Dr. Xinhua Cao Profile

Dr. Xinhua Cao

IT Clinical Application Manager at Childrens Hospital Boston

SPIE Involvement:

Author

Area of Expertise:

Medical imaging and processing , 3D visualization , image guided treatment (IGT) , automated image analysis , computed aided diagnosis (CAD)

Publications (10)

SPIE Journal Paper | 28 January 2021

DeepAMO: a multi-slice, multi-view anthropomorphic model observer for visual detection tasks performed on volume images

Ye Li, Junyu Chen, Justin Brown, S. Ted Treves, Xinhua Cao, Frederic Fahey, George Sgouros, Wesley Bolch, Eric Frey

JMI, Vol. 8, Issue 04, 041204, (January 2021) https://doi.org/10.1117/12.10.1117/1.JMI.8.4.041204

KEYWORDS: 3D modeling, Performance modeling, Image segmentation, Data modeling, Defect detection, 3D image processing, Computer simulations, Image processing, Composites, Kidney

Read Abstract +

Purpose: We propose a deep learning-based anthropomorphic model observer (DeepAMO) for image quality evaluation of multi-orientation, multi-slice image sets with respect to a clinically realistic 3D defect detection task. Approach: The DeepAMO is developed based on a hypothetical model of the decision process of a human reader performing a detection task using a 3D volume. The DeepAMO is comprised of three sequential stages: defect segmentation, defect confirmation (DC), and rating value inference. The input to the DeepAMO is a composite image, typical of that used to view 3D volumes in clinical practice. The output is a rating value designed to reproduce a human observer’s defect detection performance. In stages 2 and 3, we propose: (1) a projection-based DC block that confirms defect presence in two 2D orthogonal orientations and (2) a calibration method that “learns” the mapping from the features of stage 2 to the distribution of observer ratings from the human observer rating data (thus modeling inter- or intraobserver variability) using a mixture density network. We implemented and evaluated the DeepAMO in the context of Tc99m-DMSA SPECT imaging. A human observer study was conducted, with two medical imaging physics graduate students serving as observers. A 5 × 2-fold cross-validation experiment was conducted to test the statistical equivalence in defect detection performance between the DeepAMO and the human observer. We also compared the performance of the DeepAMO to an unoptimized implementation of a scanning linear discriminant observer (SLDO). Results: The results show that the DeepAMO’s and human observer’s performances on unseen images were statistically equivalent with a margin of difference (ΔAUC) of 0.0426 at p < 0.05, using 288 training images. A limited implementation of an SLDO had a substantially higher AUC (0.99) compared to the DeepAMO and human observer. Conclusion: The results show that the DeepAMO has the potential to reproduce the absolute performance, and not just the relative ranking of human observers on a clinically realistic defect detection task, and that building conceptual components of the human reading process into deep learning-based models can allow training of these models in settings where limited training images are available.

Proceedings Article | 13 March 2017 Paper

DICOM image quantification secondary capture (DICOM IQSC) integrated with numeric results, regions, and curves: implementation and applications in nuclear medicine

Xinhua Cao, Xiaoyin Xu, Stephan Voss

Proceedings Volume 10138, 1013814 (2017) https://doi.org/10.1117/12.2254137

KEYWORDS: Quantitative analysis, Image processing, Radiology, Kidney, Computer aided diagnosis and therapy, Imaging systems, Nuclear medicine, Picture Archiving and Communication System, Imaging informatics, Digital imaging, Medical imaging

Read Abstract +

Proceedings Article | 24 February 2017 Paper

Optimized 3D stitching algorithm for whole body SPECT based on transition error minimization (TEM)

Xinhua Cao, Xiaoyin Xu, Stephan Voss

Proceedings Volume 10133, 1013321 (2017) https://doi.org/10.1117/12.2254096

KEYWORDS: Single photon emission computed tomography, Expectation maximization algorithms, 3D image processing, Reconstruction algorithms, Transmission electron microscopy, Image blending, Visibility, Medical imaging, Bone, Cameras

Read Abstract +

Proceedings Article | 9 March 2011 Paper

Automated analysis of Xe-133 pulmonary ventilation (AAPV) in children

Xinhua Cao, S. Ted Treves

Proceedings Volume 7965, 79651O (2011) https://doi.org/10.1117/12.877682

KEYWORDS: Lung, Image segmentation, Visualization, Scintigraphy, Human-machine interfaces, Image processing, Imaging systems, Image acquisition, Xenon, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 11 March 2008 Paper

Automated motion correction based on target tracking for dynamic nuclear medicine studies

Xinhua Cao, Tracy Tetrault, Fred Fahey, Ted Treves

Proceedings Volume 6914, 69142B (2008) https://doi.org/10.1117/12.770440

KEYWORDS: Target detection, Bladder, Nuclear medicine, Kidney, Detection and tracking algorithms, Motion estimation, Image segmentation, Scintigraphy, Stomach, Image acquisition

Read Abstract +

Proceedings Article | 16 May 2002 Paper

Brain imaging registry for neurologic diagnosis and research

Kent Hoo, Stephen Wong, Robert Knowlton, Geoffrey Young, John Walker, Xinhua Cao, William Dillon, Randall Hawkins, Kenneth Laxer

Proceedings Volume 4685, (2002) https://doi.org/10.1117/12.466996

KEYWORDS: Databases, Picture Archiving and Communication System, Image processing, Data acquisition, Analytical research, Data modeling, Imaging systems, Telecommunications, Computing systems, Visualization

Read Abstract +

Proceedings Article | 16 May 2002 Paper

XML&CORBA-based distributed system for information integration and dissemination in multimedia neuroimaging applications

Xinhua Cao, Stephen Wong, Kent Hoo, Wan Ching, Randall Hawkins, William Dillon

Proceedings Volume 4685, (2002) https://doi.org/10.1117/12.467031

KEYWORDS: Distributed computing, Logic, Neuroimaging, Java, Computing systems, Image analysis, Information fusion, Human-machine interfaces, Multimedia, Data processing

Read Abstract +

Proceedings Article | 7 August 2001 Paper

Developing a digital mammography data warehouse

Hong Zhang, Xinhua Cao, Stephen Wong, Shyhliang Lou, Edward Sickles

Proceedings Volume 4323, (2001) https://doi.org/10.1117/12.435495

KEYWORDS: Breast imaging, Digital mammography, Imaging systems, Breast cancer, Picture Archiving and Communication System, Mammography, Data acquisition, Decision support systems, Data modeling, Databases

Read Abstract +

Proceedings Article | 7 August 2001 Paper

Web-based multimedia information retrieval for clinical application research

Xinhua Cao, Kent Hoo, Hong Zhang, Wan Ching, Ming Zhang, Stephen Wong

Proceedings Volume 4323, (2001) https://doi.org/10.1117/12.435500

KEYWORDS: Multimedia, Epilepsy, Analytical research, Image retrieval, Magnetic resonance imaging, Picture Archiving and Communication System, Data modeling, 3D image processing, Data archive systems, Positron emission tomography

Read Abstract +

Proceedings Article | 25 April 2000 Paper

Novel algorithm for measuring the MTF of a digital radiographic system with a CCD array detector

Xinhua Cao, H. Huang, Shyhliang Lou

Proceedings Volume 3977, (2000) https://doi.org/10.1117/12.384535

KEYWORDS: Modulation transfer functions, Imaging systems, Sensors, Digital imaging, Charge-coupled devices, Image segmentation, Detection and tracking algorithms, CCD image sensors, Computing systems, Fourier transforms

Read Abstract +

Showing 5 of 10 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