Dr. Xiao-Hui Wang Profile

Dr. Xiao-Hui Wang

Research Associate at Univ of Pittsburgh

SPIE Involvement:

Author

Publications (26)

Proceedings Article | 9 March 2011 Paper

Multi-probe-based resonance-frequency electrical impedance spectroscopy for detection of suspicious breast lesions: improving performance using partial ROC optimization

Dror Lederman, Bin Zheng, Xingwei Wang, Xiao Hui Wang, David Gur

Proceedings Volume 7963, 79631Z (2011) https://doi.org/10.1117/12.877380

KEYWORDS: Breast, Breast cancer, Mammography, Tissues, Biopsy, Sensors, Dielectric spectroscopy, Computer aided diagnosis and therapy, Machine learning, Signal detection

Read Abstract +

Proceedings Article | 9 March 2011 Paper

Computerized prediction of breast cancer risk: comparison between the global and local bilateral mammographic tissue asymmetry

Xingwei Wang, Dror Lederman, Jun Tan, Xiao Hui Wang, Bin Zheng

Proceedings Volume 7963, 79631L (2011) https://doi.org/10.1117/12.876816

KEYWORDS: Breast, Breast cancer, Tissues, Cancer, Tumor growth modeling, Performance modeling, Mammography, Feature extraction, Data modeling, Databases

Read Abstract +

Proceedings Article | 9 March 2010 Paper

Improving performance and reliability of interactive CAD schemes

Xiao-Hui Wang, Sang Cheol Park, Jun Tan, Joseph Leader, Bin Zheng

Proceedings Volume 7624, 76242E (2010) https://doi.org/10.1117/12.843917

KEYWORDS: Databases, Reliability, Computer aided diagnosis and therapy, Computer aided design, Breast, Image segmentation, Visualization, Medical imaging, Mammography, Feature extraction

Read Abstract +

An interactive computer-aided detection or diagnosis (ICAD) scheme allows observers to query suspicious abnormalities (lesions) depicted on medical images. Once a suspicious region is queried, ICAD segments the abnormal region, computes a set of image features, searches for and identifies the reference regions depicted on the verified lesions that are similar to the queried one. Based on the distribution of the selected similar regions, ICAD generates a detection (or classification) score of the queried region depicting true-positive disease. In this study, we assessed the performance and reliability of an ICAD scheme when using a database including total 1500 positive images depicted verified breast masses and 1500 negative images depicted ICAD-cued false-positive regions as well as the leave-one-out testing method. We conducted two experiments. In the first experiment, we tested the relationship between ICAD performance and the size of reference database by systematically increasing the size of reference database from 200 to 3000 images. In the second experiment, we tested the relationship between ICAD performance and the similarity level between the queried image and the retrieved similar references by applying a set of thresholds to systematically remove the queried images whose similarity level to their most "similar" reference images are lower than threshold. The performance was compared based on the areas under ROC curves (AUC). The results showed that (1) as the increase of reference database, AUC value monotonically increased from 0.636±0.041 to 0.854±0.004 and (2) as the increase of similarity threshold values, AUC value also monotonically increased from 0.854±0.004 to 0.932±0.016. The increase of AUC values and the decrease of their standard deviations indicate the improvement of both CAD performance and reliability. The study suggested that (1) assembling the large and diverse reference databases and (2) assessing and reporting the reliability of ICAD-generated results based on the similarity measurement are important in development and application of the ICAD schemes.

Proceedings Article | 3 March 2009 Paper

Computer-aided detection of HER2 amplification status using FISH images: a preliminary study

Bin Zheng, Xiao-Hui Wang, Urvashi Surti, Rohit Bhargava, David Gur

Proceedings Volume 7260, 726028 (2009) https://doi.org/10.1117/12.810155

KEYWORDS: Image segmentation, Signal detection, Computer aided design, Breast cancer, Image analysis, Statistical analysis, Luminescence, Computer aided diagnosis and therapy, Genetics

Read Abstract +

The amplification status of human epidermal growth factor receptors 2 (HER2) genes is strongly associated with clinical outcome in patients with breast cancer. The American Society of Clinical Oncology Tumor Marker Guidelines Panel has recommended routine testing of HER2 status on all newly diagnosed metastatic breast cancers since 2001. Although fluorescent in situ hybridization (FISH) technology provides superior accuracy as compared with other approaches, current manual FISH analysis methods are somewhat subjective, tedious, and may introduce interreader variability. The goal of this preliminary study is to develop and test a computer-aided detection (CAD) scheme to assess HER2 status using FISH images. Forty FISH images were selected for this study from our genetic laboratory. The CAD scheme first applies an adaptive, iterative threshold method followed by a labeling algorithm to segment cells of possible interest. A set of classification rules is then used to identify analyzable interphase cells and discard nonanalyzable cells due to cell overlapping and/or other image staining debris (or artifacts). The scheme then maps the detected analyzable cells onto two other gray scale images corresponding to the red and green color of the original image followed by application of a raster scan and labeling algorithms to separately detect the HER-2/neu ("red") and CEP17 ("green") FISH signals. A simple distance based criterion is applied to detect and merge split FISH signals within each cell. The CAD scheme computes the ratio between independent "red" and "green" FISH signals of all analyzable cells identified on an image. If the ratio is ≥ 2.0, the FISH image is assumed to have been acquired from a HER2+ case; otherwise, the FISH image is assumed to have been acquired from HER2- case. When we applied the CAD scheme to the testing dataset, the average computed HER2 amplification ratios were 1.06±0.25 and 2.53±0.81 for HER2- and HER2+ samples, respectively. The results show that the CAD scheme has the ability to automatically detect HER2 status using FISH images. The success of CAD-guided FISH image analysis could result in a more objective, consistent, and efficient approach in determining HER2 status of breast cancers.

Proceedings Article | 21 March 2008 Paper

Utilization of mammographic complexity for improving risk assessment and cancer detection

Xiao Hui Wang, Jill King, Saraswathi Golla, Janet Durick, Cynthia Britton, Jules Sumkin, Joseph Leader, Walter Good

Proceedings Volume 6916, 69161M (2008) https://doi.org/10.1117/12.770587

KEYWORDS: Cancer, Breast, Tissues, Breast cancer, Databases, Mammography, Tumors, Statistical analysis, Physics, Image compression

Read Abstract +

Proceedings Article | 17 March 2008 Paper

Applying a 2D based CAD scheme for detecting micro-calcification clusters using digital breast tomosynthesis images: an assessment

Sang Cheol Park, Bin Zheng, Xiao-Hui Wang, David Gur

Proceedings Volume 6915, 691507 (2008) https://doi.org/10.1117/12.768534

KEYWORDS: Digital breast tomosynthesis, Computer aided design, Mammography, Computer aided diagnosis and therapy, Breast, Visualization, 3D image processing, Signal to noise ratio, Image filtering

Read Abstract +

Digital breast tomosynthesis (DBT) has emerged as a promising imaging modality for screening mammography. However, visually detecting micro-calcification clusters depicted on DBT images is a difficult task. Computer-aided detection (CAD) schemes for detecting micro-calcification clusters depicted on mammograms can achieve high performance and the use of CAD results can assist radiologists in detecting subtle micro-calcification clusters. In this study, we compared the performance of an available 2D based CAD scheme with one that includes a new grouping and scoring method when applied to both projection and reconstructed DBT images. We selected a dataset involving 96 DBT examinations acquired on 45 women. Each DBT image set included 11 low dose projection images and a varying number of reconstructed image slices ranging from 18 to 87. In this dataset 20 true-positive micro-calcification clusters were visually detected on the projection images and 40 were visually detected on the reconstructed images, respectively. We first applied the CAD scheme that was previously developed in our laboratory to the DBT dataset. We then tested a new grouping method that defines an independent cluster by grouping the same cluster detected on different projection or reconstructed images. We then compared four scoring methods to assess the CAD performance. The maximum sensitivity level observed for the different grouping and scoring methods were 70% and 88% for the projection and reconstructed images with a maximum false-positive rate of 4.0 and 15.9 per examination, respectively. This preliminary study demonstrates that (1) among the maximum, the minimum or the average CAD generated scores, using the maximum score of the grouped cluster regions achieved the highest performance level, (2) the histogram based scoring method is reasonably effective in reducing false-positive detections on the projection images but the overall CAD sensitivity is lower due to lower signal-to-noise ratio, and (3) CAD achieved higher sensitivity and higher false-positive rate (per examination) on the reconstructed images. We concluded that without changing the detection threshold or performing pre-filtering to possibly increase detection sensitivity, current CAD schemes developed and optimized for 2D mammograms perform relatively poorly and need to be re-optimized using DBT datasets and new grouping and scoring methods need to be incorporated into the schemes if these are to be used on the DBT examinations.

Proceedings Article | 22 March 2007 Paper

Stereo display of CT images for lung cancer screening: a pilot study

Xiao Hui Wang, Janet Durick, David Herbert, Amy Lu, Sarawathi Golla, Dilip Shinde, Samaia Piracha, Kristin Foley, Carl Fuhrman, Betty Shindel, J. Ken Leader, Walter Good

Proceedings Volume 6516, 65160C (2007) https://doi.org/10.1117/12.709520

KEYWORDS: Lung, Computed tomography, 3D displays, Lung cancer, Stereoscopic displays, Tissues, 3D image processing, Medical imaging, CRTs, Statistical analysis

Read Abstract +

Proceedings Article | 7 March 2007 Paper

Application of 3D geometric tensors for segmenting cylindrical tree structures from volumetric datasets

Walter Good, Xiao Hui Wang, Carl Fuhrman, Jules Sumkin, Glenn Maitz, Joseph Leader, Cynthia Britton, David Gur

Proceedings Volume 6512, 65123R (2007) https://doi.org/10.1117/12.709823

KEYWORDS: Image segmentation, 3D applications, Matrices, Gold, Diagnostics, Detection and tracking algorithms, Image filtering, Statistical analysis, Chronic obstructive pulmonary disease, Radiology

Read Abstract +

Proceedings Article | 30 January 2006 Paper

Real-time stereographic display of volumetric datasets in radiology

Xiao Hui Wang, Glenn Maitz, J. Leader, Walter Good

Proceedings Volume 6055, 60551A (2006) https://doi.org/10.1117/12.640834

KEYWORDS: 3D volumetric displays, Radiology, Glasses, Lung, Magnetic resonance imaging, Human-machine interfaces, Visualization, Lung cancer, 3D displays, Stereoscopic displays

Read Abstract +

Proceedings Article | 21 May 2004 Paper

Stereo display for chest CT

Xiao Wang, Walter Good, Carl Fuhrman, Jules Sumkin, Cynthia Britton, Thomas Warfel, David Gur

Proceedings Volume 5291, (2004) https://doi.org/10.1117/12.527234

KEYWORDS: Computed tomography, Chest, Stereoscopic displays, Lung, Tissues, Transparency, 3D displays, 3D image processing, 3D modeling, Image segmentation

Read Abstract +

Proceedings Article | 5 May 2004 Paper

Projection models for stereo display of chest CT

Xiao Hui Wang, Walter Good, Carl Fuhrman, Jules Sumkin, Cynthia Britton, Thomas Warfel, David Gur

Proceedings Volume 5367, (2004) https://doi.org/10.1117/12.536111

KEYWORDS: Chest, 3D displays, Computed tomography, Lung, Volume rendering, Tissues, 3D image processing, Visualization, Lung cancer, 3D modeling

Read Abstract +

Proceedings Article | 15 May 2003 Paper

Evaluation of quantitative measures of breast tissue density from mammography with truth from MRI data

Xiao Hui Wang, Brian Chapman, Cynthia Britton, Saraswathi Golla, Luisa Wallace, Walter Good

Proceedings Volume 5032, (2003) https://doi.org/10.1117/12.481923

KEYWORDS: Tissues, Breast, Magnetic resonance imaging, Mammography, Algorithm development, Breast cancer, Signal attenuation, Skin, Image processing, Image segmentation

Read Abstract +

Proceedings Article | 15 May 2003 Paper

Improving CAD performance in detecting masses depicted on prior images

Bin Zheng, Xiao Hui Wang, Luisa Wallace, Cathy Cohen, Lara Hardesty, Christiane Hakim, Gordon Abran, Jules Sumkin, David Gur

Proceedings Volume 5032, (2003) https://doi.org/10.1117/12.480291

KEYWORDS: Computer aided design, Databases, Computer aided diagnosis and therapy, Computer simulations, Mammography, Artificial neural networks, Cancer, Feature extraction, Biopsy

Read Abstract +

Proceedings Article | 15 May 2003 Paper

Feature-based differences between mammograms

Walter Good, Xiao Hui Wang, Glenn Maitz

Proceedings Volume 5032, (2003) https://doi.org/10.1117/12.483559

KEYWORDS: Tissues, Mammography, Breast, Image processing, Skin, Image filtering, Image registration, Image compression, Nipple, Diagnostics

Read Abstract +

Proceedings Article | 17 May 2002 Paper

Visualization of 3D geometric models of the breast created from contrast-enhanced MRI

J. Ken Leader, Xiao Hui Wang, Yuan-Hsiang Chang, Brian Chapman

Proceedings Volume 4681, (2002) https://doi.org/10.1117/12.466923

KEYWORDS: 3D modeling, Magnetic resonance imaging, Breast, Image segmentation, Visualization, Tissues, Visual process modeling, Data modeling, 3D image processing, Tumor growth modeling

Read Abstract +

Proceedings Article | 9 May 2002 Paper

Incorporation of negative regions in a knowledge-based computer-aided detection scheme

Yuan-Hsiang Chang, Xiao Hui Wang, Lara Hardesty, Christiane Hakim, Bin Zheng, Walter Good, David Gur

Proceedings Volume 4684, (2002) https://doi.org/10.1117/12.467215

KEYWORDS: Mammography, Computer aided design, Computer aided diagnosis and therapy, Image processing, Information fusion, Breast cancer, Tissues, Feature extraction, Radiology

Read Abstract +

Proceedings Article | 9 May 2002 Paper

Change of region conspicuity in bilateral mammograms: potential impact on CAD performance

Bin Zheng, Xiao Hui Wang, Yuan-Hsiang Chang, Lara Hardesty, Marie Ganott, Walter Good, David Gur

Proceedings Volume 4684, (2002) https://doi.org/10.1117/12.467217

KEYWORDS: Skin, Nipple, Chest, Mammography, Computer aided diagnosis and therapy, Image registration, Computer aided design, Algorithm development, Tissues, Breast

Read Abstract +

Proceedings Article | 9 May 2002 Paper

Automatic quality assessment of JPEG and JPEG 2000 compressed images

Walter Good, Glenn Maitz, Xiao Hui Wang

Proceedings Volume 4684, (2002) https://doi.org/10.1117/12.467050

KEYWORDS: Image compression, Mammography, Image quality, Diagnostics, Image filtering, Tissues, Linear filtering, Image processing, Image quality standards, Radiology

Read Abstract +

Proceedings Article | 9 May 2002 Paper

Automated estimation of breast composition from MR images

Brian Chapman, Xiao Hui Wang, Walter Good

Proceedings Volume 4684, (2002) https://doi.org/10.1117/12.467150

KEYWORDS: Breast, Tissues, Image segmentation, Binary data, Chest, Magnetic resonance imaging, Gold, Mammography, Breast cancer, Neural networks

Read Abstract +

Proceedings Article | 3 July 2001 Paper

Computerized analysis of lesions in 3D MR breast images

He Wang, Bin Zheng, Walter Good, Xiao Hui Wang

Proceedings Volume 4322, (2001) https://doi.org/10.1117/12.431064

KEYWORDS: Image registration, Breast, Magnetic resonance imaging, 3D image processing, Tissues, Image segmentation, Breast cancer, 3D image enhancement, Mammography, Feature extraction

Read Abstract +

Proceedings Article | 28 May 2001 Paper

Correction of digitized mammograms to enhance soft display and tissue composition measurement

Xiao Hui Wang, Bin Zheng, Yuan-Hsiang Chang, Walter Good

Proceedings Volume 4319, (2001) https://doi.org/10.1117/12.428071

KEYWORDS: Tissues, Breast, Skin, Mammography, Image compression, Image processing, Neural networks, Image enhancement, Image display, Image classification

Read Abstract +

Proceedings Article | 18 April 2000 Paper

Image modification for display of temporal sequences of mammograms

Walter Good, Glenn Maitz, John Drescher, Xiao Hui Wang, Bin Zheng, Yuan-Hsiang Chang, He Wang

Proceedings Volume 3976, (2000) https://doi.org/10.1117/12.383039

KEYWORDS: Mammography, Image registration, Skin, Tissues, Breast, Nipple, Chest, Image compression, Sensors, Image restoration

Read Abstract +

Proceedings Article | 21 May 1999 Paper

Application of a Bayesian belief network in a computer-assisted diagnosis scheme for mass detection

Bin Zheng, Yuan-Hsiang Chang, Xiao Hui Wang, Walter Good, David Gur

Proceedings Volume 3661, (1999) https://doi.org/10.1117/12.348558

KEYWORDS: Databases, Computer aided design, Computer aided diagnosis and therapy, Image segmentation, Computer networks, Mammography, Image processing, Artificial neural networks, Genetic algorithms, Breast cancer

Read Abstract +

Proceedings Article | 21 May 1999 Paper

Multi-image CAD employing features derived from ipsilateral mammographic views

Walter Good, Bin Zheng, Yuan-Hsiang Chang, Xiao Hui Wang, Glenn Maitz, David Gur

Proceedings Volume 3661, (1999) https://doi.org/10.1117/12.348602

KEYWORDS: Computer aided diagnosis and therapy, Computer aided design, Mammography, Breast, Nipple, Image processing, Image compression, Image segmentation, Tissues, Algorithm development

Read Abstract +

Proceedings Article | 21 May 1999 Paper

Generalized procrustean image deformation for subtraction of mammograms

Walter Good, Bin Zheng, Yuan-Hsiang Chang, Xiao Hui Wang, Glenn Maitz

Proceedings Volume 3661, (1999) https://doi.org/10.1117/12.348559

KEYWORDS: Skin, Image registration, Mammography, Nipple, Tissues, Image processing, Breast, Image restoration, Computer aided design, Bismuth

Read Abstract +

Proceedings Article | 21 May 1999 Paper

Optimizing the feature set for a Bayesian network for breast cancer diagnosis using genetic algorithm techniques

Xiao Hui Wang, Bin Zheng, Yuan-Hsiang Chang, Walter Good

Proceedings Volume 3661, (1999) https://doi.org/10.1117/12.348560

KEYWORDS: Breast cancer, Gallium, Genetic algorithms, Cancer, Databases, Mammography, Testing and analysis, Breast, Computing systems, Image processing

Read Abstract +

Showing 5 of 26 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