Dr. Beilei Xu Profile

Dr. Beilei Xu

at Xerox Corp

SPIE Involvement:

Author

Publications (9)

SPIE Journal Paper | 30 September 2022

Classification of clinically relevant intravascular volume status using point of care ultrasound and machine learning

Safwan Wshah, Beilei Xu, John Steinharter, Clifford Reilly, Katelin Morrissette

JMI, Vol. 9, Issue 05, 054502, (September 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.5.054502

KEYWORDS: Heart, Ultrasonography, Video, Point-of-care devices, Artificial intelligence, Data modeling, 3D modeling, Machine learning, Binary data, Image processing

Read Abstract +

PurposeThis is a foundational study in which multiorgan system point of care ultrasound (POCUS) and machine learning (ML) are used to mimic physician management decisions regarding the functional intravascular volume status (IVS) and need for diuretic therapy. We present this as an impactful use case of an application of ML in aided decision making for clinical practice. IVS represents complex physiologic interactions of the cardiac, renal, pulmonary, and other organ systems. In particular, we focus on vascular congestion and overload as an evolving concept in POCUS diagnosis and clinical relevance. It is critical for physicians to be able to evaluate IVS without disrupting workflow or exposing patients to unnecessary testing, radiation, or cost. This work utilized a small retrospective dataset as a feasibility test for ML binary classification of diuretic administration validated with clinical decision data. Future work will be directed toward artificial intelligence (AI) delivery at the bedside and assessment of the impact on patient-centered outcomes and physician workflow improvement.ApproachWe retrospectively reviewed and processed 1039 POCUS video clips, including cardiac, thoracic, and inferior vena cava (IVC) views. Multiorgan POCUS clips were correlated with clinical data extracted from the electronic health record and deidentified for algorithm training and validation. We implemented a two-stream three-dimensional (3D) deep learning approach that fuses heart and IVC data to perform binary classification of the need for diuretic use.ResultsOur proposed approach achieves high classification accuracy (84%) for the determination of diuretic use with 0.84 area under the receiver operating characteristic curve.ConclusionsOur two-stream 3D deep neural network is able to classify POCUS video clips that match physicians’ classification for or against diuretic use with high accuracy. This serves as a foundational step in the progress toward AI-aided diagnosis and AI implementation in the field of IVS evaluation by POCUS.

Proceedings Article | 4 March 2015 Paper

A machine learning approach for detecting cell phone usage

Beilei Xu, Robert Loce

Proceedings Volume 9407, 94070A (2015) https://doi.org/10.1117/12.2083126

KEYWORDS: Cell phones, Imaging systems, Cameras, Machine learning, Sensors, Near infrared, Image classification, Visualization, Facial recognition systems, Safety

Read Abstract +

Proceedings Article | 25 January 2012 Paper

A method of detecting changes in image quality via sensing on customer documents

Wencheng Wu, Beilei Xu, John Handley

Proceedings Volume 8293, 82930P (2012) https://doi.org/10.1117/12.905666

KEYWORDS: Image quality, Printing, Data modeling, Quality measurement, Statistical analysis, Diagnostics, Image processing, Analytical research, Process control, Image analysis

Read Abstract +

SPIE Journal Paper | 1 January 2011

Halftone moiré due to imager distortion

Orhan Bulan, Robert Loce, Beilei Xu

JEI, Vol. 20, Issue 1, 013008, (January 2011) https://doi.org/10.1117/12.10.1117/1.3537830

KEYWORDS: Distortion, Halftones, Imaging systems, Printing, Color printing, Image processing, Light emitting diodes, Optical components, Error analysis, Clocks

Read Abstract +

Proceedings Article | 19 January 2010 Paper

Halftone moiré due to imager distortion

Orhan Bulan, Robert Loce, Beilei Xu

Proceedings Volume 7528, 752811 (2010) https://doi.org/10.1117/12.838867

KEYWORDS: Distortion, Imaging systems, Halftones, Printing, Light emitting diodes, Error analysis, Optical components, Raster graphics, Color printing, Image processing

Read Abstract +

SPIE Journal Paper | 1 July 2007

Rank-ordered error diffusion: method and applications

Robert Loce, Beilei Xu

JEI, Vol. 16, Issue 03, 033001, (July 2007) https://doi.org/10.1117/12.10.1117/1.2768603

KEYWORDS: Halftones, Diffusion, Image processing, Quantization, Printing, Binary data, Error analysis, Raster graphics, Image resolution, Imaging systems

Read Abstract +

Proceedings Article | 29 January 2007 Paper

Rank-ordered error diffusion: method and applications

Robert Loce, Beilei Xu

Proceedings Volume 6493, 64931A (2007) https://doi.org/10.1117/12.717541

KEYWORDS: Halftones, Diffusion, Quantization, Image processing, Printing, Binary data, Error analysis, Raster graphics, Computer programming, Calibration

Read Abstract +

Proceedings Article | 17 January 2005 Paper

Glossmark technology: beyond halftone frequencies

Shen-ge Wang, Chu-heng Liu, Beilei Xu

Proceedings Volume 5667, (2005) https://doi.org/10.1117/12.588595

KEYWORDS: Halftones, Imaging systems, Printing, Light sources, Diffraction, Digital watermarking, Image processing, Diffraction gratings, Mirrors, Reflectivity

Read Abstract +

Proceedings Article | 25 April 1997 Paper

Heart range determination for SPECT myocardial perfusion studies

Jin-Shin Chou, Beilei Xu, JianZhong Qian, Raymond DeVito

Proceedings Volume 3034, (1997) https://doi.org/10.1117/12.274086

KEYWORDS: Heart, Single photon emission computed tomography, Motion analysis, Algorithm development, Image processing, Motion measurement, Databases, Liver, Spleen, Cameras

Read Abstract +

Showing 5 of 9 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