Weakly supervised learning-based 3D bladder reconstruction from 2D ultrasound images for bladder volume measurement

BACKGROUND

Accurate measurement of bladder volume is necessary to maintain the consistency of the patient's anatomy in radiation therapy for pelvic tumors. As the diversity of the bladder shape, traditional methods for bladder volume measurement from 2D ultrasound have been found to produce inaccurate results.

PURPOSE

To improve the accuracy of bladder volume measurement from 2D ultrasound images for patients with pelvic tumors.

METHODS

The bladder ultrasound images from 130 patients with pelvic cancer were collected retrospectively. All data were split into a training set (80 patients), a validation set (20 patients), and a test set (30 patients). A total of 12 transabdominal ultrasound images for one patient were captured by automatically rotating the ultrasonic probe with an angle step of 15°. An incomplete 3D ultrasound volume was synthesized by arranging these 2D ultrasound images in 3D space according to the acquisition angles. With this as input, a weakly supervised learning-based 3D bladder reconstruction neural network model was built to predict the complete 3D bladder. The key point is that we designed a novel loss function, including the supervised loss of bladder segmentation in the ultrasound images at known angles and the compactness loss of the 3D bladder. Bladder volume was calculated by counting the number of voxels belonging to the 3D bladder. The dice similarity coefficient (DSC) was used to evaluate the accuracy of bladder segmentation, and the relative standard deviation (RSD) was used to evaluate the calculation accuracy of bladder volume with that of computed tomography (CT) images as the gold standard.

RESULTS

The results showed that the mean DSC was up to 0.94 and the mean absolute RSD can be reduced to 6.3% when using 12 ultrasound images of one patient. Further, the mean DSC also was up to 0.90 and the mean absolute RSD can be reduced to 9.0% even if only two ultrasound images were used (i.e., the angle step is 90°). Compared with the commercial algorithm in bladder scanners, which has a mean absolute RSD of 13.6%, our proposed method showed a considerably huge improvement.

CONCLUSIONS

The proposed weakly supervised learning-based 3D bladder reconstruction method can greatly improve the accuracy of bladder volume measurement. It has great potential to be used in bladder volume measurement devices in the future.

CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization

Low-dose computed tomography (CT) images suffer from noise and artifacts due to photon starvation and electronic noise. Recently, some works have attempted to use diffusion models to address the over-smoothness and training instability encountered by previous deep-learning-based denoising models. However, diffusion models suffer from long inference time due to a large number of sampling steps involved. Very recently, cold diffusion model generalizes classical diffusion models and has greater flexibility. Inspired by cold diffusion, this paper presents a novel COntextual eRror-modulated gEneralized Diffusion model for low-dose CT (LDCT) denoising, termed CoreDiff. First, CoreDiff utilizes LDCT images to displace the random Gaussian noise and employs a novel mean-preserving degradation operator to mimic the physical process of CT degradation, significantly reducing sampling steps thanks to the informative LDCT images as the starting point of the sampling process. Second, to alleviate the error accumulation problem caused by the imperfect restoration operator in the sampling process, we propose a novel ContextuaL Error-modulAted Restoration Network (CLEAR-Net), which can leverage contextual information to constrain the sampling process from structural distortion and modulate time step embedding features for better alignment with the input at the next time step. Third, to rapidly generalize the trained model to a new, unseen dose level with as few resources as possible, we devise a one-shot learning framework to make CoreDiff generalize faster and better using only one single LDCT image (un)paired with normal-dose CT (NDCT). Extensive experimental results on four datasets demonstrate that our CoreDiff outperforms competing methods in denoising and generalization performance, with clinically acceptable inference time. Source code is made available at https://github.com/qgao21/CoreDiff.

HOPE: Hybrid-Granularity Ordinal Prototype Learning for Progression Prediction of Mild Cognitive Impairment

Mild cognitive impairment (MCI) is often at high risk of progression to Alzheimer's disease (AD). Existing works to identify the progressive MCI (pMCI) typically require MCI subtype labels, pMCI vs. stable MCI (sMCI), determined by whether or not an MCI patient will progress to AD after a long follow-up. However, prospectively acquiring MCI subtype data is time-consuming and resource-intensive; the resultant small datasets could lead to severe overfitting and difficulty in extracting discriminative information. Inspired by that various longitudinal biomarkers and cognitive measurements present an ordinal pathway on AD progression, we propose a novel Hybrid-granularity Ordinal PrototypE learning (HOPE) method to characterize AD ordinal progression for MCI progression prediction. First, HOPE learns an ordinal metric space that enables progression prediction by prototype comparison. Second, HOPE leverages a novel hybrid-granularity ordinal loss to learn the ordinal nature of AD via effectively integrating instance-to-instance ordinality, instance-to-class compactness, and class-to-class separation. Third, to make the prototype learning more stable, HOPE employs an exponential moving average strategy to learn the global prototypes of NC and AD dynamically. Experimental results on the internal ADNI and the external NACC datasets demonstrate the superiority of the proposed HOPE over existing state-of-the-art methods as well as its interpretability. Source code is made available at https://github.com/thibault-wch/HOPE-for-mild-cognitive-impairment.

Promoting fast MR imaging pipeline by full-stack AI

Magnetic resonance imaging (MRI) is a widely used imaging modality in clinics for medical disease diagnosis, staging, and follow-up. Deep learning has been extensively used to accelerate k-space data acquisition, enhance MR image reconstruction, and automate tissue segmentation. However, these three tasks are usually treated as independent tasks and optimized for evaluation by radiologists, thus ignoring the strong dependencies among them; this may be suboptimal for downstream intelligent processing. Here, we present a novel paradigm, full-stack learning (FSL), which can simultaneously solve these three tasks by considering the overall imaging process and leverage the strong dependence among them to further improve each task, significantly boosting the efficiency and efficacy of practical MRI workflows. Experimental results obtained on multiple open MR datasets validate the superiority of FSL over existing state-of-the-art methods on each task. FSL has great potential to optimize the practical workflow of MRI for medical diagnosis and radiotherapy.

LIT-Former: Linking In-plane and Through-plane Transformers for Simultaneous CT Image Denoising and Deblurring

This paper studies 3D low-dose computed tomography (CT) imaging. Although various deep learning methods were developed in this context, typically they focus on 2D images and perform denoising due to low-dose and deblurring for super-resolution separately. Up to date, little work was done for simultaneous in-plane denoising and through-plane deblurring, which is important to obtain high-quality 3D CT images with lower radiation and faster imaging speed. For this task, a straightforward method is to directly train an end-to-end 3D network. However, it demands much more training data and expensive computational costs. Here, we propose to link in-plane and through-plane transformers for simultaneous in-plane denoising and through-plane deblurring, termed as LIT-Former, which can efficiently synergize in-plane and through-plane sub-tasks for 3D CT imaging and enjoy the advantages of both convolution and transformer networks. LIT-Former has two novel designs: efficient multi-head self-attention modules (eMSM) and efficient convolutional feed-forward networks (eCFN). First, eMSM integrates in-plane 2D self-attention and through-plane 1D self-attention to efficiently capture global interactions of 3D self-attention, the core unit of transformer networks. Second, eCFN integrates 2D convolution and 1D convolution to extract local information of 3D convolution in the same fashion. As a result, the proposed LIT-Former synergizes these two sub-tasks, significantly reducing the computational complexity as compared to 3D counterparts and enabling rapid convergence. Extensive experimental results on simulated and clinical datasets demonstrate superior performance over state-of-the-art models.

Quad-Net: Quad-domain Network for CT Metal Artifact Reduction

Metal implants and other high-density objects in patients introduce severe streaking artifacts in CT images, compromising image quality and diagnostic performance. Although various methods were developed for CT metal artifact reduction over the past decades, including the latest dual-domain deep networks, remaining metal artifacts are still clinically challenging in many cases. Here we extend the state-of-the-art dual-domain deep network approach into a quad-domain counterpart so that all the features in the sinogram, image, and their corresponding Fourier domains are synergized to eliminate metal artifacts optimally without compromising structural subtleties. Our proposed quad-domain network for MAR, referred to as Quad-Net, takes little additional computational cost since the Fourier transform is highly efficient, and works across the four receptive fields to learn both global and local features as well as their relations. Specifically, we first design a Sinogram-Fourier Restoration Network (SFR-Net) in the sinogram domain and its Fourier space to faithfully inpaint metal-corrupted traces. Then, we couple SFR-Net with an Image-Fourier Refinement Network (IFR-Net) which takes both an image and its Fourier spectrum to improve a CT image reconstructed from the SFR-Net output using cross-domain contextual information. Quad-Net is trained on clinical datasets to minimize a composite loss function. Quad-Net does not require precise metal masks, which is of great importance in clinical practice. Our experimental results demonstrate the superiority of Quad-Net over the state-of-the-art MAR methods quantitatively, visually, and statistically. The Quad-Net code is publicly available at https://github.com/longzilicart/Quad-Net.

Joint learning framework of cross-modal synthesis and diagnosis for Alzheimer's disease by mining underlying shared modality information

Alzheimer's disease (AD) is one of the most common neurodegenerative disorders presenting irreversible progression of cognitive impairment. How to identify AD as early as possible is critical for intervention with potential preventive measures. Among various neuroimaging modalities used to diagnose AD, functional positron emission tomography (PET) has higher sensitivity than structural magnetic resonance imaging (MRI), but it is also costlier and often not available in many hospitals. How to leverage massive unpaired unlabeled PET to improve the diagnosis performance of AD from MRI becomes rather important. To address this challenge, this paper proposes a novel joint learning framework of unsupervised cross-modal synthesis and AD diagnosis by mining underlying shared modality information, improving the AD diagnosis from MRI while synthesizing more discriminative PET images. We mine underlying shared modality information in two aspects: diversifying modality information through the cross-modal synthesis network and locating critical diagnosis-related patterns through the AD diagnosis network. First, to diversify the modality information, we propose a novel unsupervised cross-modal synthesis network, which implements the inter-conversion between 3D PET and MRI in a single model modulated by the AdaIN module. Second, to locate shared critical diagnosis-related patterns, we propose an interpretable diagnosis network based on fully 2D convolutions, which takes either 3D synthesized PET or original MRI as input. Extensive experimental results on the ADNI dataset show that our framework can synthesize more realistic images, outperform the state-of-the-art AD diagnosis methods, and have better generalization on external AIBL and NACC datasets.

Impact of loss functions on the performance of a deep neural network designed to restore low-dose digital mammography

Digital mammography is currently the most common imaging tool for breast cancer screening. Although the benefits of using digital mammography for cancer screening outweigh the risks associated with the x-ray exposure, the radiation dose must be kept as low as possible while maintaining the diagnostic utility of the generated images, thus minimizing patient risks. Many studies investigated the feasibility of dose reduction by restoring low-dose images using deep neural networks. In these cases, choosing the appropriate training database and loss function is crucial and impacts the quality of the results. In this work, we used a standard residual network (ResNet) to restore low-dose digital mammography images and evaluated the performance of several loss functions. For training purposes, we extracted 256,000 image patches from a dataset of 400 images of retrospective clinical mammography exams, where dose reduction factors of 75% and 50% were simulated to generate low and standard-dose pairs. We validated the network in a real scenario by using a physical anthropomorphic breast phantom to acquire real low-dose and standard full-dose images in a commercially available mammography system, which were then processed through our trained model. We benchmarked our results against an analytical restoration model for low-dose digital mammography. Objective assessment was performed through the signal-to-noise ratio (SNR) and the mean normalized squared error (MNSE), decomposed into residual noise and bias. Statistical tests revealed that the use of the perceptual loss (PL4) resulted in statistically significant differences when compared to all other loss functions. Additionally, images restored using the PL4 achieved the closest residual noise to the standard dose. On the other hand, perceptual loss PL3, structural similarity index (SSIM) and one of the adversarial losses achieved the lowest bias for both dose reduction factors. The source code of our deep neural network is available at https://github.com/WANG-AXIS/LdDMDenoising.

When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and a New Benchmark

To minimize the impact of age variation on face recognition, age-invariant face recognition (AIFR) extracts identity-related discriminative features by minimizing the correlation between identity- and age-related features while face age synthesis (FAS) eliminates age variation by converting the faces in different age groups to the same group. However, AIFR lacks visual results for model interpretation and FAS compromises downstream recognition due to artifacts. Therefore, we propose a unified, multi-task framework to jointly handle these two tasks, termed MTLFace, which can learn the age-invariant identity-related representation for face recognition while achieving pleasing face synthesis for model interpretation. Specifically, we propose an attention-based feature decomposition to decompose the mixed face features into two uncorrelated components-identity- and age-related features-in a spatially constrained way. Unlike the conventional one-hot encoding that achieves group-level FAS, we propose a novel identity conditional module to achieve identity-level FAS, which can improve the age smoothness of synthesized faces through a weight-sharing strategy. Benefiting from the proposed multi-task framework, we then leverage those high-quality synthesized faces from FAS to further boost AIFR via a novel selective fine-tuning strategy. Furthermore, to advance both AIFR and FAS, we collect and release a large cross-age face dataset with age and gender annotations, and a new benchmark specifically designed for tracing long-missing children. Extensive experimental results on five benchmark cross-age datasets demonstrate that MTLFace yields superior performance than state-of-the-art methods for both AIFR and FAS. We further validate MTLFace on two popular general face recognition datasets, obtaining competitive performance on face recognition in the wild. The source code and datasets are available at http://hzzone.github.io/MTLFace.

Learning Representation for Clustering Via Prototype Scattering and Positive Sampling

Existing deep clustering methods rely on either contrastive or non-contrastive representation learning for downstream clustering task. Contrastive-based methods thanks to negative pairs learn uniform representations for clustering, in which negative pairs, however, may inevitably lead to the class collision issue and consequently compromise the clustering performance. Non-contrastive-based methods, on the other hand, avoid class collision issue, but the resulting non-uniform representations may cause the collapse of clustering. To enjoy the strengths of both worlds, this paper presents a novel end-to-end deep clustering method with prototype scattering and positive sampling, termed ProPos. Specifically, we first maximize the distance between prototypical representations, named prototype scattering loss, which improves the uniformity of representations. Second, we align one augmented view of instance with the sampled neighbors of another view-assumed to be truly positive pair in the embedding space-to improve the within-cluster compactness, termed positive sampling alignment. The strengths of ProPos are avoidable class collision issue, uniform representations, well-separated clusters, and within-cluster compactness. By optimizing ProPos in an end-to-end expectation-maximization framework, extensive experimental results demonstrate that ProPos achieves competing performance on moderate-scale clustering benchmark datasets and establishes new state-of-the-art performance on large-scale datasets. Source code is available at https://github.com/Hzzone/ProPos.

SAN-Net: Learning generalization to unseen sites for stroke lesion segmentation with self-adaptive normalization

There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as stroke is an important cerebrovascular disease. Although deep learning-based models have been proposed for this task, generalizing these models to unseen sites is difficult due to not only the large inter-site discrepancy among different scanners, imaging protocols, and populations, but also the variations in stroke lesion shape, size, and location. To tackle this issue, we introduce a self-adaptive normalization network, termed SAN-Net, to achieve adaptive generalization on unseen sites for stroke lesion segmentation. Motivated by traditional z-score normalization and dynamic network, we devise a masked adaptive instance normalization (MAIN) to minimize inter-site discrepancies, which standardizes input MR images from different sites into a site-unrelated style by dynamically learning affine parameters from the input; i.e., MAIN can affinely transform the intensity values. Then, we leverage a gradient reversal layer to force the U-net encoder to learn site-invariant representation with a site classifier, which further improves the model generalization in conjunction with MAIN. Finally, inspired by the "pseudosymmetry" of the human brain, we introduce a simple yet effective data augmentation technique, termed symmetry-inspired data augmentation (SIDA), that can be embedded within SAN-Net to double the sample size while halving memory consumption. Experimental results on the benchmark Anatomical Tracings of Lesions After Stroke (ATLAS) v1.2 dataset, which includes MR images from 9 different sites, demonstrate that under the "leave-one-site-out" setting, the proposed SAN-Net outperforms recently published methods in terms of quantitative metrics and qualitative comparisons.

Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey

Since 2016, deep learning (DL) has advanced tomographic imaging with remarkable successes, especially in low-dose computed tomography (LDCT) imaging. Despite being driven by big data, the LDCT denoising and pure end-to-end reconstruction networks often suffer from the black box nature and major issues such as instabilities, which is a major barrier to apply deep learning methods in low-dose CT applications. An emerging trend is to integrate imaging physics and model into deep networks, enabling a hybridization of physics/model-based and data-driven elements. In this paper, we systematically review the physics/model-based data-driven methods for LDCT, summarize the loss functions and training strategies, evaluate the performance of different methods, and discuss relevant issues and future directions.

M3NAS: Multi-Scale and Multi-Level Memory-Efficient Neural Architecture Search for Low-Dose CT Denoising

Lowering the radiation dose in computed tomography (CT) can greatly reduce the potential risk to public health. However, the reconstructed images from dose-reduced CT or low-dose CT (LDCT) suffer from severe noise which compromises the subsequent diagnosis and analysis. Recently, convolutional neural networks have achieved promising results in removing noise from LDCT images. The network architectures that are used are either handcrafted or built on top of conventional networks such as ResNet and U-Net. Recent advances in neural network architecture search (NAS) have shown that the network architecture has a dramatic effect on the model performance. This indicates that current network architectures for LDCT may be suboptimal. Therefore, in this paper, we make the first attempt to apply NAS to LDCT and propose a multi-scale and multi-level memory-efficient NAS for LDCT denoising, termed M3NAS. On the one hand, the proposed M3NAS fuses features extracted by different scale cells to capture multi-scale image structural details. On the other hand, the proposed M3NAS can search a hybrid cell- and network-level structure for better performance. In addition, M3NAS can effectively reduce the number of model parameters and increase the speed of inference. Extensive experimental results on two different datasets demonstrate that the proposed M3NAS can achieve better performance and fewer parameters than several state-of-the-art methods. In addition, we also validate the effectiveness of the multi-scale and multi-level architecture for LDCT denoising, and present further analysis for different configurations of super-net.

The survival of the prostate cancer patients with secondary colorectal cancer: a study based on a SEER database from southern China

OBJECTIVE

To evaluate the prognosis of prostate cancer patients with secondary colorectal cancer.

PATIENTS AND METHODS

The study included men with prostate cancer who developed colorectal cancer after radical prostatectomy in the Surveillance, Epidemiology, and Outcomes (SEER) database. After adjusting the age at first diagnosis, the prostate-specific antigen (PSA) level and Gleason score, the influence of the occurrence of secondary colorectal cancer on the prognosis of patients was evaluated.

RESULTS

A total of 66,955 patients were included in the present study. The median follow-up was 12 years. There were 537 patients with the incidence of the secondary colorectal cancer. The results of the three survival analysis methods all showed that the secondary colorectal cancer greatly increased the mortality risk of prostate cancer patients. Cox analysis results showed the hazard ratio (HR) is 3.79 (3.21-4.47), the Cox model with time-dependent covariates was introduced, and the result was 6.15 (5.19-7.31). When the Landmark time point is set to 5 years, the HR is 4.99 (3.85-6.47).

CONCLUSIONS

This study provides an important theoretical basis for evaluating the effect of secondary colorectal cancer on the prognosis of prostate cancer patients.

SPICE: Semantic Pseudo-Labeling for Image Clustering

The similarity among samples and the discrepancy among clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from inaccurate estimation of either feature similarity or semantic discrepancy. In this paper, we present a Semantic Pseudo-labeling-based Image ClustEring (SPICE) framework, which divides the clustering network into a feature model for measuring the instance-level similarity and a clustering head for identifying the cluster-level discrepancy. We design two semantics-aware pseudo-labeling algorithms, prototype pseudo-labeling and reliable pseudo-labeling, which enable accurate and reliable self-supervision over clustering. Without using any ground-truth label, we optimize the clustering network in three stages: 1) train the feature model through contrastive learning to measure the instance similarity; 2) train the clustering head with the prototype pseudo-labeling algorithm to identify cluster semantics; and 3) jointly train the feature model and clustering head with the reliable pseudo-labeling algorithm to improve the clustering performance. Extensive experimental results demonstrate that SPICE achieves significant improvements (~10%) over existing methods and establishes the new state-of-the-art clustering results on six balanced benchmark datasets in terms of three popular metrics. Importantly, SPICE significantly reduces the gap between unsupervised and fully-supervised classification; e.g. there is only 2% (91.8% vs 93.8%) accuracy difference on CIFAR-10. Our code is made publicly available at https://github.com/niuchuangnn/SPICE.

Racial Disparity in Antibody Against High Prevalence Antigen; Anti-U

Introduction/Objective

Anti-U is an IgG antibody directed against the U antigen, which usually forms after exposure to U antigen via blood transfusion and/or pregnancy. U antigen is located on glycophorin B (GYPB) as part of the MNS blood group system. Approximately 2% of the African American population lacks this antigen, making them prone to developing anti-U. Anti-U can cause hemolytic disease of fetus and newborn (HDFN) and hemolytic transfusion reactions (HTR).

Methods/Case Report

A 60-year-old African American male underwent aortic valve surgery. The patient was A Pos with a negative antibody screen. During surgery, the patient was transfused with 3 random units of packed red blood cells (PRBCs). The postoperative course was uncomplicated, and the patient was discharged home. 6 months later, the patient was admitted for another procedure and was expected to require blood products. Thus, a type and screen test was ordered, revealing pan reactivity on screening cells. This prompted further investigation. Antibody detection was performed with the solid-phase technique followed by the tube method with Polyethylene glycol (PEG) as an enhancement medium. PEG technique is the next choice of method if the solid phase requires extended antibody work up, which was the case in our patient. PEG tube method successfully identified Anti-U, and the patient's phenotype was confirmed to be U negative.

Results (if a Case Study enter NA)

N/A.

Conclusion

It is imperative to stress the importance of racial disparity while investigating antibodies against high prevalence. In our case, our suspicion was high for Anti-U, given that patient was of African American descent. Tube methods with PEG and Solid Phase techniques are usually used for antibody identification. It is recommended that patients with rare antibodies carry an Antibody ID card indicating the rare antibody they have to prevent further exposure.

OpenKBP-Opt: an international and reproducible evaluation of 76 knowledge-based planning pipelines

Objective.To establish an open framework for developing plan optimization models for knowledge-based planning (KBP).Approach.Our framework includes radiotherapy treatment data (i.e. reference plans) for 100 patients with head-and-neck cancer who were treated with intensity-modulated radiotherapy. That data also includes high-quality dose predictions from 19 KBP models that were developed by different research groups using out-of-sample data during the OpenKBP Grand Challenge. The dose predictions were input to four fluence-based dose mimicking models to form 76 unique KBP pipelines that generated 7600 plans (76 pipelines × 100 patients). The predictions and KBP-generated plans were compared to the reference plans via: the dose score, which is the average mean absolute voxel-by-voxel difference in dose; the deviation in dose-volume histogram (DVH) points; and the frequency of clinical planning criteria satisfaction. We also performed a theoretical investigation to justify our dose mimicking models.Main results.The range in rank order correlation of the dose score between predictions and their KBP pipelines was 0.50-0.62, which indicates that the quality of the predictions was generally positively correlated with the quality of the plans. Additionally, compared to the input predictions, the KBP-generated plans performed significantly better (P< 0.05; one-sided Wilcoxon test) on 18 of 23 DVH points. Similarly, each optimization model generated plans that satisfied a higher percentage of criteria than the reference plans, which satisfied 3.5% more criteria than the set of all dose predictions. Lastly, our theoretical investigation demonstrated that the dose mimicking models generated plans that are also optimal for an inverse planning model.Significance.This was the largest international effort to date for evaluating the combination of KBP prediction and optimization models. We found that the best performing models significantly outperformed the reference dose and dose predictions. In the interest of reproducibility, our data and code is freely available.

[Regulatory mechanism of deferoxamine on macrophage polarization and wound healing in mice with deep tissue injury]

Objective: To investigate the effects of deferoxamine on macrophage polarization and wound healing in mice with deep tissue injury (DTI) and its mechanism. Methods: The experimental research methods were adopted. Fifty-four male C57BL/6J mice of 6-8 weeks old were divided into DTI control group, 2 mg/mL deferoxamine group, and 20 mg/mL deferoxamine group according to random number table, with 18 mice in each group. DTI was established on the back of mice by magnet compression method. From post injury day (PID) 1, mice were injected subcutaneously with 100 µL normal saline or the corresponding mass concentration of deferoxamine solution every other day at the wound edge until the samples were collected. Another 6 mice without any treatment were selected as normal control group. Six mice in each of the three DTI groups were collected on PID 3, 7, and 14 to observe the wound changes and calculate the wound healing rate. Normal skin tissue of mice in normal control group was collected on PID 3 in other groups (the same below) and wound tissue of mice in the other three groups on PID 7 and 14 was collected for hematoxylin-eosin (HE) staining to observe the tissue morphology. Normal skin tissue of mice in normal control group and wound tissue of mice in the other three groups on PID 7 were collected, and the percentages of CD206 and CD11c positive area were observed and measured by immunohistochemical staining, and the mRNA and protein expressions of CD206, CD11c, and inducible nitric oxide synthase (iNOS) were detected by real-time fluorescence quantitative reverse transcription polymerase chain reaction and Western blotting, respectively. Normal skin tissue of mice in normal control group and wound tissue of mice in DTI control group and 20 mg/mL deferoxamine group were collected on PID 3, 7, and 14, and the protein expressions of signal transducer and activator of transcription 3 (STAT3) and interleukin-10 (IL-10) were detected by Western blotting. The sample number in each group at each time point in the above experiments. The RAW264.7 cells were divided into 50 μmol/L deferoxamine group, 100 μmol/L deferoxamine group, 200 μmol/L deferoxamine group, and blank control group, which were treated correspondingly, with 3 wells in each group. The positive cell percentages of CD206 and CD86 after 48 h of culture were detected by flow cytometry. Data were statistically analyzed with analysis of variance for repeated measurement, one-way analysis of variance, and least significant difference test. Results: On PID 7, the wound healing rates of mice in 2 mg/mL and 20 mg/mL deferoamine groups were (17.7±3.7)% and (21.5±5.0)%, respectively, which were significantly higher than (5.1±2.3)% in DTI control group (P<0.01). On PID 14, the wound healing rates of mice in 2 mg/mL and 20 mg/mL deferoamine groups were (51.1±3.8)% and (57.4±4.4)%, respectively, which were significantly higher than (25.2±3.8)% in DTI control group (P<0.01). HE staining showed that the normal skin tissue layer of mice in normal control group was clear, the epidermis thickness was uniform, and skin appendages such as hair follicles and sweat glands were visible in the dermis. On PID 7, inflammation in wound tissue was obvious, the epidermis was incomplete, and blood vessels and skin appendages were rare in mice in DTI control group; inflammatory cells in wound tissue were reduced in mice in 2 mg/mL and 20 mg/mL deferoxamine groups, and a few of blood vessels and skin appendages could be seen. On PID 14, inflammation was significantly alleviated and blood vessels and skin appendages were increased in wound tissue of mice in 2 mg/mL and 20 mg/mL deferoxamine groups compared with those in DTI control group. On PID 7, the percentages of CD206 positive area in wound tissue of mice in 2 mg/mL and 20 mg/mL deferoxamine groups were significantly higher than that in DTI control group (P<0.01), the percentage of CD206 positive area in wound tissue of mice in DTI control group was significantly lower than that in normal skin tissue of mice in normal control group (P<0.01), the percentage of CD206 positive area in wound tissue of mice in 20 mg/mL deferoxamine group was significantly higher than that in normal skin tissue of mice in normal control group (P<0.01). The percentages of CD11c positive area in wound tissue of mice in 2 mg/mL and 20 mg/mL deferoxamine groups were significantly lower than those in DTI control group and normal skin tissue in normal control group (P<0.05 or P<0.01), and the percentage of CD11c positive area in normal skin tissue of mice in normal control group was significantly higher than that in DTI control group (P<0.05). On PID 7, the CD206 mRNA expressions in the wound tissue of mice in 2 mg/mL and 20 mg/mL deferoxamine groups were significantly higher than that in DTI control group (P<0.01), but significantly lower than that in normal skin tissue in normal control group (P<0.01); the CD206 mRNA expression in wound tissue of mice in DTI control group was significantly lower than that in normal skin tissue in normal control group (P<0.01). The mRNA expressions of CD11c and iNOS in wound tissue of mice in 2 mg/mL and 20 mg/mL deferoamine groups were significantly lower than those in DTI control group (P<0.01). The mRNA expressions of CD11c in the wound tissue of mice in DTI control group, 2 mg/mL and 20 mg/mL deferoamine groups were significantly higher than that in normal skin tissue in normal control group (P<0.01). Compared with that in normal skin tissue in normal control group, the mRNA expressions of iNOS in wound tissue of mice in 2 mg/mL and 20 mg/mL deferoamine groups were significantly decreased (P<0.01), and the mRNA expression of iNOS in wound tissue of mice in DTI control group was significantly increased (P<0.01). On PID 7, the protein expressions of CD206 in the wound tissue of mice in 2 mg/mL and 20 mg/mL deferoamine groups were significantly higher than those in DTI control group and normal skin tissue in normal control group (P<0.01), and the protein expression of CD206 in wound tissue of mice in DTI control group was significantly lower than that in normal skin tissue in normal control group (P<0.01). The protein expressions of CD11c and iNOS in wound tissue of mice in 2 mg/mL and 20 mg/mL deferoamine groups were significantly lower than those in DTI control group (P<0.01). The protein expressions of CD11c and iNOS in wound tissue of mice in DTI control group were significantly higher than those in normal skin tissue in normal control group (P<0.01). The CD11c protein expressions in wound tissue of mice in 2 mg/mL and 20 mg/mL deferoamine groups were significantly higher than those in normal skin tissue in normal control group (P<0.05 or P<0.01). The protein expression of iNOS in wound tissue of mice in 2 mg/mL deferoamine group was significantly lower than that in 20 mg/mL deferoamine group and normal skin tissue in normal control group (P<0.05). On PID 3, 7, and 14, the protein expressions of STAT3 and IL-10 in wound tissue of mice in 20 mg/mL deferoxamine group were significantly higher than those in DTI control group (P<0.05 or P<0.01), and the protein expressions of STAT3 were significantly higher than those in normal skin tissue in normal control group (P<0.05 or P<0.01). On PID 7 and 14, the protein expressions of IL-10 in wound tissue of mice in 20 mg/mL deferoxamine group were significantly higher than those in normal skin tissue in normal control group (P<0.01). On PID 3, 7, and 14, the protein expressions of IL-10 in wound tissue of mice in DTI control group were significantly lower than those in normal skin tissue in normal control group (P<0.05 or P<0.01). After 48 h of culture, compared with those in blank control group, the CD206 positive cell percentages in 100 μmol/L and 200 μmol/L deferoamine groups were significantly increased (P<0.01), while the CD86 positive cell percentages in 100 μmol/L and 200 μmol/L deferoamine groups were significantly decreased (P<0.01). Conclusions: Deferoxamine can promote the polarization of macrophages toward the anti-inflammatory M2 phenotype and improve wound healing by enhancing the STAT3/IL-10 signaling pathway in DTI mice.

Convolutional Ordinal Regression Forest for Image Ordinal Estimation

Image ordinal estimation is to predict the ordinal label of a given image, which can be categorized as an ordinal regression (OR) problem. Recent methods formulate an OR problem as a series of binary classification problems. Such methods cannot ensure that the global ordinal relationship is preserved since the relationships among different binary classifiers are neglected. We propose a novel OR approach, termed convolutional OR forest (CORF), for image ordinal estimation, which can integrate OR and differentiable decision trees with a convolutional neural network for obtaining precise and stable global ordinal relationships. The advantages of the proposed CORF are twofold. First, instead of learning a series of binary classifiers independently, the proposed method aims at learning an ordinal distribution for OR by optimizing those binary classifiers simultaneously. Second, the differentiable decision trees in the proposed CORF can be trained together with the ordinal distribution in an end-to-end manner. The effectiveness of the proposed CORF is verified on two image ordinal estimation tasks, i.e., facial age estimation and image esthetic assessment, showing significant improvements and better stability over the state-of-the-art OR methods.

[Status of HVPG clinical application in China in 2021]

Objective: The investigation and research on the application status of Hepatic Venous Pressure Gradient (HVPG) is very important to understand the real situation and future development of this technology in China. Methods: This study comprehensively investigated the basic situation of HVPG technology in China, including hospital distribution, hospital level, annual number of cases, catheters used, average cost, indications and existing problems. Results: According to the survey, there were 70 hospitals in China carrying out HVPG technology in 2021, distributed in 28 provinces (autonomous regions and municipalities directly under the central Government). A total of 4 398 cases of HVPG were performed in all the surveyed hospitals in 2021, of which 2 291 cases (52.1%) were tested by HVPG alone. The average cost of HVPG detection was (5 617.2±2 079.4) yuan. 96.3% of the teams completed HVPG detection with balloon method, and most of the teams used thrombectomy balloon catheter (80.3%). Conclusion: Through this investigation, the status of domestic clinical application of HVPG has been clarified, and it has been confirmed that many domestic medical institutions have mastered this technology, but it still needs to continue to promote and popularize HVPG technology in the future.

Stabilizing deep tomographic reconstruction: Part A. Hybrid framework and experimental results

A recent PNAS paper reveals that several popular deep reconstruction networks are unstable. Specifically, three kinds of instabilities were reported: (1) strong image artefacts from tiny perturbations, (2) small features missed in a deeply reconstructed image, and (3) decreased imaging performance with increased input data. Here, we propose an analytic compressed iterative deep (ACID) framework to address this challenge. ACID synergizes a deep network trained on big data, kernel awareness from compressed sensing (CS)-inspired processing, and iterative refinement to minimize the data residual relative to real measurement. Our study demonstrates that the ACID reconstruction is accurate, is stable, and sheds light on the converging mechanism of the ACID iteration under a bounded relative error norm assumption. ACID not only stabilizes an unstable deep reconstruction network but also is resilient against adversarial attacks to the whole ACID workflow, being superior to classic sparsity-regularized reconstruction and eliminating the three kinds of instabilities.

Stabilizing deep tomographic reconstruction: Part B. Convergence analysis and adversarial attacks

Due to lack of the kernel awareness, some popular deep image reconstruction networks are unstable. To address this problem, here we introduce the bounded relative error norm (BREN) property, which is a special case of the Lipschitz continuity. Then, we perform a convergence study consisting of two parts: (1) a heuristic analysis on the convergence of the analytic compressed iterative deep (ACID) scheme (with the simplification that the CS module achieves a perfect sparsification), and (2) a mathematically denser analysis (with the two approximations: [1] A^T is viewed as an inverse A^{- 1} in the perspective of an iterative reconstruction procedure and [2] a pseudo-inverse is used for a total variation operator H). Also, we present adversarial attack algorithms to perturb the selected reconstruction networks respectively and, more importantly, to attack the ACID workflow as a whole. Finally, we show the numerical convergence of the ACID iteration in terms of the Lipschitz constant and the local stability against noise.

Content-Noise Complementary Learning for Medical Image Denoising

Medical imaging denoising faces great challenges, yet is in great demand. With its distinctive characteristics, medical imaging denoising in the image domain requires innovative deep learning strategies. In this study, we propose a simple yet effective strategy, the content-noise complementary learning (CNCL) strategy, in which two deep learning predictors are used to learn the respective content and noise of the image dataset complementarily. A medical image denoising pipeline based on the CNCL strategy is presented, and is implemented as a generative adversarial network, where various representative networks (including U-Net, DnCNN, and SRDenseNet) are investigated as the predictors. The performance of these implemented models has been validated on medical imaging datasets including CT, MR, and PET. The results show that this strategy outperforms state-of-the-art denoising algorithms in terms of visual quality and quantitative metrics, and the strategy demonstrates a robust generalization capability. These findings validate that this simple yet effective strategy demonstrates promising potential for medical image denoising tasks, which could exert a clinical impact in the future. Code is available at: https://github.com/gengmufeng/CNCL-denoising.

An ensemble learning method based on ordinal regression for COVID-19 diagnosis from chest CT

Coronavirus disease 2019 (COVID-19) has brought huge losses to the world, and it remains a great threat to public health. X-ray computed tomography (CT) plays a central role in the management of COVID-19. Traditional diagnosis with pulmonary CT images is time-consuming and error-prone, which could not meet the need for precise and rapid COVID-19 screening. Nowadays, deep learning (DL) has been successfully applied to CT image analysis, which assists radiologists in workflow scheduling and treatment planning for patients with COVID-19. Traditional methods use cross-entropy as the loss function with a Softmax classifier following a fully-connected layer. Most DL-based classification methods target intraclass relationships in a certain class (early, progressive, severe, or dissipative phases), ignoring the natural order of different phases of the disease progression,i.e.,from an early stage and progress to a late stage. To learn both intraclass and interclass relationships among different stages and improve the accuracy of classification, this paper proposes an ensemble learning method based on ordinal regression, which leverages the ordinal information on COVID-19 phases. The proposed method uses multi-binary, neuron stick-breaking (NSB), and soft labels (SL) techniques, and ensembles the ordinal outputs through a median selection. To evaluate our method, we collected 172 confirmed cases. In a 2-fold cross-validation experiment, the accuracy is increased by 22% compared with traditional methods when we use modified ResNet-18 as the backbone. And precision, recall, andF1-score are also improved. The experimental results show that our proposed method achieves a better classification performance than the traditional methods, which helps establish guidelines for the classification of COVID-19 chest CT images.

Strided Self-Supervised Low-Dose CT Denoising for Lung Nodule Classification

Lung nodule classification based on low-dose computed tomography (LDCT) images has attracted major attention thanks to the reduced radiation dose and its potential for early diagnosis of lung cancer from LDCT-based lung cancer screening. However, LDCT images suffer from severe noise, largely influencing the performance of lung nodule classification. Current methods combining denoising and classification tasks typically require the corresponding normal-dose CT (NDCT) images as the supervision for the denoising task, which is impractical in the context of clinical diagnosis using LDCT. To jointly train these two tasks in a unified framework without the NDCT images, this paper introduces a novel self-supervised method, termed strided Noise2Neighbors or SN2N, for blind medical image denoising and lung nodule classification, where the supervision is generated from noisy input images. More specifically, the proposed SN2N can construct the supervision information from its neighbors for LDCT denoising, which does not need NDCT images anymore. The proposed SN2N method enables joint training of LDCT denoising and lung nodule classification tasks by using self-supervised loss for denoising and cross-entropy loss for classification. Extensively experimental results on the Mayo LDCT dataset demonstrate that our SN2N achieves competitive performance compared with the supervised learning methods that have paired NDCT images as supervision. Moreover, our results on the LIDC-IDRI dataset show that the joint training of LDCT denoising and lung nodule classification significantly improves the performance of LDCT-based lung nodule classification.

Feasibility evaluation of PET scan-time reduction for diagnosing amyloid-β levels in Alzheimer's disease patients using a deep-learning-based denoising algorithm

PURPOSE

To shorten positron emission tomography (PET) scanning time in diagnosing amyloid-β levels thus increasing the workflow in centers involving Alzheimer's Disease (AD) patients.

METHODS

PET datasets were collected for 25 patients injected with ¹⁸F-AV45 radiopharmaceutical. To generate necessary training data, PET images from both normal-scanning-time (20-min) as well as so-called "shortened-scanning-time" (1-min, 2-min, 5-min, and 10-min) were reconstructed for each patient. Building on our earlier work on MCDNet (Monte Carlo Denoising Net) and a new Wasserstein-GAN algorithm, we developed a new denoising model called MCDNet-2 to predict normal-scanning-time PET images from a series of shortened-scanning-time PET images. The quality of the predicted PET images was quantitatively evaluated using objective metrics including normalized-root-mean-square-error (NRMSE), structural similarity (SSIM), and peak signal-to-noise ratio (PSNR). Furthermore, two radiologists performed subjective evaluations including the qualitative evaluation and a five-point grading evaluation. The denoising performance of the proposed MCDNet-2 was finally compared with those of U-Net, MCDNet, and a traditional denoising method called Gaussian Filtering.

RESULTS

The proposed MCDNet-2 can yield good denoising performance in 5-min PET images. In the comparison of denoising methods, MCDNet-2 yielded the best performance in the subjective evaluation although it is comparable with MCDNet in objective comparison (NRMSE, PSNR, and SSIM). In the qualitative evaluation of amyloid-β positive or negative results, MCDNet-2 was found to achieve a classification accuracy of 100%.

CONCLUSIONS

The proposed denoising method has been found to reduce the PET scan time from the normal level of 20 min to 5 min but still maintaining acceptable image quality in correctly diagnosing amyloid-β levels. These results suggest strongly that deep learning-based methods such as ours can be an attractive solution to the clinical needs to improve PET imaging workflow.

Cine Cardiac MRI Motion Artifact Reduction Using a Recurrent Neural Network

Cine cardiac magnetic resonance imaging (MRI) is widely used for the diagnosis of cardiac diseases thanks to its ability to present cardiovascular features in excellent contrast. As compared to computed tomography (CT), MRI, however, requires a long scan time, which inevitably induces motion artifacts and causes patients' discomfort. Thus, there has been a strong clinical motivation to develop techniques to reduce both the scan time and motion artifacts. Given its successful applications in other medical imaging tasks such as MRI super-resolution and CT metal artifact reduction, deep learning is a promising approach for cardiac MRI motion artifact reduction. In this paper, we propose a novel recurrent generative adversarial network model for cardiac MRI motion artifact reduction. This model utilizes bi-directional convolutional long short-term memory (ConvLSTM) and multi-scale convolutions to improve the performance of the proposed network, in which bi-directional ConvLSTMs handle long-range temporal features while multi-scale convolutions gather both local and global features. We demonstrate a decent generalizability of the proposed method thanks to the novel architecture of our deep network that captures the essential relationship of cardiovascular dynamics. Indeed, our extensive experiments show that our method achieves better image quality for cine cardiac MRI images than existing state-of-the-art methods. In addition, our method can generate reliable missing intermediate frames based on their adjacent frames, improving the temporal resolution of cine cardiac MRI sequences.

Deep learning predicts cardiovascular disease risks from lung cancer screening low dose computed tomography

Cancer patients have a higher risk of cardiovascular disease (CVD) mortality than the general population. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for simultaneous CVD risk estimation in at-risk patients. Our deep learning CVD risk prediction model, trained with 30,286 LDCTs from the National Lung Cancer Screening Trial, achieves an area under the curve (AUC) of 0.871 on a separate test set of 2,085 subjects and identifies patients with high CVD mortality risks (AUC of 0.768). We validate our model against ECG-gated cardiac CT based markers, including coronary artery calcification (CAC) score, CAD-RADS score, and MESA 10-year risk score from an independent dataset of 335 subjects. Our work shows that, in high-risk patients, deep learning can convert LDCT for lung cancer screening into a dual-screening quantitative tool for CVD risk estimation.

The circular RNA circPTK2 inhibits EMT in hepatocellular carcinoma by acting as a ceRNA and sponging miR-92a to upregulate E-cadherin

OBJECTIVE

Hepatocellular carcinoma (HCC) is a common malignant tumor. Increasing evidence has demonstrated that microRNAs (miRNAs) play an important role in a wide variety of cellular processes. However, there are few reports about the role and underlying molecular mechanisms of miRNAs in HCC.

PATIENTS AND METHODS

qRT-PCR and Western blots were performed to quantify the expression of miR-92a, E-cadherin, and circPTK2. Proliferation and invasion assays were performed to explore the function of miR-92a and circPTK2. A Luciferase assay was used to test the relationship between miR-92a, E-cadherin, and circPTK2.

RESULTS

In this study, we found that miR-92a was upregulated in HCC tissues and HCC cell lines. Overexpression of miR-92a enhanced cell proliferation and invasion by targeting the E-cadherin 3'UTR in HCC cells. Furthermore, we found that circPTK2 inhibited EMT by inhibiting miR-92a, preventing its ability to downregulate E-cadherin in HCC cells.

CONCLUSIONS

We identified a regulatory axis comprising circPTK2/miR-92a/E-cadherin in HCC cells that may serve as a valuable biomarker and therapeutic target for patients with HCC.

Parameter-Transferred Wasserstein Generative Adversarial Network (PT-WGAN) for Low-Dose PET Image Denoising

Due to the widespread use of positron emission tomography (PET) in clinical practice, the potential risk of PET-associated radiation dose to patients needs to be minimized. However, with the reduction in the radiation dose, the resultant images may suffer from noise and artifacts that compromise diagnostic performance. In this paper, we propose a parameter-transferred Wasserstein generative adversarial network (PT-WGAN) for low-dose PET image denoising. The contributions of this paper are twofold: i) a PT-WGAN framework is designed to denoise low-dose PET images without compromising structural details, and ii) a task-specific initialization based on transfer learning is developed to train PT-WGAN using trainable parameters transferred from a pretrained model, which significantly improves the training efficiency of PT-WGAN. The experimental results on clinical data show that the proposed network can suppress image noise more effectively while preserving better image fidelity than recently published state-of-the-art methods. We make our code available at https://github.com/90n9-yu/PT-WGAN.

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.

Two genetically similar H9N2 influenza viruses isolated from different species show similar virulence in minks but different virulence in mice

The H9N2 influenza virus has been frequently endemic in poultry, infected mammals and humans and has threatened public health. It is therefore imperative to understand the molecular mechanism enabling this virus to jump from avian to mammalian species. In this study, two H9N2 influenza viruses were isolated from the same region in eastern China but from different hosts; one was isolated from mink and named A/Mink/Shandong/WM01/2014(H9N2)(WM01), while the other was isolated from chicken and named A/Chicken/Shandong/LX830/2014(H9N2)(LX830). Sequencing and phylogenetic analysis showed that both H9N2 influenza viruses had similar genetic backgrounds. The results of infection in minks suggested that both viruses caused significant weight loss and pathological changes in the lungs. Mouse infection showed that LX830 was nonpathogenic in mice, but WM01 resulted in 25% mortality and pathological changes in the lungs, such as severe edema and diffused inflammation of the interalveolar septa. Comparison of the full genomes of both H9N2 influenza viruses showed 52-nucleotide-synonym mutations in 8 gene segments and 7-nucleotide-antonym mutations, resulting in 7 amino acid (AA) substitutions distributed in the PB1, PA, NA and M gene segments. None of these mutations did affect splicing of the M and NS gene segments at the nucleotide level or minor open reading frames (ORFs), such as PB1-F2 and PA-X. Phylogenetic analysis showed that both H9N2 influenza viruses belong to the prevalent epidemic genotype in Asia. Keywords: H9N2 influenza virus; chicken; minks; pathogenicity; phylogenetic.

Multi-Contrast Super-Resolution MRI Through a Progressive Network

Magnetic resonance imaging (MRI) is widely used for screening, diagnosis, image-guided therapy, and scientific research. A significant advantage of MRI over other imaging modalities such as computed tomography (CT) and nuclear imaging is that it clearly shows soft tissues in multi-contrasts. Compared with other medical image super-resolution methods that are in a single contrast, multi-contrast super-resolution studies can synergize multiple contrast images to achieve better super-resolution results. In this paper, we propose a one-level non-progressive neural network for low up-sampling multi-contrast super-resolution and a two-level progressive network for high up-sampling multi-contrast super-resolution. The proposed networks integrate multi-contrast information in a high-level feature space and optimize the imaging performance by minimizing a composite loss function, which includes mean-squared-error, adversarial loss, perceptual loss, and textural loss. Our experimental results demonstrate that 1) the proposed networks can produce MRI super-resolution images with good image quality and outperform other multi-contrast super-resolution methods in terms of structural similarity and peak signal-to-noise ratio; 2) combining multi-contrast information in a high-level feature space leads to a significantly improved result than a combination in the low-level pixel space; and 3) the progressive network produces a better super-resolution image quality than the non-progressive network, even if the original low-resolution images were highly down-sampled.

Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising

Inspired by complexity and diversity of biological neurons, our group proposed quadratic neurons by replacing the inner product in current artificial neurons with a quadratic operation on input data, thereby enhancing the capability of an individual neuron. Along this direction, we are motivated to evaluate the power of quadratic neurons in popular network architectures, simulating human-like learning in the form of "quadratic-neuron-based deep learning". Our prior theoretical studies have shown important merits of quadratic neurons and networks in representation, efficiency, and interpretability. In this paper, we use quadratic neurons to construct an encoder-decoder structure, referred as the quadratic autoencoder, and apply it to low-dose CT denoising. The experimental results on the Mayo low-dose CT dataset demonstrate the utility and robustness of quadratic autoencoder in terms of image denoising and model efficiency. To our best knowledge, this is the first time that the deep learning approach is implemented with a new type of neurons and demonstrates a significant potential in the medical imaging field.

A two-dimensional feasibility study of deep learning-based feature detection and characterization directly from CT sinograms

Machine Learning, especially deep learning, has been used in typical x-ray computed tomography (CT) applications, including image reconstruction, image enhancement, image domain feature detection and image domain feature characterization. To our knowledge, this is the first study on machine learning for feature detection and analysis directly based on CT projection data. Specifically, we present neural network methods for blood vessel detection and characterization in the sinogram domain avoiding any partial volume, beam hardening, or motion artifacts introduced during reconstruction. First, we estimate sinogram domain vessel maps using a residual encoder-decoder convolutional neural network (REDCNN). Next, we estimate the vessel centerline and we extract the vessel-only sinogram from the original sinogram, eliminating any background information. Finally, we use a fully connected neural network to estimate the vessel lumen cross-sectional area from the vessel-only sinogram. We trained and tested the proposed methods using CatSim simulations, real CT measurements of vessel phantoms, and clinical data from the NIH CT image database. We achieved encouraging initial results showing the feasibility of CT analysis in the sinogram domain. In principle, sinogram domain analysis should be possible for many other and more complicated clinical CT analysis tasks. Further studies are needed for this sinogram domain analysis approach to become practical for clinical applications.

A method of rapid quantification of patient-specific organ doses for CT using deep-learning-based multi-organ segmentation and GPU-accelerated Monte Carlo dose computing

PURPOSE

One technical barrier to patient-specific computed tomography (CT) dosimetry has been the lack of computational tools for the automatic patient-specific multi-organ segmentation of CT images and rapid organ dose quantification. When previous CT images are available for the same body region of the patient, the ability to obtain patient-specific organ doses for CT - in a similar manner as radiation therapy treatment planning - will open the door to personalized and prospective CT scan protocols. This study aims to demonstrate the feasibility of combining deep-learning algorithms for automatic segmentation of multiple radiosensitive organs from CT images with the GPU-based Monte Carlo rapid organ dose calculation.

METHODS

A deep convolutional neural network (CNN) based on the U-Net for organ segmentation is developed and trained to automatically delineate multiple radiosensitive organs from CT images. Two databases are used: The lung CT segmentation challenge 2017 (LCTSC) dataset that contains 60 thoracic CT scan patients, each consisting of five segmented organs, and the Pancreas-CT (PCT) dataset, which contains 43 abdominal CT scan patients each consisting of eight segmented organs. A fivefold cross-validation method is performed on both sets of data. Dice similarity coefficients (DSCs) are used to evaluate the segmentation performance against the ground truth. A GPU-based Monte Carlo dose code, ARCHER, is used to calculate patient-specific CT organ doses. The proposed method is evaluated in terms of relative dose errors (RDEs). To demonstrate the potential improvement of the new method, organ dose results are compared against those obtained for population-average patient phantoms used in an off-line dose reporting software, VirtualDose, at Massachusetts General Hospital.

RESULTS

The median DSCs are found to be 0.97 (right lung), 0.96 (left lung), 0.92 (heart), 0.86 (spinal cord), 0.76 (esophagus) for the LCTSC dataset, along with 0.96 (spleen), 0.96 (liver), 0.95 (left kidney), 0.90 (stomach), 0.87 (gall bladder), 0.80 (pancreas), 0.75 (esophagus), and 0.61 (duodenum) for the PCT dataset. Comparing with organ dose results from population-averaged phantoms, the new patient-specific method achieved smaller absolute RDEs (mean ± standard deviation) for all organs: 1.8% ± 1.4% (vs 16.0% ± 11.8%) for the lung, 0.8% ± 0.7% (vs 34.0% ± 31.1%) for the heart, 1.6% ± 1.7% (vs 45.7% ± 29.3%) for the esophagus, 0.6% ± 1.2% (vs 15.8% ± 12.7%) for the spleen, 1.2% ± 1.0% (vs 18.1% ± 15.7%) for the pancreas, 0.9% ± 0.6% (vs 20.0% ± 15.2%) for the left kidney, 1.7% ± 3.1% (vs 19.1% ± 9.8%) for the gallbladder, 0.3% ± 0.3% (vs 24.2% ± 18.7%) for the liver, and 1.6% ± 1.7% (vs 19.3% ± 13.6%) for the stomach. The trained automatic segmentation tool takes <5 s per patient for all 103 patients in the dataset. The Monte Carlo radiation dose calculations performed in parallel to the segmentation process using the GPU-accelerated ARCHER code take <4 s per patient to achieve <0.5% statistical uncertainty in all organ doses for all 103 patients in the database.

CONCLUSION

This work shows the feasibility to perform combined automatic patient-specific multi-organ segmentation of CT images and rapid GPU-based Monte Carlo dose quantification with clinically acceptable accuracy and efficiency.

Deep Efficient End-to-end Reconstruction (DEER) Network for Few-view Breast CT Image Reconstruction

Breast CT provides image volumes with isotropic resolution in high contrast, enabling detection of small calcification (down to a few hundred microns in size) and subtle density differences. Since breast is sensitive to x-ray radiation, dose reduction of breast CT is an important topic, and for this purpose, few-view scanning is a main approach. In this article, we propose a Deep Efficient End-to-end Reconstruction (DEER) network for few-view breast CT image reconstruction. The major merits of our network include high dose efficiency, excellent image quality, and low model complexity. By the design, the proposed network can learn the reconstruction process with as few as O ( N ) parameters, where N is the side length of an image to be reconstructed, which represents orders of magnitude improvements relative to the state-of-the-art deep-learning-based reconstruction methods that map raw data to tomographic images directly. Also, validated on a cone-beam breast CT dataset prepared by Koning Corporation on a commercial scanner, our method demonstrates a competitive performance over the state-of-the-art reconstruction networks in terms of image quality. The source code of this paper is available at: https://github.com/HuidongXie/DEER.

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.

Deep Encoder-Decoder Adversarial Reconstruction(DEAR) Network for 3D CT from Few-View Data

X-ray computed tomography (CT) is widely used in clinical practice. The involved ionizingX-ray radiation, however, could increase cancer risk. Hence, the reduction of the radiation dosehas been an important topic in recent years. Few-view CT image reconstruction is one of the mainways to minimize radiation dose and potentially allow a stationary CT architecture. In this paper,we propose a deep encoder-decoder adversarial reconstruction (DEAR) network for 3D CT imagereconstruction from few-view data. Since the artifacts caused by few-view reconstruction appear in3D instead of 2D geometry, a 3D deep network has a great potential for improving the image qualityin a data driven fashion. More specifically, our proposed DEAR-3D network aims at reconstructing3D volume directly from clinical 3D spiral cone-beam image data. DEAR is validated on a publiclyavailable abdominal CT dataset prepared and authorized by Mayo Clinic. Compared with other2D deep learning methods, the proposed DEAR-3D network can utilize 3D information to producepromising reconstruction results.

A dual-stream deep convolutional network for reducing metal streak artifacts in CT images

Machine learning and deep learning are rapidly finding applications in the medical imaging field. In this paper, we address the long-standing problem of metal artifacts in computed tomography (CT) images by training a dual-stream deep convolutional neural network for streak removal. While many metal artifact reduction methods exist, even state-of-the-art algorithms fall short in some clinical applications. Specifically, proton therapy planning requires high image quality with accurate tumor volumes to ensure treatment success. We explore a dual-stream deep network structure with residual learning to correct metal streak artifacts after a first-pass by a state-of-the-art interpolation-based algorithm, NMAR. We provide the network with a mask of the streaks in order to focus attention on those areas. Our experiments compare a mean squared error loss function with a perceptual loss function to emphasize preservation of image features and texture. Both visual and quantitative metrics are used to assess the resulting image quality for metal implant cases. Success may be due to the duality of information processing, with one network stream performing local structure correction, while the other stream provides an attention mechanism to destreak effectively. This study shows that image-domain deep learning can be highly effective for metal artifact reduction (MAR), and highlights the benefits and drawbacks of different loss functions for solving a major CT reconstruction challenge.

Framework of Randomized Distribution Features for Visual Representation and Categorization

This paper introduces a framework to deal with the distribution of descriptive features, which preserves the advantages of the vectorial representation and computational efficiency of histogram-based techniques, and inherits the rigorous theoretical guarantee and competitive performance of metric-based ones. The methods developed under this framework describe the underlying distribution of a set of features as a vectorial feature by utilizing random features. Moreover, the proposed methods asymptotically converge to metric-based methods in terms of the similarity and distance and, depending on a specific kernel function, reduce to histogram-based methods. The experimental results show the benefits of a comparable performance on categorization tasks compared to conventional metric-based methods at a significantly reduced computational cost.

Osteoprotegerin mediate RANK/RANKL signaling inhibition eases asthma inflammatory reaction by affecting the survival and function of dendritic cells

INTRODUCTION

Asthma is a chronic inflammatory, heterogeneous airway disease affecting millions of people around the world. Dendritic cells (DCs) are considered the most important antigen-presenting cell in asthma airway inflammatory reaction. But whether osteoprotegerin (OPG) mediate RANK/RANKL signaling inhibition influences asthma development by affecting the survival and function of DCs remains unclear. In this study, we assessed the effects of OPG on DCs and asthma.

MATERIAL AND METHODS

BALB/c mice immunized with ovalbumin (OVA) were challenged thrice with an aerosol of OVA every second day for eight days. Dexamethasone (1.0mg/kg) or OPG (50μg/kg) was administered intraperitoneally to OVA-immunized BALB/c mice on day 24 once a day for nine days. Mice were analyzed for effects of OPG on asthma, inflammatory cell infiltration and cytokine levels in lung tissue. The expression of RANK and β-actin was detected by Western Blot. DCs were isolated from mouse bone morrow. Cell survival was assessed by cell counting. The content of IL-12 was detected by ELISA.

RESULTS

Results showed that OVA increased the number of inflammatory factors in BALF, elevated lung inflammation scores in mice. OPG reversed the alterations induced by OVA in the asthmatic mice. OPG inhibited the survival and function of DC via inhibition of RANK/RANKL signaling.

CONCLUSIONS

This research proved inhibition of RANK/RANKL signaling by OPG could ease the inflammatory reaction in asthma, providing new evidence for the application of OPG on asthma.