DATA-DRIVEN IMAGING GEOMETRIC RECOVERY OF ULTRAHIGH RESOLUTION ROBOTIC MICRO-CT FOR IN-VIVO AND OTHER APPLICATIONS.

We introduce an ultrahigh-resolution (50µm) robotic micro-CT design for localized imaging of carotid plaques using robotic arms, cutting-edge detector, and machine learning technologies. To combat geometric error-induced artifacts in interior CT scans, we propose a data-driven geometry estimation method that maximizes the consistency between projection data and the reprojection counterparts of a reconstructed volume. Particularly, we use a normalized cross correlation metric to overcome the projection truncation effect. Our approach is validated on a robotic CT scan of a sacrificed mouse and a micro-CT phantom scan, both producing sharper images with finer details than that prior correction.

Contrast-enhanced photon-counting micro-CT of tumor xenograft models.

OBJECTIVE: Photon-counting micro-computed tomography (micro-CT) is a major advance in small animal preclinical imaging. Small molecule- and nanoparticle-based contrast agents have been widely used to enable the differentiation of liver tumors from surrounding tissues using photon-counting micro-CT. However, there is a notable gap in the application of these market-available agents to the imaging of breast and ovarian tumors using photon-counting micro-CT. Herein, we have used photon-counting micro-CT to determine the effectiveness of these contrast agents in differentiating ovarian and breast tumor xenografts in live, intact mice. Approach. Nude mice carrying different types of breast and ovarian tumor xenografts (AU565, MDA-MB-231 and SKOV-3 human cancer cells) were injected with ISOVUE-370 (a small molecule-based agent) or Exitrone Nano 12000 (a nanoparticle-based agent) and subjected to photon-counting micro-CT. To improve tumor visualization using photon-counting micro-CT, we developed a novel color visualization method, which changes color tones to highlight contrast media distribution, offering a robust alternative to traditional material decomposition methods with less computational demand. Main results. Our in vivo experiments confirm the effectiveness of this color visualization approach, showing distinct enhancement characteristics for each contrast agent. Qualitative and quantitative analyses suggest that Exitrone Nano 12000 provides superior vasculature enhancement and better quantitative consistency across scans, while ISOVUE-370 delivers a more comprehensive tumor enhancement but with significant variance between scans due to its short blood half-time. Further, a paired t-test on mean and standard deviation values within tumor volumes showed significant differences between the AU565 and SKOV-3 tumor models with the nanoparticle-based contrast agent (p-values < 0.02), attributable to their distinct vascularity, as confirmed by immunohistochemical analysis. Significance. These findings underscore the utility of photon-counting micro-CT in non-invasively assessing the morphology and anatomy of different tumor xenografts, which is crucial for tumor characterization and longitudinal monitoring of tumor progression and response to treatments. .

Deep Few-view High-resolution Photon-counting Extremity CT at Halved Dose for a Clinical Trial.

The latest X-ray photon-counting computed tomography (PCCT) for extremity allows multi-energy high-resolution (HR) imaging for tissue characterization and material decomposition. However, both radiation dose and imaging speed need improvement for contrast-enhanced and other studies. Despite the success of deep learning methods for 2D few-view reconstruction, applying them to HR volumetric reconstruction of extremity scans for clinical diagnosis has been limited due to GPU memory constraints, training data scarcity, and domain gap issues. In this paper, we propose a deep learning-based approach for PCCT image reconstruction at halved dose and doubled speed in a New Zealand clinical trial. Particularly, we present a patch-based volumetric refinement network to alleviate the GPU memory limitation, train network with synthetic data, and use model-based iterative refinement to bridge the gap between synthetic and real-world data. The simulation and phantom experiments demonstrate consistently improved results under different acquisition conditions on both in- and off-domain structures using a fixed network. The image quality of 8 patients from the clinical trial are evaluated by three radiologists in comparison with the standard image reconstruction with a full-view dataset. It is shown that our proposed approach is essentially identical to or better than the clinical benchmark in terms of diagnostic image quality scores. Our approach has a great potential to improve the safety and efficiency of PCCT without compromising image quality.

Systematic Review on Learning-based Spectral CT.

Spectral computed tomography (CT) has recently emerged as an advanced version of medical CT and significantly improves conventional (single-energy) CT. Spectral CT has two main forms: dual-energy computed tomography (DECT) and photon-counting computed tomography (PCCT), which offer image improvement, material decomposition, and feature quantification relative to conventional CT. However, the inherent challenges of spectral CT, evidenced by data and image artifacts, remain a bottleneck for clinical applications. To address these problems, machine learning techniques have been widely applied to spectral CT. In this review, we present the state-of-the-art data-driven techniques for spectral CT.

Deep-silicon photon-counting x-ray projection denoising through reinforcement learning.

BACKGROUND: In recent years, deep reinforcement learning (RL) has been applied to various medical tasks and produced encouraging results. OBJECTIVE: In this paper, we demonstrate the feasibility of deep RL for denoising simulated deep-silicon photon-counting CT (PCCT) data in both full and interior scan modes. PCCT offers higher spatial and spectral resolution than conventional CT, requiring advanced denoising methods to suppress noise increase. METHODS: In this work, we apply a dueling double deep Q network (DDDQN) to denoise PCCT data for maximum contrast-to-noise ratio (CNR) and a multi-agent approach to handle data non-stationarity. RESULTS: Using our method, we obtained significant image quality improvement for single-channel scans and consistent improvement for all three channels of multichannel scans. For the single-channel interior scans, the PSNR (dB) and SSIM increased from 33.4078 and 0.9165 to 37.4167 and 0.9790 respectively. For the multichannel interior scans, the channel-wise PSNR (dB) increased from 31.2348, 30.7114, and 30.4667 to 31.6182, 30.9783, and 30.8427 respectively. Similarly, the SSIM improved from 0.9415, 0.9445, and 0.9336 to 0.9504, 0.9493, and 0.0326 respectively. CONCLUSIONS: Our results show that the RL approach improves image quality effectively, efficiently, and consistently across multiple spectral channels and has great potential in clinical applications.

Contrast-enhanced photon-counting micro-CT of tumor xenograft models.

Photon-counting micro computed tomography (micro-CT) offers new potential in preclinical imaging, particularly in distinguishing materials. It becomes especially helpful when combined with contrast agents, enabling the differentiation of tumors from surrounding tissues. There are mainly two types of contrast agents in the market for micro-CT: small molecule-based and nanoparticle-based. However, despite their widespread use in liver tumor studies, there is a notable gap in research on the application of these commercially available agents for photon-counting micro-CT in breast and ovarian tumors. Herein, we explored the effectiveness of these agents in differentiating tumor xenografts from various origins (AU565, MDA-MB-231, and SKOV-3) in nude mice, using photon-counting micro-CT. Specifically, ISOVUE-370 (a small molecule-based agent) and Exitrone Nano 12000 (a nanoparticle-based agent) were investigated in this context. To improve tumor visualization, we proposed a novel color visualization method for photon-counting micro-CT, which changes color tones to highlight contrast media distribution, offering a robust alternative to traditional material decomposition methods with less computational demand. Our in vivo experiments confirm its effectiveness, showing distinct enhancement characteristics for each contrast agent. Qualitative and quantitative analyses suggested that Exitrone Nano 12000 provides superior vasculature enhancement and better quantitative consistency across scans, while ISOVUE-370 gives more comprehensive tumor enhancement but with a significant variance between scans due to its short blood half-time. This variability leads to high sensitivity to timing and individual differences among mice. Further, a paired t-test on mean and standard deviation values within tumor volumes showed significant differences between the AU565 and SKOV-3 tumor models with the nanoparticle-based (p-values < 0.02), attributable to their distinct vascularity, as confirmed by immunohistochemistry. These findings underscore the utility of photon-counting micro-CT in non-invasively assessing the morphology and anatomy of different tumor xenografts, which is crucial for tumor characterization and longitudinal monitoring of tumor development and response to treatments.

Systematic Review on Learning-based Spectral CT.

Spectral computed tomography (CT) has recently emerged as an advanced version of medical CT and significantly improves conventional (single-energy) CT. Spectral CT has two main forms: dual-energy computed tomography (DECT) and photon-counting computed tomography (PCCT), which offer image improvement, material decomposition, and feature quantification relative to conventional CT. However, the inherent challenges of spectral CT, evidenced by data and image artifacts, remain a bottleneck for clinical applications. To address these problems, machine learning techniques have been widely applied to spectral CT. In this review, we present the state-of-the-art data-driven techniques for spectral CT.

On Expressivity and Trainability of Quadratic Networks.

Inspired by the diversity of biological neurons, quadratic artificial neurons can play an important role in deep learning models. The type of quadratic neurons of our interest replaces the inner-product operation in the conventional neuron with a quadratic function. Despite promising results so far achieved by networks of quadratic neurons, there are important issues not well addressed. Theoretically, the superior expressivity of a quadratic network over either a conventional network or a conventional network via quadratic activation is not fully elucidated, which makes the use of quadratic networks not well grounded. In practice, although a quadratic network can be trained via generic backpropagation, it can be subject to a higher risk of collapse than the conventional counterpart. To address these issues, we first apply the spline theory and a measure from algebraic geometry to give two theorems that demonstrate better model expressivity of a quadratic network than the conventional counterpart with or without quadratic activation. Then, we propose an effective training strategy referred to as referenced linear initialization (ReLinear) to stabilize the training process of a quadratic network, thereby unleashing the full potential in its associated machine learning tasks. Comprehensive experiments on popular datasets are performed to support our findings and confirm the performance of quadratic deep learning. We have shared our code in https://github.com/FengleiFan/ReLinear.

Exploring Restrictions to use of community greenways for physical activity through structural equation modeling.

Public health problems caused by rapid urbanization have attracted increasing amounts of attention. Existing studies show that improving the frequency and duration of physical activity among urban residents can effectively reduce their disease risk. A community greenway, as a green space for public activity directly serving community residents, is one of the best spatial place for bringing health benefits to people. Although the scale and scope of greenway construction have been increasing in recent years, the utilization rate of some greenways is not high for various reasons, restricting the extent to which people engage in healthy physical activities in greenway spaces. In this study, the greenway of Nancheng Community in Wenjiang District, Chengdu city, China was selected as the object of study, and structural equation modeling was conducted to explore the objective environmental factors and individual characteristics acting as barriers to use of the community greenway by the population for physical activity. The results show that user experience, the greenway landscape, and safety and accessibility are important factors that restrict people's willingness engage in physical activity in the community greenway environment. The results of this study provide a direction for further consideration of ways to enhance people's willingness to make use of greenways for physical activity, and further provide a theoretical basis for the healthy design and transformation of community greenway spaces.

Noise Suppression With Similarity-Based Self-Supervised Deep Learning.

Image denoising is a prerequisite for downstream tasks in many fields. Low-dose and photon-counting computed tomography (CT) denoising can optimize diagnostic performance at minimized radiation dose. Supervised deep denoising methods are popular but require paired clean or noisy samples that are often unavailable in practice. Limited by the independent noise assumption, current self-supervised denoising methods cannot process correlated noises as in CT images. Here we propose the first-of-its-kind similarity-based self-supervised deep denoising approach, referred to as Noise2Sim, that works in a nonlocal and nonlinear fashion to suppress not only independent but also correlated noises. Theoretically, Noise2Sim is asymptotically equivalent to supervised learning methods under mild conditions. Experimentally, Nosie2Sim recovers intrinsic features from noisy low-dose CT and photon-counting CT images as effectively as or even better than supervised learning methods on practical datasets visually, quantitatively and statistically. Noise2Sim is a general self-supervised denoising approach and has great potential in diverse applications.

Photon-counting computed tomography thermometry via material decomposition and machine learning.

Thermal ablation procedures, such as high intensity focused ultrasound and radiofrequency ablation, are often used to eliminate tumors by minimally invasively heating a focal region. For this task, real-time 3D temperature visualization is key to target the diseased tissues while minimizing damage to the surroundings. Current computed tomography (CT) thermometry is based on energy-integrated CT, tissue-specific experimental data, and linear relationships between attenuation and temperature. In this paper, we develop a novel approach using photon-counting CT for material decomposition and a neural network to predict temperature based on thermal characteristics of base materials and spectral tomographic measurements of a volume of interest. In our feasibility study, distilled water, 50 mmol/L CaCl2, and 600 mmol/L CaCl2 are chosen as the base materials. Their attenuations are measured in four discrete energy bins at various temperatures. The neural network trained on the experimental data achieves a mean absolute error of 3.97 °C and 1.80 °C on 300 mmol/L CaCl2 and a milk-based protein shake respectively. These experimental results indicate that our approach is promising for handling non-linear thermal properties for materials that are similar or dissimilar to our base materials.

Estimating optical parameters of biological tissues with photon-counting micro-CT.

Wavelength-dependent absorption and scattering properties determine the fluorescence photon transport in biological tissues and image resolution of optical molecular tomography. Currently, these parameters are computed from optically measured data. For small animal imaging, estimation of optical parameters is a large-scale optimization problem, which is highly ill-posed. In this paper, we propose a new, to the best of our knowledge, approach to estimate optical parameters of biological tissues with photon-counting micro-computed tomography (micro-CT). From photon-counting x-ray data, multi-energy micro-CT images can be reconstructed to perform multi-organ segmentation and material decomposition in terms of tissue constituents. The concentration and characteristics of major tissue constituents can be utilized to calculate the optical absorption and scattering coefficients of the involved tissues. In our study, we perform numerical simulation, phantom experiments, and in vivo animal studies to calculate the optical parameters using our proposed approach. The results show that our approach can estimate optical parameters of tissues with a relative error of <10%, accurately mapping the optical parameter distributions in a small animal.

Design and characterization of a time-domain optical tomography platform for mesoscopic lifetime imaging.

We report on the system design and instrumental characteristics of a novel time-domain mesoscopic fluorescence molecular tomography (TD-MFMT) system for multiplexed molecular imaging in turbid media. The system is equipped with a supercontinuum pulsed laser for broad spectral excitation, based on a high-density descanned raster scanning intensity-based acquisition for 2D and 3D imaging and augmented with a high-dynamical range linear time-resolved single-photon avalanche diode (SPAD) array for lifetime quantification. We report on the system's spatio-temporal and spectral characteristics and its sensitivity and specificity in controlled experimental settings. Also, a phantom study is undertaken to test the performance of the system to image deeply-seated fluorescence inclusions in tissue-like media. In addition, ex vivo tumor xenograft imaging is performed to validate the system's applicability to the biological sample. The characterization results manifest the capability to sense small fluorescence concentrations (on the order of nanomolar) while quantifying fluorescence lifetimes and lifetime-based parameters at high resolution. The phantom results demonstrate the system's potential to perform 3D multiplexed imaging thanks to spectral and lifetime contrast in the mesoscopic range (at millimeters depth). The ex vivo imaging exhibits the prospect of TD-MFMT to resolve intra-tumoral heterogeneity in a depth-dependent manner.

Low-dimensional Manifold Constrained Disentanglement Network for Metal Artifact Reduction.

Deep neural network based methods have achieved promising results for CT metal artifact reduction (MAR), most of which use many synthesized paired images for supervised learning. As synthesized metal artifacts in CT images may not accurately reflect the clinical counterparts, an artifact disentanglement network (ADN) was proposed with unpaired clinical images directly, producing promising results on clinical datasets. However, as the discriminator can only judge if large regions semantically look artifact-free or artifact-affected, it is difficult for ADN to recover small structural details of artifact-affected CT images based on adversarial losses only without sufficient constraints. To overcome the illposedness of this problem, here we propose a low-dimensional manifold (LDM) constrained disentanglement network (DN), leveraging the image characteristics that the patch manifold of CT images is generally low-dimensional. Specifically, we design an LDM-DN learning algorithm to empower the disentanglement network through optimizing the synergistic loss functions used in ADN while constraining the recovered images to be on a low-dimensional patch manifold. Moreover, learning from both paired and unpaired data, an efficient hybrid optimization scheme is proposed to further improve the MAR performance on clinical datasets. Extensive experiments demonstrate that the proposed LDM-DN approach can consistently improve the MAR performance in paired and/or unpaired learning settings, outperforming competing methods on synthesized and clinical datasets.

Astrocyte secretes IL-6 to modulate PSD-95 palmitoylation in basolateral amygdala and depression-like behaviors induced by peripheral nerve injury.

Dysfunction of glutamatergic synaptic plasticity in basolateral amygdala (BLA) constitutes a critical pathogenic mechanism underlying the depression-like behaviors induced by chronic pain. Astrocytes serve as an important supporting cell modulating glutamatergic synaptic transmission. Here, we found that peripheral spared nerve injury (SNI) induced astrocyte activation to release IL-6 in BLA. Inhibition of astrocyte activity attenuated SNI-induced IL-6 overexpression and depression-like behaviors. Moreover, SNI enhanced the abundance of DHHC2 in synaptosome and DHHC3 in Golgi apparatus, promoted PSD-95 palmitoylation, and increased the recruitment of GluR1 and NR2B at synapses. Suppression of IL-6 or PSD-95 palmitoylation attenuated the synaptic accumulation of GluR1 and NR2B in BLA and improved depression-like behaviors induced by SNI. Furthermore, IL-6 downstream PI3K increased the expression of DHHC3 in Golgi apparatus and facilitated the interaction of palmitoylated PSD-95 with GluR1 and NR2B at synapses. These findings collectively suggested that SNI activated astrocyte to release IL-6 in BLA, which promoted PSD-95 palmitoylation and enhanced the synaptic trafficking of GluR1 and NR2B, and subsequently mediated the depression-like behaviors induced by nerve injury.

Optimized collusion prevention for online exams during social distancing.

Online education is important in the COVID-19 pandemic, but online exam at individual homes invites students to cheat in various ways, especially collusion. While physical proctoring is impossible during social distancing, online proctoring is costly, compromises privacy, and can lead to prevailing collusion. Here we develop an optimization-based anti-collusion approach for distanced online testing (DOT) by minimizing the collusion gain, which can be coupled with other techniques for cheating prevention. With prior knowledge of student competences, our DOT technology optimizes sequences of questions and assigns them to students in synchronized time slots, reducing the collusion gain by 2-3 orders of magnitude relative to the conventional exam in which students receive their common questions simultaneously. Our DOT theory allows control of the collusion gain to a sufficiently low level. Our recent final exam in the DOT format has been successful, as evidenced by statistical tests and a post-exam survey.

On Interpretability of Artificial Neural Networks: A Survey.

Deep learning as represented by the artificial deep neural networks (DNNs) has achieved great success recently in many important areas that deal with text, images, videos, graphs, and so on. However, the black-box nature of DNNs has become one of the primary obstacles for their wide adoption in mission-critical applications such as medical diagnosis and therapy. Because of the huge potentials of deep learning, increasing the interpretability of deep neural networks has recently attracted much research attention. In this paper, we propose a simple but comprehensive taxonomy for interpretability, systematically review recent studies in improving interpretability of neural networks, describe applications of interpretability in medicine, and discuss possible future research directions of interpretability, such as in relation to fuzzy logic and brain science.

Clinical Micro-CT Empowered by Interior Tomography, Robotic Scanning, and Deep Learning.

While micro-CT systems are instrumental in preclinical research, clinical micro-CT imaging has long been desired with cochlear implantation as a primary application. The structural details of the cochlear implant and the temporal bone require a significantly higher image resolution than that (about 0.2 mm) provided by current medical CT scanners. In this paper, we propose a clinical micro-CT (CMCT) system design integrating conventional spiral cone-beam CT, contemporary interior tomography, deep learning techniques, and the technologies of a micro-focus X-ray source, a photon-counting detector (PCD), and robotic arms for ultrahigh-resolution localized tomography of a freely-selected volume of interest (VOI) at a minimized radiation dose level. The whole system consists of a standard CT scanner for a clinical CT exam and VOI specification, and a robotic micro-CT scanner for a local scan of high spatial and spectral resolution at minimized radiation dose. The prior information from the global scan is also fully utilized for background compensation of the local scan data for accurate and stable VOI reconstruction. Our results and analysis show that the proposed hybrid reconstruction algorithm delivers accurate high-resolution local reconstruction, and is insensitive to the misalignment of the isocenter position, initial view angle and scale mismatch in the data/image registration. These findings demonstrate the feasibility of our system design. We envision that deep learning techniques can be leveraged for optimized imaging performance. With high-resolution imaging, high dose efficiency and low system cost synergistically, our proposed CMCT system has great promise in temporal bone imaging as well as various other clinical applications.

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

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 1×1 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.

A meta-analysis of the diagnostic value of microRNA-1246 for malignant tumors.

BACKGROUND: Cancer morbidity and mortality are growing rapidly worldwide. There have been an increasing number of studies on the correlation between miRNA1246 expression in circulating blood and tumors; however, no comprehensive conclusion has been reached. Therefore, this meta-analysis was carried out to systematically evaluate the diagnostic value of blood levels of microRNA-1246 for malignant tumors. METHODS: We searched PubMed, MEDLINE, Embase, The Cochrane Library, the China National Knowledge Internet (CNKI), and Wanfang databases from the inception of each database until November 2018. The quality of the included literature was evaluated using the quality assessment tool called Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). The data were pooled using Stata14 and Meta-DiSc 1.4 software. RESULTS: Seven studies were included. The pooled sensitivity (SENS) was 0.80 (95% CI 0.65-0.89), the pooled specificity (SPEC) was 0.77 (95% CI 0.70-0.83), the pooled positive likelihood ratio (PLR) was 3.55 (95% CI 2.53-4.99), the pooled negative likelihood ratio (NLR) was 0.26 (95% CI 0.16-0.47), the pooled diagnostic odds ratio (DOR) was 13.78 (95% CI 5.84-32.5), and the area under the curve (AUC) was 0.83 (95% CI 0.79-0.86). The result of Deeks' funnel plot was P = 0.31, indicating a lack of publication bias. CONCLUSION: MicroRNA-1246 in the blood can be used as a good indicator for the diagnosis of malignant tumor diseases and has a moderate diagnostic accuracy for the differentiation of patients with malignant tumors from healthy people.