Publications and Talks

Publications:

2023:

• T. Tu*, S. Azizi*, D. Driess, M. Schaekermann, M. Amin, P. Chang, A. Carroll, and et al. "Towards generalist biomedical AI." arXiv preprint arXiv:2307.14334 (2023). [*Co-first Author].  [ArXiv]

• S. Azizi*, L. Culp*, J. Freyberg, B. Mustafa, S. Baur, and et al. “Robust and Efficient Medical Imaging with Self-supervision,” Nature Biomedical Engineering, (2022). [*Co-first Author]. [ArXiv][Link]

• K. Singhal, T. Tu, J. Gottweis, R. Sayres, Ellery Wulczyn, L. Hou, K. Clark, S. Azizi*, A. Karthikesalingam*,  V. Natarajan* and et al. "Towards expert-level medical question answering with large language models." arXiv preprint arXiv:2305.09617 (2023). [*Co-senior Author] [ArXiv]

• K. Singhal*, S. Azizi*, T. Tu*, S. Mahdavi, J. Wei, H. W. Chung, and et al. “Large Language Models Encode Clinical Knowledge,” Nature, Vol 620 [*Co-first Author].  [ArXiv][Link]

• S. Azizi, S. Kornblith, C. Saharia, M. Norouzi, and D. J. Fleet. "Synthetic data from diffusion models improves imagenet classification (2023)." arXiv preprint arXiv:2304.08466. [ArXiv]

• I. Ktena, O. Wiles, I. Albuquerque, S. Rebuffi, R Tanno, A. Guha Roy, S. Azizi et al. "Generative models improve fairness of medical classifiers under distribution shifts." arXiv preprint arXiv:2304.09218 (2023). [ArXiv]

• K. Dvijotham, J. Winkens, M. Barsbey, S. Ghaisas, N. Pawlowski, R. Stanforth, P. MacWilliams, Z. Ahmed, S. Azizi, and et al. “Enhancing the reliability and accuracy of AI-enabled diagnosis via complementarity-driven deferral to clinicians (CoDoC),” Nature Medicine 29, 2022. [Link]

• J. D. Krogue, S. Azizi, F. Tan, I. Flament-Auvigne, T. Brown, M. Plass, R. Reihs et al. "Predicting lymph node metastasis from primary tumor histology and clinicopathologic factors in colorectal cancer using deep learning." Nature Communications Medicine 3, no. 1 (2023). [Link]

2022:

• S. F. Zheng, J. E. Nam, E. Dorigatti, B. Bischl, S. Azizi, M. Rezaei, "Joint Debiased Representation and Image Clustering Learning with Self-Supervision", Under Review, September 2022. [ArXiv]

2021:

• A.G. Roy*, J. Ren*, S. Azizi, A. Loh, V. Natarajan, B. Mustafa, N. Pawlowski, B. Lakshminarayanan, J. Winkens, and et al. “Does Your Dermatology Classifier Know What It Doesn’t Know? Detecting the Long-Tail of Unseen Conditions.” Medical Image Analysis Journal, October 2021 [* Co-first Author]. (Impact factor – 13.28) [Link]

• S. Azizi, B. Mustafa, F. Ryan, Z. Beaver, J. Freyberg, J. Deaton, A. Loh, A. Karthikesalingam, S. Kornblith, T. Chen, V. Natarajan, and M. Norouzi, “Big Self-Supervised Models Advance Medical Image Classification,” International Conference on Computer Vision (ICCV), October 2021. [ArXiv] [Oral-Short] [Poster] [Slides] [Blog Post]

• M. Rezaei, F. Soleymani, B. Bischl, and S. Azizi, “Deep Bregman Divergence for Contrastive Learning of Visual Representations,” Under Review, 2021. [ArXiv]

2020:

• Z. Yi, Q. Tang, S. Azizi, D. Jang, and Z. Xu, “Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting,” International Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, June 2020. [PDF] [ArXiv] [Oral-Short] [Code]

2019:

• A. Sedghi, M. Pesteie, G. Javadi, S. Azizi, and et. Al, “Deep Neural Maps for Unsupervised Visualization of High Grade Cancer in Prostate Biopsies,” Journal of Computer Assisted Radiology and Surgery (IJCARS): IPCAI’19 special issue, 2019. (Impact factor – 3.53)

• S. Asgari, S. Azizi, and et. al, “A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbations,” International Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [ArXiv]

• B. Pyman, A. Sedghi, S. Azizi, K. Tyryshkin, N. Renwick, and P. Mousavi, “Exploring microRNA Regulation of Cancer with Context-Aware Deep Cancer Classifier,” In Pacific symposium on Biocomputing (PSB), 2019.

2018:

• S. Azizi, et al., “Investigating deep recurrent neural networks for prostate cancer detection: analysis of temporal enhanced ultrasound,” IEEE Transactions on Medical Imaging (TMI), 2018. (Impact factor – 13.94)

• S. Azizi, et al., “Towards a real-time, open-source system for temporal enhanced ultrasound-guided prostate biopsy,” Journal of Computer Assisted Radiology and Surgery, 2018. (Impact factor – 3.53)

• M. Mohrehkesh, S. Azizi and et al, “Hierarchical watermarking framework based on analysis of local complexity variations”, Multimedia Tools and Applications, 2018. (Impact factor – 2.97)

• S. Azizi, A. Rajaram, and et al., “3D Tissue Mimicking Biophantoms for Ultrasound Imaging: Bioprinting and Image Analysis,” In SPIE Medical Imaging, 2018. [Runner-up for Young Scientist Award] [Link] [Slides]

• S. Azizi, et al., “Learning from noisy label statistics: detecting high grade prostate cancer in ultrasound guided biopsy,” Medical Image Computing and Computer Assisted Interventions (MICCAI), 2018. [Poster]

2017:

• S. Azizi, et al., “Detection and grading of prostate cancer using temporal enhanced ultrasound: combining deep neural networks and tissue mimicking simulations,” Journal of Computer Assisted Radiology and Surgery (IJCARS): MICCAI’16 special issues, 2017. [Winner of Best Paper Award on MICCAI’17] [Link]

• S. Azizi, et al., “Transfer learning from RF to B-mode temporal enhanced ultrasound features for prostate cancer detection,” Journal of Computer Assisted Radiology and Surgery, 2017. (Impact factor – 3.53) [Slides]

• S. Bayat, S. Azizi, et al., “Investigation of physical properties underlying enhanced temporal ultrasound” IEEE Transaction on Ultrasonics, Ferroelectrics, and Frequency Control (UFFC), 2017. (Impact factor – 3.56)

• S. Bayat, F. Imani, C. Gerardo, G. Nir, S. Azizi, and et al., “Tissue mimicking simulations for temporal enhanced ultrasound-based tissue typing,” In SPIE Medical Imaging, 2017.

2013-2016:

• S. Azizi, et al., “Detection of prostate cancer using temporal sequences of ultrasound data: a large clinical feasibility study,” Journal of Computer Assisted Radiology and Surgery: IPCAI’16 special issue, 2016. (Impact factor – 3.53) [Runner-up of the Audience Best Paper Award, IPCAI’16] [Slides] [Poster]

• S. Azizi, et al., “Classifying cancer grades using temporal ultrasound for transrectal prostate biopsy,” Medical Image Computing and Computer Assisted Interventions (MICCAI), 2016. [Top 4% of submissions] [Slides] [Poster] [Youtube]

• S. Azizi, et al., “Ultrasound-based detection of prostate cancer using automatic feature selection with deep belief networks,” Medical Image Computing and Computer Assisted Interventions (MICCAI), 2015. [Poster]

• S. A. Bitaghsir, N. Karimi, S. Azizi and S. Samavi “Stereo image watermarking method based on binocular just noticeable difference,” In conference on Electrical Engineering (ICEE), IEEE, pp. 33-88, 2014.

• S. Azizi, S. Samavi, M. Mohrekesh and S. Shirani, “Cascaded transform space watermarking based on analysis of local entropy variation,” International Conf. on Multimedia and Expo Workshops (ICME), 2013.

• S. Azizi, M. Mohrekesh, S. Samavi, “Hybrid image watermarking using local complexity variations,” conference on Electrical Engineering (ICEE), IEEE, pp. 1-6, 2013.

• M. Mohrekesh, S. Azizi and S. Samavi, “Accelerating GPU implementation of Contourlet transform,” Iranian conference on Machine Vision and Image Processing (MVIP), IEEE, 2013.

• M. Karimi, M. Mohrekesh, S. Azizi and S. Samavi, “Transparent watermarking based on psychovisual properties using neural networks,” Machine Vision and Image Processing (MVIP), IEEE, 2013.

Selected Presentations and Talks:

• Foundation Models for Medical AI, IEEE Biomedical Imaging & Image Processing (BIIP) 2023 [Invited Speaker] [Recording]

• Exploring Foundation Models for Generalist Medical AI, SECAI & CeTI Summer School, Dresden, Germany, 2023. [Keynote Speaker] [Slides]

• Exploring Foundation Models for Generalist Medical AI, Accra, Ghana, Deep Learning Indaba 2023 [Keynote Speaker]

• Exploring Foundation Models for Generalist Medical AI, Switzerland,  AMDL Generative AI 2023 at EPFL  [Keynote Speaker]

• Exploring Foundation Models for Generalist Medical AI, Vancouver, Canada, 10th Workshop on Medical Computer Vision, CVPR 2023 [Keynote Speaker]

• Large Language Models Encode Clinical Knowledge. German Cancer Research Center (DKFZ), Heidelberg, Germany, 2023. [Invited Speaker][Link]

• Advancement and trends in medical image analysis using deep learning. Computer Science Dept., University of Victoria, Canada, 2018. [Invited Speaker] [Slides]

• Ultrasound-based tissue typing techniques. Technical University of Munich (TUM), Computer Science Dept., Munich, Germany, 2017. [Invited Speaker] [Slides]

• Transfer learning from RF to B-mode temporal enhanced ultrasound features for prostate cancer detection. Barcelona, Spain, IPCAI 2017. [Slides]

• Detection of prostate cancer using temporal sequences of ultrasound data: a large clinical feasibility study. Heidelberg, Germany, IPCAI 2016. [Runner-up Audience Best Paper Award] [Slides]

• Classifying cancer grades using temporal ultrasound for transrectal prostate biopsy. Athens, Greece, MICCAI 2016. [Acceptance Rate of Top 4% for Oral Presentation] [Slides] [Youtube]

• Ultrasound-based detection of prostate cancer using automatic feature selection with deep belief networks: a clinical feasibility study. Vancouver General Hospital, Canada, 2015.

• Ultrasound-based detection of prostate cancer using automatic feature selection with deep belief networks. Munich, Germany, 2015.