Dr. Weijie Chen Profile

Dr. Weijie Chen

Physicist at US Food and Drug Administration

SPIE Involvement:

Conference Chair | Editorial Board Member: Journal of Medical Imaging | Editor | Author

Area of Expertise:

Artificial Intelligence and machine learning , digital pathology , breast MRI , medical image analysis , statistics

Websites:

Personal Website

Profile Summary

Weijie Chen obtained his PhD in Medical Physics from the University of Chicago in 2007. He is currently a research physicist in the Center for Devices and Radiological Health at the US FDA. At CDRH, he conducts research and supports regulatory review of medical devices with his expertise in artificial intelligence and machine learning, medical image analysis and statistical assessment methodologies for diagnostic medicine. He is an editorial board member and associate editor for the SPIE Journal of Medical Imaging.

Publications (46)

Proceedings Article | 3 April 2024 Paper

Paper

Assessment of machine learning algorithms for TILs scoring using whole slide images: comparison with pathologists

Arian Arab, Victor Garcia, Seyed Mostafa Kahaki, Nicholas Petrick, Brandon Gallas, Weijie Chen

Proceedings Volume 12933, 1293315 (2024) https://doi.org/10.1117/12.3008518

KEYWORDS: Calibration, Tumors, Image segmentation, Algorithm development, Machine learning, Detection and tracking algorithms, Cancer detection, Breast cancer

Read Abstract +

Proceedings Article | 3 April 2024 Presentation + Paper

Presentation + Paper

Deep learning-based ROI detection of AEH and EC on histopathology WSIs for predicting hormonal treatment response

Seyed Kahaki, Ian Hagemann, Kenny Cha, Christopher Trindade, Nicholas Petrick, Nicolas Kostelecky, Lindsay Borden, Doaa Atwi, Kar-Ming Fung, Weijie Chen

Proceedings Volume 12933, 129330S (2024) https://doi.org/10.1117/12.3008276

KEYWORDS: Deep learning, Performance modeling, Machine learning, Pathology, Data modeling, Cancer, Therapeutics, Oncology, Medicine

Read Abstract +

Proceedings Article | 29 March 2024 Presentation + Paper

Presentation + Paper

Use of equivalent relative utility to evaluate artificial intelligence-based rule-out devices

Kwok Lung Fan, Yee Lam Elim Thompson, Weijie Chen, Craig Abbey, Frank Samuelson

Proceedings Volume 12929, 129290P (2024) https://doi.org/10.1117/12.3008632

KEYWORDS: Artificial intelligence, Diagnostics, Mammography, Cancer detection, Diagnostic tests, Evolutionary algorithms, Medical imaging, Cancer, Binary data, Statistical analysis

Read Abstract +

SPIE Journal Paper | 15 February 2024

End-to-end deep learning method for predicting hormonal treatment response in women with atypical endometrial hyperplasia or endometrial cancer

Seyed Mostafa M. Kahaki, Ian Hagemann, Kenny Cha, Christopher Trindade, Nicholas Petrick, Nicolas Kostelecky, Lindsay Borden, Doaa Atwi, Kar-Ming Fung, Weijie Chen

JMI, Vol. 11, Issue 01, 017502, (February 2024) https://doi.org/10.1117/12.10.1117/1.JMI.11.1.017502

KEYWORDS: Education and training, Deep learning, Data modeling, Performance modeling, Feature extraction, Machine learning, Radiomics, RGB color model, Tumor growth modeling, Statistical modeling

Read Abstract +

SPIE Journal Paper | 18 July 2023 Open Access

Open Access

Longitudinal assessment of demographic representativeness in the Medical Imaging and Data Resource Center open data commons

Heather M. Whitney, Natalie Baughan, Kyle J. Myers, Karen Drukker, Judy Gichoya, Brad Bower, Weijie Chen, Nicholas Gruszauskas, Jayashree Kalpathy-Cramer, Sanmi Koyejo, Rui C. Sá, Berkman Sahiner, Zi Zhang, Maryellen L. Giger

JMI, Vol. 10, Issue 06, 061105, (July 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.6.061105

KEYWORDS: COVID 19, Medical imaging, Algorithm development, Diseases and disorders, Artificial intelligence, Data modeling, Gold, Medicine, Medical research, Evolutionary algorithms

Read Abstract +

SPIE Journal Paper | 23 June 2023 Open Access

Open Access

Regulatory considerations for medical imaging AI/ML devices in the United States: concepts and challenges

Nicholas Petrick, Weijie Chen, Jana Delfino, Brandon Gallas, Yanna Kang, Daniel Krainak, Berkman Sahiner, Ravi Samala

JMI, Vol. 10, Issue 05, 051804, (June 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.5.051804

KEYWORDS: Medical imaging, Data modeling, Medical devices, Education and training, Imaging devices, Performance modeling, Instrument modeling, Machine learning, Design and modelling, Medical device development

Read Abstract +

SPIE Journal Paper | 26 April 2023 Open Access

Open Access

Toward fairness in artificial intelligence for medical image analysis: identification and mitigation of potential biases in the roadmap from data collection to model deployment

Karen Drukker, Weijie Chen, Judy Gichoya, Nicholas Gruszauskas, Jayashree Kalpathy-Cramer, Sanmi Koyejo, Kyle Myers, Rui Sá, Berkman Sahiner, Heather Whitney, Zi Zhang, Maryellen Giger

JMI, Vol. 10, Issue 06, 061104, (April 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.6.061104

KEYWORDS: Data modeling, Education and training, Medical imaging, Artificial intelligence, Performance modeling, Data acquisition, Machine learning, Evolutionary algorithms, Diseases and disorders, COVID 19

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Presentation + Paper

MISS-tool: medical image segmentation synthesis tool to emulate segmentation errors

Shuyue Guan, Ravi Samala, Arian Arab, Weijie Chen

Proceedings Volume 12465, 1246518 (2023) https://doi.org/10.1117/12.2653650

KEYWORDS: Image segmentation, Medical imaging, Lung, Anatomy, Radiotherapy, Image processing algorithms and systems, Error analysis, Education and training

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

Presentation + Paper

Weakly supervised deep learning for predicting the response to hormonal treatment of women with atypical endometrial hyperplasia: a feasibility study

Seyed Kahaki, Ian Hagemann, Kenny Cha, Christopher Trindade, Nicholas Petrick, Nicolas Kostelecky, Weijie Chen

Proceedings Volume 12471, 124710T (2023) https://doi.org/10.1117/12.2652912

KEYWORDS: Machine learning, Tumor growth modeling, Deep learning, RGB color model, Performance modeling, Pathology, Statistical modeling, Feature extraction

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Poster + Paper

Effect of color-normalization on deep learning segmentation models for tumor-infiltrating lymphocytes scoring using breast cancer histopathology images

Arian Arab, Victor Garcia, Shuyue Guan, Brandon Gallas, Berkman Sahiner, Nicholas Petrick, Weijie Chen

Proceedings Volume 12471, 124711H (2023) https://doi.org/10.1117/12.2653989

KEYWORDS: Image segmentation, Breast cancer, Deep learning, Pathology, Color normalization

Read Abstract +

SPIE Journal Paper | 8 July 2022 Open Access

Open Access

Determining Roe and Metz model parameters for simulating multireader multicase confidence-of-disease rating data based on real-data or conjectured Obuchowski–Rockette parameter estimates

Stephen Hillis, Brian Smith, Weijie Chen

JMI, Vol. 9, Issue 04, 045501, (July 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.4.045501

KEYWORDS: Data modeling, Computer simulations, Error analysis, Algorithm development, Statistical analysis, Statistical modeling, Magnetic resonance imaging, Electronic filtering, Performance modeling, Analytical research

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Presentation + Paper

Wait-time-saving analysis and clinical effectiveness of computer-aided triage and notification (CADt) devices based on queueing theory

Yee Lam Elim Thompson, Gary Levine, Weijie Chen, Berkman Sahiner, Qin Li, Nicholas Petrick, Frank Samuelson

Proceedings Volume 12035, 120350Q (2022) https://doi.org/10.1117/12.2603184

KEYWORDS: Artificial intelligence, Monte Carlo methods, Diagnostics, Radiology, Instrument modeling, Process modeling, Mathematical modeling, Solids, Performance modeling, Molecular nanotechnology

Read Abstract +

SPIE Journal Paper | 1 October 2021 Open Access

Open Access

Lessons learned in transitioning to AI in the medical imaging of COVID-19

Issam El Naqa, Qiyuan Hu, Weijie Chen, Hui Li, Jordan Fuhrman, Naveena Gorre, Maryellen Giger

JMI, Vol. 8, Issue S1, 010902, (October 2021) https://doi.org/10.1117/12.10.1117/1.JMI.8.S1.010902

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Poster + Presentation + Paper

Reproducibility in deep learning algorithms for digital pathology applications: a case study using the CAMELYON16 datasets

Weizhe Li, Weijie Chen

Proceedings Volume 11603, 1160318 (2021) https://doi.org/10.1117/12.2581996

KEYWORDS: Evolutionary algorithms, Pathology, Algorithm development, Artificial intelligence, Detection and tracking algorithms, Neural networks, Lymphatic system, Cancer, Breast cancer

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Presentation + Paper

Simulation of multi-reader multi-case study data with realistic ROC performance characteristics

Xiaochen Zhu, Weijie Chen

Proceedings Volume 11316, 113160M (2020) https://doi.org/10.1117/12.2550545

KEYWORDS: Computer simulations, Data modeling, Monte Carlo methods, Performance modeling, Mathematical modeling, Statistical analysis, Diagnostics, Statistical modeling

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Paper

Characterization of color normalization methods in digital pathology whole slide images

Dorsa Ziaei, Weizhe Li, Samuel Lam, Wei-Chung Cheng, Weijie Chen

Proceedings Volume 11320, 1132017 (2020) https://doi.org/10.1117/12.2550585

KEYWORDS: Scanners, Color difference, Pathology, Artificial intelligence, Algorithm development

Read Abstract +

The color rendering of whole-slide images (WSIs) depends on factors involving the sample, such as tissue type, preparation methods, staining type and staining protocol, as well as equipment, such as the WSI scanner, WSI viewer, and WSI display. Variations in any of these steps may change the color rendering and therefore affect the performance of pathologists in the interpretation of WSIs and the robustness of artificial intelligence algorithms. In the literature, color normalization techniques have been proposed to reduce the color variations. The purpose of this work is to develop an objective approach to characterizing color normalization methods used in digital pathology. We employed color normalization methods to normalize the color rendered by a WSI scanner and then compared the normalized color with the actual scan by that scanner. The normalization errors were evaluated on the pixel level using the CIE color difference ΔE metric that have been shown to correlate with visually perceived differences in human vision. A selected set of 310 patch images of breast tissues scanned by two scanners from the ICPR 2014 MITOS & ATYPIA contest was used. Images from one scanner were color normalized to match the color rendering of the other scanner. Four color normalization methods were compared – Macenko, Reinhard, Vahadane, and StainGAN. Experimental results show that average color differences between two scanners in terms of ΔE were reduced from 16.2 before normalization to the range of [13.7,16.9] after normalization for the Macenko, Reinhard, Vahadane methods, and to 8.3 for the StainGAN method. Apparently the StainGAN method is significantly superior to the other three methods in terms of the ΔE metric. As such, we demonstrated a quantitative method for objectively evaluating color normalization techniques. Future work is needed to explore the relationship of the color fidelity measure and the impact of color normalization on pathologist and AI performance in clinical tasks.

SPIE Journal Paper | 28 February 2020 Open Access

Open Access

Special Section Guest Editorial: Evaluation Methodologies for Clinical AI

Susan Astley, Weijie Chen, Kyle Myers, Robert Nishikawa

JMI, Vol. 7, Issue 01, 012701, (February 2020) https://doi.org/10.1117/12.10.1117/1.JMI.7.1.012701

KEYWORDS: Artificial intelligence, Evolutionary algorithms, Imaging systems, Medical imaging, Pathology, Computer aided diagnosis and therapy, Mammography, Image acquisition, Image segmentation, Computer aided design

Read Abstract +

Proceedings Article | 18 March 2019 Paper

Paper

Segmentation of follicles from CD8-stained slides of follicular lymphoma using deep learning

C. Senaras, M. K. Niazi, V. Arole, W. Chen, B. Sahiner, A. Shana’ah, A. Louissaint, R. Hasserjian, G. Lozanski, M. Gurcan

Proceedings Volume 10956, 109560R (2019) https://doi.org/10.1117/12.2512262

KEYWORDS: Lymphoma, Image segmentation, Tumors, Cancer, Pathology, Lymphatic system, Algorithm development, Computer programming, Convolutional neural networks, Health informatics

Read Abstract +

Proceedings Article | 4 March 2019 Presentation + Paper

Presentation + Paper

Adaptive sample size re-estimation in MRMC studies

Weijie Chen, Zhipeng Huang, Frank Samuelson, Lucas Tcheuko

Proceedings Volume 10952, 109520G (2019) https://doi.org/10.1117/12.2513646

KEYWORDS: Statistical analysis, Error analysis, Computer simulations, Software development, Diagnostics, Clinical trials, Medical imaging, Human-machine interfaces, Imaging devices

Read Abstract +

SPIE Journal Paper | 21 January 2019

Impact of prevalence and case distribution in lab-based diagnostic imaging studies

Brandon Gallas, Weijie Chen, Elodia Cole, Robert Ochs, Nicholas Petrick, Etta Pisano, Berkman Sahiner, Frank Samuelson, Kyle Myers

JMI, Vol. 6, Issue 01, 015501, (January 2019) https://doi.org/10.1117/12.10.1117/1.JMI.6.1.015501

KEYWORDS: Atomic force microscopy, Cancer, Breast, Statistical analysis, Diagnostics, Mammography, Image processing, Digital mammography, Error analysis, Medical imaging

Read Abstract +

SPIE Journal Paper | 17 May 2018

Paired split-plot designs of multireader multicase studies

Weijie Chen, Qi Gong, Brandon Gallas

JMI, Vol. 5, Issue 03, 031410, (May 2018) https://doi.org/10.1117/12.10.1117/1.JMI.5.3.031410

KEYWORDS: Statistical analysis, Statistical modeling, Computer simulations, Atomic force microscopy, Error analysis, Diagnostics, Roentgenium, Data modeling, Medical imaging, Digital mammography

Read Abstract +

Proceedings Article | 7 March 2018 Presentation + Paper

Presentation + Paper

Efficiency gain of paired split-plot designs in MRMC ROC studies

Weijie Chen, Qi Gong, Brandon Gallas

Proceedings Volume 10577, 105770F (2018) https://doi.org/10.1117/12.2293741

KEYWORDS: Cancer, Data modeling, Statistical analysis, Diagnostics, Computer simulations, Statistical modeling, Digital mammography, Mammography

Read Abstract +

Proceedings Article | 7 March 2018 Paper

Paper

Assessment of computerized algorithms by comparing with human observers in binary classification tasks: a simulation study

Yang Yang, Berkman Sahiner, Zhipeng Huang, Nicholas Petrick, Weijie Chen

Proceedings Volume 10577, 1057713 (2018) https://doi.org/10.1117/12.2293807

KEYWORDS: Monte Carlo methods, Statistical analysis, Algorithm development, Binary data, Error analysis, Chromium, Computer simulations, Evolutionary algorithms, Computer aided diagnosis and therapy, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 6 March 2018 Paper

Paper

Tumor microenvironment for follicular lymphoma: structural analysis for outcome prediction

C. Senaras, M. Pennell, W. Chen, B. Sahiner, A. Shana’ah, A. Louissaint, R. Hasserjian, G. Lozanski, M. Gurcan

Proceedings Volume 10581, 1058106 (2018) https://doi.org/10.1117/12.2295284

KEYWORDS: Lymphoma, Tumors, Field emission displays, Lymphatic system, Tissues, Cancer, Structural analysis, Health informatics, Pathology, Systems modeling

Read Abstract +

Proceedings Article | 10 March 2017 Presentation + Paper

Presentation + Paper

Comparison of two classifiers when the data sets are imbalanced: the power of the area under the precision-recall curve as the figure of merit versus the area under the ROC curve

Berkman Sahiner, Weijie Chen, Aria Pezeshk, Nicholas Petrick

Proceedings Volume 10136, 101360G (2017) https://doi.org/10.1117/12.2254742

KEYWORDS: Content based image retrieval, Statistical modeling, Statistical methods, Electronic filtering, Statistical analysis, Receivers, Computer simulations, Medical imaging, Monte Carlo methods, Computer aided diagnosis and therapy, Image retrieval, Silver

Read Abstract +

Proceedings Article | 10 March 2017 Presentation + Paper

Presentation + Paper

Re-use of pilot data and interim analysis of pivotal data in MRMC studies: a simulation study

Weijie Chen, Frank Samuelson, Berkman Sahiner, Nicholas Petrick

Proceedings Volume 10136, 101360H (2017) https://doi.org/10.1117/12.2255029

KEYWORDS: Error analysis, Data modeling, Statistical analysis, Medical imaging, Imaging devices, Medical devices, Cancer, Instrument modeling, Performance modeling, Diagnostics, Monte Carlo methods, Computer simulations, Gold

Read Abstract +

Proceedings Article | 1 March 2017 Presentation + Paper

Presentation + Paper

FOXP3-stained image analysis for follicular lymphoma: optimal adaptive thresholding with maximal nucleus coverage

C. Senaras, M. Pennell, W. Chen, B. Sahiner, A. Shana’ah, A. Louissaint, R. Hasserjian, G. Lozanski, M. Gurcan

Proceedings Volume 10140, 101400E (2017) https://doi.org/10.1117/12.2255671

KEYWORDS: Image segmentation, Lymphoma, Tissues, Image analysis, Biopsy, Tumors, Detection and tracking algorithms, Pathology

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Paper

MRMC analysis of agreement studies

Brandon Gallas, Amrita Anam, Weijie Chen, Adam Wunderlich, Zhiwei Zhang

Proceedings Volume 9787, 97870F (2016) https://doi.org/10.1117/12.2217074

KEYWORDS: Medical imaging, Medical statistics, Clinical trials, Image quality, Imaging devices, Monte Carlo methods, Statistical analysis, Error analysis, Data modeling, Imaging systems, Silver

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Paper

Proper bibeta ROC model: algorithm, software, and performance evaluation

Weijie Chen, Nan Hu

Proceedings Volume 9787, 97870E (2016) https://doi.org/10.1117/12.2216777

KEYWORDS: Algorithm development, Performance modeling, Data modeling, Statistical modeling, Receivers, Statistical inference, Reliability, Optimization (mathematics), Statistical analysis, Monte Carlo methods, Mathematical modeling

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Paper

Semi-parametric estimation of the area under the precision-recall curve

Berkman Sahiner, Weijie Chen, Aria Pezeshk, Nicholas Petrick

Proceedings Volume 9787, 97870D (2016) https://doi.org/10.1117/12.2216434

KEYWORDS: Content based image retrieval, Systems modeling, Receivers, Binary data, Classification systems, Statistical analysis, Performance modeling, Statistical modeling, Data modeling, Monte Carlo methods, Medical imaging, Electronic filtering

Read Abstract +

Proceedings Article | 20 March 2015 Paper

Paper

Improving CAD performance by seamless insertion of pulmonary nodules in chest CT exams

Aria Pezeshk, Berkman Sahiner, Weijie Chen, Nicholas Petrick

Proceedings Volume 9414, 94140A (2015) https://doi.org/10.1117/12.2082200

KEYWORDS: CAD systems, Computer aided diagnosis and therapy, Medical imaging, Computed tomography, Chest, Computer aided design, Photonic integrated circuits, Target detection, Lung, Data modeling

Read Abstract +

Proceedings Article | 17 March 2015 Paper

Paper

Investigation of methods for calibration of classifier scores to probability of disease

Weijie Chen, Berkman Sahiner, Frank Samuelson, Aria Pezeshk, Nicholas Petrick

Proceedings Volume 9416, 94161E (2015) https://doi.org/10.1117/12.2082142

KEYWORDS: Statistical analysis, Calibration, Error analysis, Diagnostics, Computer simulations, Binary data, Monte Carlo methods, Computer aided diagnosis and therapy, Receivers, Imaging systems

Read Abstract +

Proceedings Article | 17 March 2015 Paper

Paper

Comparison of two stand-alone CADe systems at multiple operating points

Berkman Sahiner, Weijie Chen, Aria Pezeshk, Nicholas Petrick

Proceedings Volume 9416, 941612 (2015) https://doi.org/10.1117/12.2082123

KEYWORDS: Computer aided diagnosis and therapy, Selenium, Computer aided design, Error analysis, CAD systems, Statistical analysis, Computing systems, Binary data, Data analysis

Read Abstract +

SPIE Journal Paper | 30 December 2014 Open Access

Open Access

Special Section Guest Editorial: Pioneers in Medical Imaging: Honoring the Memory of Robert F. Wagner

Kyle Myers, Weijie Chen

JMI, Vol. 1, Issue 03, 031001, (December 2014) https://doi.org/10.1117/12.10.1117/1.JMI.1.3.031001

KEYWORDS: Medical imaging, Data modeling, Statistical analysis, Medical research, Computer aided diagnosis and therapy, Image quality, Binary data, Imaging systems, Breast cancer, Analytical research

SPIE Journal Paper | 4 December 2014

Multireader multicase reader studies with binary agreement data: simulation, analysis, validation, and sizing

Weijie Chen, Adam Wunderlich, Nicholas Petrick, Brandon Gallas

JMI, Vol. 1, Issue 03, 031011, (December 2014) https://doi.org/10.1117/12.10.1117/1.JMI.1.3.031011

KEYWORDS: Binary data, Data modeling, Statistical analysis, Monte Carlo methods, Error analysis, Diagnostics, Mathematical modeling, Performance modeling, Medical imaging, Data analysis

Read Abstract +

Proceedings Article | 27 March 2014 Paper

Paper

Seamless insertion of real pulmonary nodules in chest CT exams

Aria Pezeshk, Berkman Sahiner, Rongping Zeng, Adam Wunderlich, Weijie Chen, Nicholas Petrick

Proceedings Volume 9035, 90351K (2014) https://doi.org/10.1117/12.2043786

KEYWORDS: 3D acquisition, Image processing, Chest, Computer aided diagnosis and therapy, Lung, Computed tomography, Fourier transforms, Photon counting, 3D image processing, Image blending

Read Abstract +

Proceedings Article | 26 February 2013 Paper

Paper

Neural network training by maximization of the area under the ROC curve: application to characterization of masses on breast ultrasound as malignant or benign

Berkman Sahiner, Xin He, Weijie Chen, Heang-Ping Chan, Lubomir Hadjiiski, Nicholas Petrick

Proceedings Volume 8670, 86701M (2013) https://doi.org/10.1117/12.2007615

KEYWORDS: Neural networks, Breast, Ultrasonography, Artificial neural networks, Computer aided design, Computer aided diagnosis and therapy, Image segmentation, Evolutionary algorithms, Error analysis, Data acquisition

Read Abstract +

Back-propagation neural networks (BPNs) are traditionally trained using error measures such as sum-of-squares or cross-entropy. If the training sample size is small, and the neural network has a large number of hidden layer nodes, the BPN may be overtrained, i.e., it may fit the training data well, but may generalize poorly to independent test data. In this study, we investigated a training technique that maximized the approximate area under the ROC curve (AUC) to reduce overtraining. In general, the non-parametric AUC is a discontinuous and non-differentiable function of the neural network output, which makes it unsuitable for gradient descent algorithms such as back-propagation. We used a semidifferentiable approximation to AUC, which appeared to provide reasonable training for the data sets explored in this study. We performed a simulation study using synthetic data sets consisting of Gaussian mixtures to investigate the behavior of this new technique with respect to overtraining. Our results indicated that an artificial neural network trained using the AUC-maximization method is less prone to overtraining. The advantage of the AUC-maximization method was consistently observed over different values of hidden layer BPN nodes, training sample sizes, and the dimensionality of the feature spaces evaluated in our simulation study. For a five-hidden-node BPN trained using 50 training samples per class, the average test AUC was 0.896 (standard deviation (SD): 0.026) with AUC-maximization and 0.856 (SD: 0.028) with the sum-of-squares method. The gain in test performance by the AUC-maximization method over the traditional BPN training was greater when the training sample size was smaller. We also applied this new method to a data set previously acquired for characterization of masses on breast ultrasound as malignant or benign. Our results with this real-world data set had the same trend as with our simulation data sets in that the AUC-maximization technique was less prone to overtraining than the sum-of-squares method.

Proceedings Article | 3 March 2011 Paper

Paper

Agreement between two versions of a CADx system: a simulation study

Berkman Sahiner, Nicholas Petrick, Sophie Paquerault, Weijie Chen, Tien Nguyen

Proceedings Volume 7966, 79660J (2011) https://doi.org/10.1117/12.877727

KEYWORDS: Computer aided diagnosis and therapy, CAD systems, Computer aided design, Feature extraction, Computing systems, Matrices, Solid modeling, Systems modeling, Computer simulations, Algorithm development

Read Abstract +

Proceedings Article | 3 March 2011 Paper

Paper

Assessment of updated CAD without a new reader study: effect of calibration of computer output on the computer-aided reader performance in CADx

Weijie Chen, Nicholas Petrick, Berkman Sahiner

Proceedings Volume 7966, 79661P (2011) https://doi.org/10.1117/12.878278

KEYWORDS: Computer aided diagnosis and therapy, Calibration, CAD systems, Computer simulations, Computer aided design, Medical imaging, Image compression, Current controlled current source, Diagnostics, Performance modeling

Read Abstract +

Proceedings Article | 9 March 2010 Paper

Paper

Training variability in the evaluation of automated classifiers

Weijie Chen, Brandon Gallas

Proceedings Volume 7624, 762404 (2010) https://doi.org/10.1117/12.844605

KEYWORDS: Argon, Erbium, Data analysis, Medical imaging, Computer aided diagnosis and therapy, Statistical analysis, Current controlled current source, Autoregressive models, Computer aided design, Receivers

Read Abstract +

Proceedings Article | 13 March 2009 Paper

Paper

Comparison of classifier performance estimators: a simulation study

Weijie Chen, Robert Wagner, Waleed Yousef, Brandon Gallas

Proceedings Volume 7263, 72630X (2009) https://doi.org/10.1117/12.811584

KEYWORDS: Error analysis, Monte Carlo methods, Device simulation, Statistical analysis, Medical imaging, Image compression, Current controlled current source

Read Abstract +

Proceedings Article | 17 March 2008 Paper

Paper

Hybrid linear classifier for jointly normal data: theory

Weijie Chen, Charles Metz, Maryellen Giger

Proceedings Volume 6915, 691504 (2008) https://doi.org/10.1117/12.770326

KEYWORDS: Medical imaging, Computer aided diagnosis and therapy, Computer aided design, Statistical analysis, Matrices

Read Abstract +

Proceedings Article | 30 March 2007 Paper

Paper

Joint feature selection and classification using a Bayesian neural network with automatic relevance determination priors: potential use in CAD of medical imaging

Weijie Chen, Richard Zur, Maryellen Giger

Proceedings Volume 6514, 65141G (2007) https://doi.org/10.1117/12.710654

KEYWORDS: Feature selection, Neural networks, Computer aided diagnosis and therapy, Statistical analysis, Breast, Medical imaging, Magnetic resonance imaging, Computer aided design, Monte Carlo methods, Medical physics

Read Abstract +

Proceedings Article | 30 March 2007 Paper

Paper

Automatic selection of region of interest for radiographic texture analysis

Li Lan, Maryellen Giger, Joel Wilkie, Tamara Vokes, Weijie Chen, Hui Li, Tracy Lyons, Michael Chinander, Ann Pham

Proceedings Volume 6514, 651436 (2007) https://doi.org/10.1117/12.711531

KEYWORDS: Bone, Image segmentation, Image filtering, Edge detection, Binary data, X-ray imaging, Databases, Computer programming, Minerals, Analytical research

Read Abstract +

Proceedings Article | 10 March 2006 Paper

Paper

A novel strategy for segmentation of magnetic resonance (MR) images corrupted by intensity inhomogeneity artifacts

Weijie Chen, Maryellen Giger

Proceedings Volume 6144, 61441C (2006) https://doi.org/10.1117/12.653602

KEYWORDS: Image segmentation, Magnetic resonance imaging, Wavelets, Image processing algorithms and systems, Expectation maximization algorithms, Magnetism, Fuzzy logic, Breast, Quantitative analysis, Wavelet transforms

Read Abstract +

Proceedings Article | 12 May 2004 Paper

Paper

Automated identification of temporal pattern with high initial enhancement in dynamic MR lesions using fuzzy c-means algorithm

Weijie Chen, Maryellen Giger, Ulrich Bick

Proceedings Volume 5370, (2004) https://doi.org/10.1117/12.535619

KEYWORDS: Breast, Fuzzy logic, Magnetic resonance imaging, Breast cancer, Solids, Receivers, Tumors, Cancer, Databases, Image segmentation

Read Abstract +

Showing 5 of 46 publications

Proceedings Volume Editor (2)

SPIE Conference Volume | 12 April 2024

Medical Imaging 2024: Computer-Aided Diagnosis

SPIE Conference Volume | 4 May 2023

Medical Imaging 2023: Computer-Aided Diagnosis

Conference Committee Involvement (13)

Computer-Aided Diagnosis

17 February 2025 | San Diego, California, United States

Computer-Aided Diagnosis

19 February 2024 | San Diego, California, United States

Computer-Aided Diagnosis

20 February 2023 | San Diego, California, United States

Computer-Aided Diagnosis

21 February 2022 | San Diego, California, United States

Digital and Computational Pathology

20 February 2022 | San Diego, California, United States

Showing 5 of 13 Conference Committees

SIGN IN TO:

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

Advertisement

Advertisement