung cancer screening project where he and his team developed deep learning and radiomics applications for lung cancer detection and classification. At AIMI, he is involved in AI and medical imaging research, particularly in leading projects for development of deep learning and computer vision methods and other tools to detect and characterize cancer on radiologic images. He is an author, reviewer and editorial board member in several journals and conferences and his interdisciplinary research and studies have been supported and recognized by a number of awards and grants.

Honors & Awards

  • Funding for Postdoctoral Research, Stanford University, Stanford, CA (2019)
  • European Union Research Fellowship, Technical University of Munich, Munich, Germany (2014)
  • Grant for COST Training School on Algebraic Reconstruction Methods in Tomography, Technical University of Denmark, Copenhagen, Denmark (2016)
  • Graduate Scholarship for Master Studies, Scientific and Technological Research Council of Turkey (2011)

Boards, Advisory Committees, Professional Organizations

  • Editorial Board Member, Journal of Medical Artificial Intelligence (2019 - Present)
  • Associate Member, American Association for Cancer Research (AACR) (2019 - Present)
  • Fellowship Member, Society of Breast Imaging (SBI) (2019 - Present)
  • Member, Computer Vision Foundation (CVF) (2018 - Present)
  • Member, European Society for Hybrid Molecular and Translational Imaging (ESHI-MT) (2018 - Present)
  • Senior Member, International Association of Computer Science & Information Technology (IACSIT) (2018 - Present)
  • Member, American Association of Physicists in Medicine (AAPM) (2017 - Present)

Professional Education

  • Ph.D., Technical University of Munich, Munich, Germany, Computer Science, Medical Imaging and Informatics (2018)
  • M.Sc., Istanbul Technical University, Istanbul Turkey, Biomedical Engineering (2014)


All Publications

  • Low-Dose CT Perfusion of the Liver Using Reconstruction of Difference IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES Seyyedi, S., Liapi, E., Lasser, T., Ivkov, R., Hatwar, R., Stayman, J. 2018; 2 (3): 205?14


    Liver CT perfusion (CTP) is used in the detection, staging, and treatment response analysis of hepatic diseases. Unfortunately, CTP radiation exposures is significant, limiting more widespread use. Traditional CTP data processing reconstructs individual temporal samples, ignoring a large amount of shared anatomical information between temporal samples, suggesting opportunities for improved data processing. We adopt a prior-image-based reconstruction approach called Reconstruction of Difference (RoD) to enable low-exposure CTP acquisition. RoD differs from many algorithms by directly estimating the attenuation changes between the current patient state and a prior CT volume. We propose to use a high-fidelity unenhanced baseline CT image to integrate prior anatomical knowledge into subsequent data reconstructions. Using simulation studies based on a 4D digital anthropomorphic phantom with realistic time-attenuation curves, we compare RoD with conventional filtered-backprojection, penalized-likelihood estimation, and prior image penalized-likelihood estimation. We evaluate each method in comparisons of reconstructions at individual time points, accuracy of estimated time-attenuation curves, and in an analysis of common perfusion metric maps including hepatic arterial perfusion, hepatic portal perfusion, perfusion index, and time-to-peak. Results suggest that RoD enables significant exposure reductions, outperforming standard and more sophisticated model-based reconstruction, making RoD a potentially important tool to enable low-dose liver CTP.

    View details for DOI 10.1109/TRPMS.2018.2812360

    View details for Web of Science ID 000456149400006

    View details for PubMedID 29785411

    View details for PubMedCentralID PMC5958919

  • Incorporating a Noise Reduction Technique Into X-Ray Tensor Tomography IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING Seyyedi, S., Wieczorek, M., Pfeiffer, F., Lasser, T. 2018; 4 (1): 137?46
  • Six dimensional X-ray Tensor Tomography with a compact laboratory setup APPLIED PHYSICS LETTERS Sharma, Y., Wieczorek, M., Schaff, F., Seyyedi, S., Prade, F., Pfeiffer, F., Lasser, T. 2016; 109 (13)

    View details for DOI 10.1063/1.4963649

    View details for Web of Science ID 000384747900068

  • An Object-Oriented Simulator for 3D Digital Breast Tomosynthesis Imaging System COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE Seyyedi, S., Cengiz, K., Kamasak, M., Yildirim, I. 2013: 250689


    Digital breast tomosynthesis (DBT) is an innovative imaging modality that provides 3D reconstructed images of breast to detect the breast cancer. Projections obtained with an X-ray source moving in a limited angle interval are used to reconstruct 3D image of breast. Several reconstruction algorithms are available for DBT imaging. Filtered back projection algorithm has traditionally been used to reconstruct images from projections. Iterative reconstruction algorithms such as algebraic reconstruction technique (ART) were later developed. Recently, compressed sensing based methods have been proposed in tomosynthesis imaging problem. We have developed an object-oriented simulator for 3D digital breast tomosynthesis (DBT) imaging system using C++ programming language. The simulator is capable of implementing different iterative and compressed sensing based reconstruction methods on 3D digital tomosynthesis data sets and phantom models. A user friendly graphical user interface (GUI) helps users to select and run the desired methods on the designed phantom models or real data sets. The simulator has been tested on a phantom study that simulates breast tomosynthesis imaging problem. Results obtained with various methods including algebraic reconstruction technique (ART) and total variation regularized reconstruction techniques (ART+TV) are presented. Reconstruction results of the methods are compared both visually and quantitatively by evaluating performances of the methods using mean structural similarity (MSSIM) values.

    View details for DOI 10.1155/2013/250689

    View details for Web of Science ID 000327969700001

    View details for PubMedID 24371468

    View details for PubMedCentralID PMC3859269

  • Comparison of Radiomics-based Machine Learning and Deep Learning Image Classification for Sub-cm Lung Nodules IASLC 20th World Conference on Lung Cancer Seyyedi, S., Janzen, I., Khattra, S., Lam, S., MacAulay, C. 2019
  • Evaluation of Low-Dose CT Perfusion for the Liver using Reconstruction of Difference International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine Seyyedi, S., Liapi, E., Lasser, T., Stayman, W. 2017
  • A Regularized X-Ray Tensor Tomography Reconstruction Technique CT Meeting Seyyedi, S., Wieczorek, M., Pfeiffer, F., Lasser, T. 2016
  • COMPONENT-BASED TV REGULARIZATION FOR X-RAY TENSOR TOMOGRAPHY Seyyedi, S., Wieczorek, M., Sharma, Y., Schaff, F., Jud, C., Pfeiffer, F., Lasser, T., IEEE IEEE. 2016: 581?84
  • 3D Digital Breast Tomosynthesis Image Reconstruction Using Anisotropic Total Variation Minimization Seyyedi, S., Yildirim, I., IEEE IEEE. 2014: 6052?55


    This paper presents a compressed sensing based reconstruction method for 3D digital breast tomosynthesis (DBT) imaging. Algebraic reconstruction technique (ART) has been in use in DBT imaging by minimizing the isotropic total variation (TV) of the reconstructed image. The resolution in DBT differs in sagittal and axial directions which should be encountered during the TV minimization. In this study we develop a 3D anisotropic TV (ATV) minimization by considering the different resolutions in different directions. A customized 3D Shepp-logan phantom was generated to mimic a real DBT image by considering the overlapping tissue and directional resolution issues. Results of the ART, ART+3D TV and ART+3D ATV are compared using structural similarity (SSIM) diagram.

    View details for Web of Science ID 000350044706013

    View details for PubMedID 25571377

  • An Object-Oriented Simulator for 3D Digital Breast Tomosynthesis System Seyyedi, S., Cengiz, K., Kamasak, M., Yildirim, I., IEEE IEEE. 2013: 262-+
  • Evaluating the Effect of Acquisition Parameters in Digital Breast Tomosynthesis System with Iterative Reconstruction Methods on Image Quality Seyyedi, S., Yildirim, I., Kamasak, M., IEEE IEEE. 2013
  • 3-D Tomosynthesis Image Reconstruction Using Total Variation Ertas, M., Akan, A., Cengiz, K., Kamasak, M., Seyyedi, S., Yildirim, I., IEEE IEEE. 2012: 1?5

Footer Links:

Stanford Medicine Resources: