Xiaoliu Zhang

Bio: Xiaoliu Zhang is an academic researcher from University of Iowa. The author has contributed to research in topics: Bone mineral & Image restoration. The author has an hindex of 4, co-authored 14 publications receiving 277 citations.

CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE)

Abstract: In this paper, we present a semi-supervised deep learning approach to accurately recover high-resolution (HR) CT images from low-resolution (LR) counterparts. Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs. We also include the joint constraints in the loss function to facilitate structural preservation. In this process, we incorporate deep convolutional neural network (CNN), residual learning, and network in network techniques for feature extraction and restoration. In contrast to the current trend of increasing network depth and complexity to boost the imaging performance, we apply a parallel ${1}\times {1}$ CNN to compress the output of the hidden layer and optimize the number of layers and the number of filters for each convolutional layer. The quantitative and qualitative evaluative results demonstrate that our proposed model is accurate, efficient and robust for super-resolution (SR) image restoration from noisy LR input images. In particular, we validate our composite SR networks on three large-scale CT datasets, and obtain promising results as compared to the other state-of-the-art methods.

CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)

Abstract: Computed tomography (CT) is widely used in screening, diagnosis, and image-guided therapy for both clinical and research purposes. Since CT involves ionizing radiation, an overarching thrust of related technical research is development of novel methods enabling ultrahigh quality imaging with fine structural details while reducing the X-ray radiation. In this paper, we present a semi-supervised deep learning approach to accurately recover high-resolution (HR) CT images from low-resolution (LR) counterparts. Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs. We also include the joint constraints in the loss function to facilitate structural preservation. In this deep imaging process, we incorporate deep convolutional neural network (CNN), residual learning, and network in network techniques for feature extraction and restoration. In contrast to the current trend of increasing network depth and complexity to boost the CT imaging performance, which limit its real-world applications by imposing considerable computational and memory overheads, we apply a parallel $1\times1$ CNN to compress the output of the hidden layer and optimize the number of layers and the number of filters for each convolutional layer. Quantitative and qualitative evaluations demonstrate that our proposed model is accurate, efficient and robust for super-resolution (SR) image restoration from noisy LR input images. In particular, we validate our composite SR networks on three large-scale CT datasets, and obtain promising results as compared to the other state-of-the-art methods.

Quantitative imaging of peripheral trabecular bone microarchitecture using MDCT

Abstract: Purpose Osteoporosis associated with reduced bone mineral density (BMD) and micro-architectural changes puts patients at an elevated risk of fracture. Modern multi detector-row CT (MDCT) technology, producing high spatial resolution at increasingly lower dose radiation, is emerging as a viable modality for trabecular bone (Tb) imaging. Wide variation in CT scanners raise concerns of data uniformity in multi-site and longitudinal studies. A comprehensive cadaveric study was performed to evaluate MDCT-derived Tb micro-architectural measures. A human pilot study was performed comparing continuity of Tb measures estimated from two MDCT scanners with significantly different image resolution features. Method Micro-CT imaging of cadaveric ankle specimens (n = 25) was used to examine the validity of MDCT-derived Tb micro-architectural measures. Repeat scan reproducibility of MDCT-based Tb measures and their ability to predict mechanical properties were examined. To assess multi-scanner data continuity of Tb measures, the distal tibias of twenty volunteers (age: 26.2 ± 4.5 Y,10 F) were scanned using the Siemens SOMATOM Definition Flash and the higher resolution Siemens SOMATOM Force scanners with an average 45-day time gap between scans. The correlation of Tb measures derived from the two scanners over 30 and 60% peel regions at the 4 to 8% of distal tibia was analyzed. Results MDCT-based Tb measures characterizing bone network area density, plate-rod micro-architecture, and transverse trabeculae showed good correlations (r ∈ [0.85,0.92]) with the gold standard micro-CT derived values of matching Tb measures. However, other MDCT-derived Tb measures characterizing trabecular thickness and separation, erosion index, and structure model index produced weak correlation (r 0.95) between values estimated from the two scanners. Relatively lower correlation coefficients were observed for the bone network area density (r = 0.91) and Tb separation (r = 0.93) measures. Conclusion Most MDCT-derived Tb micro-architectural measures are reproducible and their values derived from two scanners strongly correlate with each other as well as with bone strength. This study has highlighted those MDCT-derived measures which show the greatest promise for characterization of bone network area density, plate-rod and transverse trabecular distributions with a good correlation (r ≥ 0.85) compared with their micro-CT derived values. At the same time, other measures representing trabecular thickness and separation, erosion index, and structure model index produced weak correlations (r < 0.8) with their micro-CT derived values, failing to accurately portray the projected trabecular micro-architectural features. Strong correlations of Tb measures estimated from two scanners suggests that image data from different scanners can be used successfully in multi-site and longitudinal studies with linear calibration required for some measures. In summary, modern MDCT scanners are suitable for effective quantitative imaging of peripheral Tb micro-architecture if care is taken to focus on appropriate quantitative metrics. This article is protected by copyright. All rights reserved.

Deep Learning Based High-Resolution Reconstruction of Trabecular Bone Microstructures from Low-Resolution CT Scans using GAN-CIRCLE.

Abstract: Osteoporosis is a common age-related disease characterized by reduced bone density and increased fracture-risk. Microstructural quality of trabecular bone (Tb), commonly found at axial skeletal sites and at the end of long bones, is an important determinant of bone-strength and fracture-risk. High-resolution emerging CT scanners enable in vivo measurement of Tb microstructures at peripheral sites. However, resolution-dependence of microstructural measures and wide resolution-discrepancies among various CT scanners together with rapid upgrades in technology warrant data harmonization in CT-based cross-sectional and longitudinal bone studies. This paper presents a deep learning-based method for high-resolution reconstruction of Tb microstructures from low-resolution CT scans using GAN-CIRCLE. A network was developed and evaluated using post-registered ankle CT scans of nineteen volunteers on both low- and highresolution CT scanners. 9,000 matching pairs of low- and high-resolution patches of size 64×64 were randomly harvested from ten volunteers for training and validation. Another 5,000 matching pairs of patches from nine other volunteers were used for evaluation. Quantitative comparison shows that predicted high-resolution scans have significantly improved structural similarity index (p < 0.01) with true high-resolution scans as compared to the same metric for low-resolution data. Different Tb microstructural measures such as thickness, spacing, and network area density are also computed from low- and predicted high-resolution images, and compared with the values derived from true high-resolution scans. Thickness and network area measures from predicted images showed higher agreement with true high-resolution CT (CCC = [0.95, 0.91]) derived values than the same measures from low-resolution images (CCC = [0.72, 0.88]).

A comparative study of trabecular bone micro-structural measurements using different CT modalities.

Abstract: Osteoporosis, characterized by reduced bone mineral density and micro-architectural degeneration, significantly enhances fracture-risk. There are several viable methods for trabecular bone micro-imaging, which widely vary in terms of technology, reconstruction principle, spatial resolution, and acquisition time. We have performed an excised cadaveric bone specimen study to evaluate different CT-imaging modalities for trabecular bone micro-structural analysis. Excised cadaveric bone specimens from the distal radius were scanned using micro-CT and four in vivo CT imaging modalities: HR-pQCT, dental CBCT, whole-body MDCT, and extremity CBCT. A new algorithm was developed to optimize soft thresholding parameters for individual in vivo CT modalities for computing quantitative bone volume fraction maps. Finally, agreement of trabecular bone micro-structural measures, derived from different in vivo CT imaging, with reference measures from micro-CT imaging was examined. Observed values of most trabecular measures, including trabecular bone volume, network area, transverse and plate-rod micro-structure, thickness, and spacing, for in vivo CT modalities were higher than their micro-CT-based reference values. In general, HR-pQCT-based trabecular bone measures were closer to their reference values as compared to other in vivo CT modalities. Despite large differences in observed values of measures among modalities, high linear correlation (r ∈ [0.94 0.99]) was found between micro-CT and in vivo CT-derived measures of trabecular bone volume, transverse and plate micro-structural volume, and network area. All HR-pQCT-derived trabecular measures, except the erosion index, showed high correlation (r ∈ [0.91 0.99]). The plate-width measure showed a higher correlation (r ∈ [0.72 0.91]) among in vivo and micro-CT modalities than its counterpart binary plate-rod characterization-based measure erosion index (r ∈ [0.65 0.81]). Although a strong correlation was observed between micro-structural measures from in vivo and micro-CT imaging, large shifts in their values for in vivo modalities warrant proper scanner calibration prior to adopting in multi-site and longitudinal studies.

Solving inverse problems using data-driven models

Abstract: Recent research in inverse problems seeks to develop a mathematically coherent foundation for combining data-driven models, and in particular those based on deep learning, with domain-specific knowledge contained in physical–analytical models. The focus is on solving ill-posed inverse problems that are at the core of many challenging applications in the natural sciences, medicine and life sciences, as well as in engineering and industrial applications. This survey paper aims to give an account of some of the main contributions in data-driven inverse problems.

CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE)

Abstract: In this paper, we present a semi-supervised deep learning approach to accurately recover high-resolution (HR) CT images from low-resolution (LR) counterparts. Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs. We also include the joint constraints in the loss function to facilitate structural preservation. In this process, we incorporate deep convolutional neural network (CNN), residual learning, and network in network techniques for feature extraction and restoration. In contrast to the current trend of increasing network depth and complexity to boost the imaging performance, we apply a parallel ${1}\times {1}$ CNN to compress the output of the hidden layer and optimize the number of layers and the number of filters for each convolutional layer. The quantitative and qualitative evaluative results demonstrate that our proposed model is accurate, efficient and robust for super-resolution (SR) image restoration from noisy LR input images. In particular, we validate our composite SR networks on three large-scale CT datasets, and obtain promising results as compared to the other state-of-the-art methods.

CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)

Abstract: Computed tomography (CT) is widely used in screening, diagnosis, and image-guided therapy for both clinical and research purposes. Since CT involves ionizing radiation, an overarching thrust of related technical research is development of novel methods enabling ultrahigh quality imaging with fine structural details while reducing the X-ray radiation. In this paper, we present a semi-supervised deep learning approach to accurately recover high-resolution (HR) CT images from low-resolution (LR) counterparts. Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs. We also include the joint constraints in the loss function to facilitate structural preservation. In this deep imaging process, we incorporate deep convolutional neural network (CNN), residual learning, and network in network techniques for feature extraction and restoration. In contrast to the current trend of increasing network depth and complexity to boost the CT imaging performance, which limit its real-world applications by imposing considerable computational and memory overheads, we apply a parallel $1\times1$ CNN to compress the output of the hidden layer and optimize the number of layers and the number of filters for each convolutional layer. Quantitative and qualitative evaluations demonstrate that our proposed model is accurate, efficient and robust for super-resolution (SR) image restoration from noisy LR input images. In particular, we validate our composite SR networks on three large-scale CT datasets, and obtain promising results as compared to the other state-of-the-art methods.