Dr. Shiyu Xu Profile

Dr. Shiyu Xu

Principal algorithm engineer at reflexion medical

SPIE Involvement:

Author

Publications (11)

Proceedings Article | 18 March 2019 Paper

Cell nuclei segmentation in divergent images using deep learning and stochastic processing

Qing Wu, Shiyu Xu, Hui Zhang, Xuyang Shi

Proceedings Volume 10956, 1095616 (2019) https://doi.org/10.1117/12.2513105

KEYWORDS: Image segmentation, Stochastic processes, Image processing, Neural networks, Image resolution, Machine learning, Data processing, Biomedical engineering, Microscopes, Image processing algorithms and systems

Read Abstract +

Proceedings Article | 9 March 2018 Paper

Deep residual learning enabled metal artifact reduction in CT

Shiyu Xu, Hao Dang

Proceedings Volume 10573, 105733O (2018) https://doi.org/10.1117/12.2293945

KEYWORDS: Metals, Computed tomography, Convolutional neural networks, X-rays, Reconstruction algorithms

Read Abstract +

Proceedings Article | 9 March 2017 Presentation + Paper

Deformable known component model-based reconstruction for coronary CT angiography

X. Zhang, S. Tilley, S. Xu, A. Mathews, E. McVeigh, J. Stayman

Proceedings Volume 10132, 1013213 (2017) https://doi.org/10.1117/12.2255303

KEYWORDS: Metals, Lead, Model-based design, Arteries, CT reconstruction, Electrodes, Heart, Signal attenuation, Optical spheres, X-rays, Copper

Read Abstract +

Proceedings Article | 9 March 2017 Presentation + Paper

Polyenergetic known-component reconstruction without prior shape models

C. Zhang, W. Zbijewski, X. Zhang, S. Xu, J. Stayman

Proceedings Volume 10132, 101320O (2017) https://doi.org/10.1117/12.2255542

KEYWORDS: Spectral models, Image segmentation, Metals, CT reconstruction, Data modeling, Model-based design, Scanners, Signal attenuation, Prototyping

Read Abstract +

Purpose: Previous work has demonstrated that structural models of surgical tools and implants can be integrated into model-based CT reconstruction to greatly reduce metal artifacts and improve image quality. This work extends a polyenergetic formulation of known-component reconstruction (Poly-KCR) by removing the requirement that a physical model (e.g. CAD drawing) be known a priori, permitting much more widespread application. Methods: We adopt a single-threshold segmentation technique with the help of morphological structuring elements to build a shape model of metal components in a patient scan based on initial filtered-backprojection (FBP) reconstruction. This shape model is used as an input to Poly-KCR, a formulation of known-component reconstruction that does not require a prior knowledge of beam quality or component material composition. An investigation of performance as a function of segmentation thresholds is performed in simulation studies, and qualitative comparisons to Poly-KCR with an a priori shape model are made using physical CBCT data of an implanted cadaver and in patient data from a prototype extremities scanner. Results: We find that model-free Poly-KCR (MF-Poly-KCR) provides much better image quality compared to conventional reconstruction techniques (e.g. FBP). Moreover, the performance closely approximates that of Poly- KCR with an a prior shape model. In simulation studies, we find that imaging performance generally follows segmentation accuracy with slight under- or over-estimation based on the shape of the implant. In both simulation and physical data studies we find that the proposed approach can remove most of the blooming and streak artifacts around the component permitting visualization of the surrounding soft-tissues. Conclusion: This work shows that it is possible to perform known-component reconstruction without prior knowledge of the known component. In conjunction with the Poly-KCR technique that does not require knowledge of beam quality or material composition, very little needs to be known about the metal implant and system beforehand. These generalizations will allow more widespread application of KCR techniques in real patient studies where the information of surgical tools and implants is limited or not available.

Proceedings Article | 18 March 2015 Paper

Distance driven back projection image reconstruction in digital tomosysthesis

Nuhad Malalla, Shiyu Xu, Ying Chen

Proceedings Volume 9412, 94125B (2015) https://doi.org/10.1117/12.2082158

KEYWORDS: Sensors, Image restoration, Computer simulations, Reconstruction algorithms, Breast, Image sensors, X-rays, Convolution, Expectation maximization algorithms, Digital breast tomosynthesis

Read Abstract +

Proceedings Article | 18 March 2015 Paper

Limited angle C-arm tomosynthesis reconstruction algorithms

Nuhad Malalla, Shiyu Xu, Ying Chen

Proceedings Volume 9412, 94123U (2015) https://doi.org/10.1117/12.2081699

KEYWORDS: Reconstruction algorithms, Expectation maximization algorithms, Sensors, 3D image processing, Computer simulations, Spherical lenses, X-rays, X-ray imaging, 3D image reconstruction, Imaging systems

Read Abstract +

Proceedings Article | 19 March 2014 Paper

Statistical iterative reconstruction using fast optimization transfer algorithm with successively increasing factor in Digital Breast Tomosynthesis

Shiyu Xu, Zhenxi Zhang, Ying Chen

Proceedings Volume 9033, 90335C (2014) https://doi.org/10.1117/12.2043815

KEYWORDS: Reconstruction algorithms, Digital breast tomosynthesis, Optimization (mathematics), Computing systems, Expectation maximization algorithms, Systems modeling, Statistical modeling, Tomography, X-rays, Statistical analysis

Read Abstract +

Proceedings Article | 19 March 2014 Paper

Pre-computed backprojection based penalized-likelihood (PPL) reconstruction with an edge-preserved regularizer for stationary Digital Breast Tomosynthesis

Shiyu Xu, Christy Inscoe, Jianping Lu, Otto Zhou, Ying Chen

Proceedings Volume 9033, 903359 (2014) https://doi.org/10.1117/12.2043772

KEYWORDS: X-rays, Digital breast tomosynthesis, 3D acquisition, 3D image processing, Denoising, X-ray detectors, Image resolution, Image quality, Modulation transfer functions, Iterative methods

Read Abstract +

SPIE Journal Paper | 6 February 2014

Breast tomosynthesis imaging configuration optimization based on computer simulation

Shiyu Xu, Linlin Cong, Jianping Lu, Otto Zhou, Yueh Lee, Ying Chen

JEI, Vol. 23, Issue 01, 013017, (February 2014) https://doi.org/10.1117/12.10.1117/1.JEI.23.1.013017

KEYWORDS: X-rays, Breast, X-ray sources, Beam shaping, Mammography, Sensors, Modulation transfer functions, Computer simulations, Image quality, X-ray detectors

Read Abstract +

Proceedings Article | 6 March 2013 Paper

A simulation based image reconstruction strategy with predictable image quality in limited-angle x-ray tomography

Shiyu Xu, Ying Chen

Proceedings Volume 8668, 86685P (2013) https://doi.org/10.1117/12.2007976

KEYWORDS: X-rays, Tomography, Image restoration, X-ray imaging, X-ray detectors, Modulation transfer functions, Sensors, Image quality, Image resolution, Smoothing

Read Abstract +

Proceedings Article | 6 March 2013 Paper

An application of pre-computed backprojection based penalized-likelihood (PPL) image reconstruction on stationary digital breast tomosynthesis

Shiyu Xu, Jianping Lu, Otto Zhou, Ying Chen

Proceedings Volume 8668, 86680V (2013) https://doi.org/10.1117/12.2007981

KEYWORDS: Digital breast tomosynthesis, X-rays, Image restoration, Image resolution, Sensors, 3D acquisition, 3D image processing, Imaging systems, Modulation transfer functions, 3D image reconstruction

Read Abstract +

Showing 5 of 11 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years