Assoc. Prof. Dr.Ā Baoshun Shi,Ā Yanshan University,Ā China.
Baoshun Shi is an esteemed researcher and academic in medical imaging, specializing in CT/MRI reconstruction, deep dictionary learning, and computational imaging. His academic journey from Yanshan University to his current role as an Associate Professor has been marked by groundbreaking research and mentorship. His work has significantly contributed to medical diagnostics, receiving recognition through prestigious grants and impactful publications. His innovations continue to shape the future of medical imaging technologies.
Profile
Google Scholar
Early Academic Pursuits āØ
Baoshun Shi embarked on his academic journey with a deep fascination for electronic science and technology. His rigorous training at Yanshan University laid a strong foundation for his expertise in imaging sciences. Under the mentorship of Prof. Qiusheng Lian, he pursued both his Masterās and Ph.D. degrees from 2012 to 2017, immersing himself in advanced research on electronic imaging and computational techniques. His early studies revolved around the intricacies of image reconstruction and enhancement, which would later define his contributions to medical imaging and deep learning methodologies.
Professional Endeavors š
After completing his doctorate, Baoshun Shi transitioned into academia as a Lecturer at the School of Information Science and Engineering at Yanshan University in 2017. His passion for research and education quickly propelled him to the position of Associate Professor in 2021. In this role, he has been instrumental in shaping the next generation of scholars while spearheading groundbreaking studies in medical imaging. His dedication to academic excellence is evident in his mentorship and continuous efforts to push the boundaries of imaging technology.
Contributions and Research Focus š
Baoshun Shiās research is centered on revolutionizing medical imaging through advanced computational models. His work spans multiple domains, including CT/MRI reconstruction, medical image analysis, deep dictionary learning, and compressed imaging. He has extensively explored imaging inverse problems, leveraging deep learning and model-driven approaches to enhance diagnostic accuracy and efficiency. His innovative methodologies in sparse-view CT reconstruction and metal artifact reduction have significantly contributed to the evolution of medical imaging solutions, making them more precise and accessible.
Accolades and Recognition š
Recognized for his pioneering work, Baoshun Shi has secured prestigious research grants and accolades. As the Principal Investigator, he has led multiple national and provincial research projects, including grants from the National Natural Science Foundation of China and the Hebei Natural Science Foundation. His projects, focused on deep dictionary learning and unsupervised imaging techniques, have earned him a distinguished reputation in the field of medical imaging. His contributions are acknowledged not only through research funding but also through the impact his findings have had on computational imaging advancements.
Impact and Influence š
Baoshun Shiās research has had far-reaching implications, transforming the landscape of medical imaging and computational diagnostics. His deep-learning-driven approaches have set new benchmarks in image reconstruction, enabling more accurate and efficient analysis of CT and MRI scans. His work has been instrumental in reducing imaging artifacts, improving resolution, and optimizing sparse-view imaging, thereby enhancing diagnostic capabilities. His influence extends beyond research papers, as his findings are being implemented in real-world medical applications, benefiting both practitioners and patients alike.
Legacy and Future Contributions š
As a thought leader in medical imaging and computational science, Baoshun Shi continues to shape the future of imaging technologies. His ongoing research in deep dictionary networks and unsupervised learning models aims to push the boundaries of what is possible in diagnostic imaging. With an unwavering commitment to scientific advancement, he strives to develop cutting-edge solutions that will further enhance medical diagnostics, making them more efficient and accessible. His legacy is one of innovation, mentorship, and transformative contributions to the field of imaging science, paving the way for future breakthroughs.
Publication
- Research advances on dictionary learning models, algorithms and applications ā QS Lian, BS Shi, SZ Chen (2015)
- Constrained phase retrieval: when alternating projection meets regularization ā B Shi, Q Lian, X Huang, N An (2018)
- Deep prior-based sparse representation model for diffraction imaging: A plug-and-play method ā B Shi, Q Lian, H Chang (2020)
- Multiāscale crossāpath concatenation residual network for Poisson denoising ā Y Su, Q Lian, X Zhang, B Shi, X Fan (2019)
- Compressed sensing MRI based on the hybrid regularization by denoising and the epigraph projection ā L Qiusheng, F Xiaoyu, S Baoshun, Z Xiaohua (2020)
- Compressed sensing MRI with phase noise disturbance based on adaptive tight frame and total variation ā F Xiaoyu, L Qiusheng, S Baoshun (2017)
- Provable general bounded denoisers for snapshot compressive imaging with convergence guarantee ā B Shi, Y Wang, D Li (2023)
- FASPR: A fast sparse phase retrieval algorithm via the epigraph concept ā B Shi, S Chen, Y Tian, X Fan, Q Lian (2018)
- PPR: Plug-and-play regularization model for solving nonlinear imaging inverse problems ā B Shi, Q Lian, X Fan (2019)
- Transfer orthogonal sparsifying transform learning for phase retrieval ā Q Lian, B Shi, S Chen (2017)
Conclusion š
Baoshun Shiās contributions to medical imaging and computational diagnostics have been transformative. His expertise in deep learning, imaging inverse problems, and artifact reduction has paved the way for more accurate and efficient diagnostic methods. As he continues to push the boundaries of scientific discovery, his legacy remains one of innovation and impact, ensuring that medical imaging evolves to better serve the healthcare industry and patients worldwide.