Prof. Weimin Zhou Profile

Prof. Weimin Zhou

Assistant Professor

SPIE Involvement:

Conference Program Committee | Author

Publications (28)

Proceedings Article | 2 April 2024 Poster + Paper

Unsupervised generation of pseudo normal PET from MRI with diffusion model for epileptic focus localization

Wentao Chen, Jiwei Li, Xichen Xu, Hui Huang, Siyu Yuan, Miao Zhang, Tianming Xu, Jie Luo, Weimin Zhou

Proceedings Volume 12930, 1293027 (2024) https://doi.org/10.1117/12.3008266

KEYWORDS: Positron emission tomography, Magnetic resonance imaging, Diffusion, Image processing, Epilepsy, Medical imaging, Image segmentation

Read Abstract +

Proceedings Article | 29 March 2024 Presentation + Paper

Ambient-Pix2PixGAN for translating medical images from noisy data

Wentao Chen, Xichen Xu, Jie Luo, Weimin Zhou

Proceedings Volume 12929, 129290H (2024) https://doi.org/10.1117/12.3008260

KEYWORDS: Medical imaging, Positron emission tomography, Signal to noise ratio, Image quality, Magnetic resonance imaging, Signal detection, Image processing, Data modeling

Read Abstract +

Proceedings Article | 29 March 2024 Poster + Paper

AmbientCycleGAN for establishing interpretable stochastic object models based on mathematical phantoms and medical imaging measurements

Xichen Xu, Wentao Chen, Weimin Zhou

Proceedings Volume 12929, 1292913 (2024) https://doi.org/10.1117/12.3008148

KEYWORDS: Mathematical modeling, Medical imaging, Stochastic processes, Mammography, Systems modeling, Signal detection, Imaging systems

Read Abstract +

SPIE Journal Paper | 26 September 2023 Open Access

Approximating the Hotelling observer with autoencoder-learned efficient channels for binary signal detection tasks

Jason Granstedt, Weimin Zhou, Mark Anastasio

JMI, Vol. 10, Issue 05, 055501, (September 2023) https://doi.org/10.1117/12.10.1117/1.JMI.10.5.055501

KEYWORDS: Education and training, Signal detection, Imaging systems, Signal attenuation, Breast, Binary data, Information operations, Image restoration, Image processing, Signal processing

Read Abstract +

PurposeThe objective assessment of image quality (IQ) has been advocated for the analysis and optimization of medical imaging systems. One method of computing such IQ metrics is through a numerical observer. The Hotelling observer (HO) is the optimal linear observer, but conventional methods for obtaining the HO can become intractable due to large image sizes or insufficient data. Channelized methods are sometimes employed in such circumstances to approximate the HO. The performance of such channelized methods varies, with different methods obtaining superior performance to others depending on the imaging conditions and detection task. A channelized HO method using an AE is presented and implemented across several tasks to characterize its performance.ApproachThe process for training an AE is demonstrated to be equivalent to developing a set of channels for approximating the HO. The efficiency of the learned AE-channels is increased by modifying the conventional AE loss function to incorporate task-relevant information. Multiple binary detection tasks involving lumpy and breast phantom backgrounds across varying dataset sizes are considered to evaluate the performance of the proposed method and compare to current state-of-the-art channelized methods. Additionally, the ability of the channelized methods to generalize to images outside of the training dataset is investigated.ResultsAE-learned channels are demonstrated to have comparable performance with other state-of-the-art channel methods in the detection studies and superior performance in the generalization studies. Incorporating a cleaner estimate of the signal for the detection task is also demonstrated to significantly improve the performance of the proposed method, particularly in datasets with fewer images.ConclusionsAEs are demonstrated to be capable of learning efficient channels for the HO. The resulting significant increase in detection performance for small dataset sizes when incorporating a signal prior holds promising implications for future assessments of imaging technologies.

DOWNLOAD PAPER

Proceedings Article | 3 April 2023 Presentation + Paper

Optimal visual search strategy with inter-saccade response correlations

Weimin Zhou, Miguel Eckstein

Proceedings Volume 12467, 1246705 (2023) https://doi.org/10.1117/12.2655817

KEYWORDS: Signal detection, Eye, Eye models, Visual system, Medical imaging, Background noise, Visual process modeling, Target detection

Read Abstract +

Proceedings Article | 3 April 2023 Presentation + Paper

Estimating task-based performance bounds for image reconstruction methods by use of learned-ideal observers

Kaiyan Li, Weimin Zhou, Hua Li, Mark Anastasio

Proceedings Volume 12467, 124670I (2023) https://doi.org/10.1117/12.2655241

KEYWORDS: Image restoration, Information operations, Signal detection, Imaging systems, Tomography, Stochastic processes, Binary data, Image quality, Education and training, X-ray computed tomography

Read Abstract +

Proceedings Article | 3 April 2023 Poster + Paper

Task-aware denoising autoencoders for establishing efficient channels

Weimin Zhou

Proceedings Volume 12467, 1246716 (2023) https://doi.org/10.1117/12.2654465

KEYWORDS: Signal detection, Denoising, Covariance matrices, Visual system, Medical imaging, Imaging systems, Image denoising

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

Analyzing neural networks applied to an anatomical simulation of the breast

Craig Abbey, Sourya Sengupta, Weimin Zhou, Andreu Badal, Rongping Zeng, Frank Samuelson, Miguel Eckstein, Kyle Myers, Mark Anastasio, Jovan Brankov

Proceedings Volume 12035, 1203505 (2022) https://doi.org/10.1117/12.2612614

KEYWORDS: Denoising, Neural networks, Breast, Data modeling, Digital breast tomosynthesis, Signal detection

Read Abstract +

Proceedings Article | 4 April 2022 Presentation + Paper

A deep Q-learning method for optimizing visual search strategies in backgrounds of dynamic noise

Weimin Zhou, Miguel Eckstein

Proceedings Volume 12035, 120350B (2022) https://doi.org/10.1117/12.2613133

KEYWORDS: Eye, Visual system, Signal detection, Visibility, Eye models, Visual process modeling, Neural networks, Medical imaging

Read Abstract +

SPIE Journal Paper | 23 February 2022 Open Access

Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks

Weimin Zhou, Sayantan Bhadra, Frank Brooks, Hua Li, Mark Anastasio

JMI, Vol. 9, Issue 01, 015503, (February 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.1.015503

KEYWORDS: Imaging systems, Medical imaging, Gallium nitride, Stochastic processes, Magnetic resonance imaging, Signal to noise ratio, Statistical modeling, Data acquisition, Systems modeling, Visualization

Read Abstract +

DOWNLOAD PAPER

Proceedings Article | 15 February 2021 Presentation + Paper

SlabGAN: a method for generating efficient 3D anisotropic medical volumes using generative adversarial networks

Jason Granstedt, Varun Kelkar, Weimin Zhou, Mark Anastasio

Proceedings Volume 11596, 1159617 (2021) https://doi.org/10.1117/12.2581380

KEYWORDS: Gallium nitride, 3D image processing, Medical imaging, Magnetic resonance imaging, Super resolution, Stochastic processes, Neuroimaging, Medical image reconstruction, Imaging systems, Image restoration

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

A hybrid channelized Hotelling observer for estimating the ideal linear observer for total-variation-based image reconstruction

John Paul Phillips, Emil Sidky, Greg Ongie, Weimin Zhou, Juan Cruz-Bastida, Ingrid Reiser, Mark Anastasio, Xiaochuan Pan

Proceedings Volume 11599, 115990D (2021) https://doi.org/10.1117/12.2581248

KEYWORDS: Image restoration, Signal detection, Reconstruction algorithms, Nonlinear optics, X-ray computed tomography, Optimization (mathematics), Medical imaging, Image quality, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Advancing the AmbientGAN for learning stochastic object models

Weimin Zhou, Sayantan Bhadra, Frank Brooks, Jason Granstedt, Hua Li, Mark Anastasio

Proceedings Volume 11599, 115990A (2021) https://doi.org/10.1117/12.2581687

KEYWORDS: Systems modeling, Stochastic processes, Imaging systems, 3D image processing, Gallium nitride, 3D metrology, Stereoscopy, Network architectures, Medical imaging, Magnetic resonance imaging

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Supervised learning-based ideal observer approximation for joint detection and estimation tasks

Kaiyan Li, Weimin Zhou, Hua Li, Mark Anastasio

Proceedings Volume 11599, 115990F (2021) https://doi.org/10.1117/12.2582327

KEYWORDS: Information operations, Imaging systems, Monte Carlo methods, Machine learning, Convolutional neural networks, Computer simulations

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Task-based performance evaluation of deep neural network-based image denoising

Kaiyan Li, Weimin Zhou, Hua Li, Mark Anastasio

Proceedings Volume 11599, 115990L (2021) https://doi.org/10.1117/12.2582324

KEYWORDS: Neural networks, Image denoising, Denoising, Signal detection, Surgery, Signal attenuation, Quality measurement, Medical imaging applications, Medical imaging, Information operations

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Learning numerical observers using unsupervised domain adaptation

Shenghua He, Weimin Zhou, Hua Li, Mark Anastasio

Proceedings Volume 11316, 113160W (2020) https://doi.org/10.1117/12.2549812

KEYWORDS: Signal detection, Imaging systems, Image quality, Neural networks, Medical imaging

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Learning efficient channels with a dual loss autoencoder

Jason Granstedt, Weimin Zhou, Mark Anastasio

Proceedings Volume 11316, 113160C (2020) https://doi.org/10.1117/12.2549363

KEYWORDS: Neural networks, Signal detection, Imaging systems, Signal to noise ratio, Breast, Performance modeling, Image quality

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Markov-Chain Monte Carlo approximation of the Ideal Observer using generative adversarial networks

Weimin Zhou, Mark Anastasio

Proceedings Volume 11316, 113160D (2020) https://doi.org/10.1117/12.2549732

KEYWORDS: Signal detection, Monte Carlo methods, Imaging systems, Statistical analysis, Systems modeling, Stochastic processes, Performance modeling

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Medical image reconstruction with image-adaptive priors learned by use of generative adversarial networks

Sayantan Bhadra, Weimin Zhou, Mark Anastasio

Proceedings Volume 11312, 113120V (2020) https://doi.org/10.1117/12.2549750

KEYWORDS: Magnetic resonance imaging, Data modeling, Inverse problems, Medical image reconstruction, Reconstruction algorithms, Image restoration, Medical diagnostics, Imaging systems

Read Abstract +

Medical image reconstruction is often an ill-posed inverse problem. In order to address such ill-posed inverse problems, prior knowledge of the sought after object property is usually incorporated by means of regularization. For example, sparsity-promoting regularization in a suitable transform domain is widely used to reconstruct images with diagnostic quality from noisy and/or incomplete medical data. However, sparsity-promoting regularization may not be able to comprehensively describe the actual prior information of the objects being imaged. Deep generative models, such as generative adversarial networks (GANs) have shown great promise in learning the underlying distribution of images. Prior distributions for images estimated using GANs have been employed as a means of regularization with impressive results in several linear inverse problems in computer vision that are also relevant to medical imaging. However, in practice, it can be difficult for a GAN to comprehensively describe prior distributions, which can potentially lead to a lack of fidelity between the reconstructed image and the observed data. Recently, an image-adaptive GAN-based reconstruction method (IAGAN) was proposed to guarantee stronger data consistency by adapting the trained generative model parameters to the observed measurements. In this work, for the first time, we apply the IAGAN method to reconstruct images from undersampled magnetic resonance imaging (MRI) measurements. A state-of-the-art GAN model called Progressive Growing of GANs (ProGAN) was trained on a large number of ground truth images from the NYU fastMRI dataset, and the learned generator was subsequently employed in the IAGAN framework to reconstruct high fidelity images from retrospectively undersampled experimental k-space data in the validation dataset. It is demonstrated that by use of the GAN-based reconstruction method with noisy and/or incomplete measurements, we can potentially recover fine structures in the object that are relevant for medical diagnosis that may be difficult to achieve using traditional reconstruction methods relying on sparsity-promoting penalties.

Proceedings Article | 16 March 2020 Presentation + Paper

Progressively-Growing AmbientGANs for learning stochastic object models from imaging measurements

Weimin Zhou, Sayantan Bhadra, Frank Brooks, Hua Li, Mark Anastasio

Proceedings Volume 11316, 113160Q (2020) https://doi.org/10.1117/12.2549610

KEYWORDS: Magnetic resonance imaging, Imaging systems, Signal detection, Stochastic processes, Neuroimaging, Brain, Data modeling, Systems modeling

Read Abstract +

Proceedings Article | 4 March 2019 Presentation + Paper

Autoencoder embedding of task-specific information

Jason Granstedt, Weimin Zhou, Mark Anastasio

Proceedings Volume 10952, 1095207 (2019) https://doi.org/10.1117/12.2513120

KEYWORDS: Computer programming, Signal detection, Statistical analysis, Imaging systems, Targeting Task Performance metric, Machine learning, Image processing algorithms and systems

Read Abstract +

Proceedings Article | 4 March 2019 Presentation + Paper

Learning the ideal observer for joint detection and localization tasks by use of convolutional neural networks

Weimin Zhou, Mark Anastasio

Proceedings Volume 10952, 1095209 (2019) https://doi.org/10.1117/12.2513016

KEYWORDS: Signal detection, Convolutional neural networks, Binary data, Medical imaging, Imaging systems, Quality measurement, Image quality

Read Abstract +

Proceedings Article | 4 March 2019 Presentation + Paper

Learning stochastic object model from noisy imaging measurements using AmbientGANs

Weimin Zhou, Sayantan Bhadra, Frank Brooks, Mark Anastasio

Proceedings Volume 10952, 109520M (2019) https://doi.org/10.1117/12.2512633

KEYWORDS: Signal detection, Stochastic processes, Imaging systems, Radon transform, Image processing, Tomography, Statistical modeling

Read Abstract +

Proceedings Article | 4 March 2019 Presentation + Paper

Learning the Hotelling observer for SKE detection tasks by use of supervised learning methods

Weimin Zhou, Hua Li, Mark Anastasio

Proceedings Volume 10952, 1095208 (2019) https://doi.org/10.1117/12.2512607

KEYWORDS: Signal detection, Statistical analysis, Binary data, Machine learning, Signal to noise ratio, Information operations, Matrices, Quality measurement, Image quality, Medical imaging

Read Abstract +

Proceedings Article | 14 May 2018 Presentation

Development of computed phase-sensitive x-ray imaging technologies for pre-clinical science (Conference Presentation)

Mark Anastasio, Frank Brooks, Sergey Komarov, Yujia Chen, Weimin Zhou

Proceedings Volume 10632, 106320I (2018) https://doi.org/10.1117/12.2309429

KEYWORDS: X-ray imaging, X-ray technology, X-rays, Tissues, 3D image processing, Refractive index, Coherence imaging, Image acquisition, Tomography, In vivo imaging

Read Abstract +

Proceedings Article | 9 March 2018 Presentation + Paper

Joint-reconstruction-enabled data acquisition design for single-shot edge-illumination x-ray phase-contrast tomography

Yujia Chen, Weimin Zhou, Mark Anastasio

Proceedings Volume 10573, 1057322 (2018) https://doi.org/10.1117/12.2293621

KEYWORDS: Tomography, Data acquisition, X-rays, Reconstruction algorithms, Image restoration, Refractive index, Image quality, X-ray technology, X-ray imaging

Read Abstract +

Proceedings Article | 7 March 2018 Paper

Learning the ideal observer for SKE detection tasks by use of convolutional neural networks (Cum Laude Poster Award)

Weimin Zhou, Mark Anastasio

Proceedings Volume 10577, 1057719 (2018) https://doi.org/10.1117/12.2293772

KEYWORDS: Statistical analysis, Data modeling, Binary data, Signal detection, Convolutional neural networks, Machine learning, Monte Carlo methods, Medical imaging, Image processing

Read Abstract +

SPIE Journal Paper | 31 January 2017 Open Access

Generation of anatomically realistic numerical phantoms for photoacoustic and ultrasonic breast imaging

Yang Lou, Weimin Zhou, Thomas Matthews, Catherine Appleton, Mark Anastasio

JBO, Vol. 22, Issue 04, 041015, (January 2017) https://doi.org/10.1117/12.10.1117/1.JBO.22.4.041015

KEYWORDS: Breast, Skin, Photoacoustic tomography, Tissues, Tissue optics, Acoustics, Breast imaging, Binary data, Magnetic resonance imaging, Ultrasonics

Read Abstract +

DOWNLOAD PAPER

Showing 5 of 28 publications

Conference Committee Involvement (2)

Image Perception, Observer Performance, and Technology Assessment

17 February 2025 | San Diego, California, United States

Image Perception, Observer Performance, and Technology Assessment

20 February 2024 | San Diego, California, United States

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