Multi-center sparse learning and decision fusion for automatic COVID-19 diagnosis.

The coronavirus disease 2019 (COVID-19) pandemic caused by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to a sharp increase in hospitalized patients with multi-organ disease pneumonia. Early and automatic diagnosis of COVID-19 is essential to slow down the spread of this epidemic and reduce the mortality of patients infected with SARS-CoV-2. In this paper, we propose a joint multi-center sparse learning (MCSL) and decision fusion scheme exploiting chest CT images for automatic COVID-19 diagnosis. Specifically, considering the inconsistency of data in multiple centers, we first convert CT images into histogram of oriented gradient (HOG) images to reduce the structural differences between multi-center data and enhance the generalization performance. We then exploit a 3-dimensional convolutional neural network (3D-CNN) model to learn the useful information between and within 3D HOG image slices and extract multi-center features. Furthermore, we employ the proposed MCSL method that learns the intrinsic structure between multiple centers and within each center, which selects discriminative features to jointly train multi-center classifiers. Finally, we fuse these decisions made by these classifiers. Extensive experiments are performed on chest CT images from five centers to validate the effectiveness of the proposed method. The results demonstrate that the proposed method can improve COVID-19 diagnosis performance and outperform the state-of-the-art methods.

Improved low-dose positron emission tomography image reconstruction using deep learned prior.

Positron emission tomography (PET) is a promising medical imaging technology that provides non-invasive and quantitative measurement of biochemical process in the human bodies. PET image reconstruction is challenging due to the ill-poseness of the inverse problem. With lower statistics caused by the limited detected photons, low-dose PET imaging leads to noisy reconstructed images with much quality degradation. Recently, deep neural networks (DNN) have been widely used in computer vision tasks and attracted growing interests in medical imaging. In this paper, we proposed a maximuma posteriori(MAP) reconstruction algorithm incorporating a convolutional neural network (CNN) representation in the formation of the prior. Rather than using the CNN in post-processing, we embedded the neural network in the reconstruction framework for image representation. Using the simulated data, we first quantitatively evaluated our proposed method in terms of the noise-bias tradeoff, and compared with the filtered maximum likelihood (ML), the conventional MAP, and the CNN post-processing methods. In addition to the simulation experiments, the proposed method was further quantitatively validated on the acquired patient brain and body data with the tradeoff between noise and contrast. The results demonstrated that the proposed CNN-MAP method improved noise-bias tradeoff compared with the filtered ML, the conventional MAP, and the CNN post-processing methods in the simulation study. For the patient study, the CNN-MAP method achieved better noise-contrast tradeoff over the other three methods. The quantitative enhancements indicate the potential value of the proposed CNN-MAP method in low-dose PET imaging.

Medical Imaging Engineering and Technology Branch of the Chinese Society of Biomedical Engineering expert consensus on the application of Emergency Mobile Cabin CT.

Started during December 2019, following the emergence of several COVID-19 cases in Wuhan City, Hubei Province, there was a rapid surge and spread of new COVID-19 cases throughout China. The disease has since been included in the Class B infectious diseases category, as stipulated in the Law of the People's Republic of China on the Prevention and Treatment of Infectious Diseases and shall be managed according to Class A infectious diseases. During the early phases of COVID-19 infection, no specific pulmonary imaging features may be evident, or features overlapping with other pneumonia may be observed. Although CT is not the gold standard for the diagnosis of COVID-19, it nonetheless is a convenient and fast method, and its application can be deployed in community hospitals. Furthermore, CT can be used to render a suggestive diagnosis and evaluate the severity as well as the effects of therapeutic interventions for typical cases of COVID-19. The mobile emergency special CT device described in this document (also known as Emergency Mobile Cabin CT) has several unique characteristics, including its mobility, flexibility, and networking capabilities. Furthermore, it adopts a fully independent isolation design to avoid cross-infection between patients and medical staff. It can play an important role in screening suspected cases presenting with imaging features of COVID-19 in hospitals of various levels that provide care to suspected or confirmed COVID-19 patients as part of the first line procedures of epidemic prevention and control.

A novel supervised learning method to generate CT images for attenuation correction in delayed pet scans.

BACKGROUND AND OBJECTIVES: Attenuation correction is important for PET image reconstruction. In clinical PET/CT scans, the attenuation information is usually obtained by CT. However, additional CT scans for delayed PET imaging may increase the risk of cancer. In this paper, we propose a novel CT generation method for attenuation correction in delayed PET imaging that requires no additional CT scans. METHODS: As only PET raw data is available for the delayed PET scan, routine image registration methods are difficult to use directly. To solve this problem, a reconstruction network is developed to produce pseudo PET images from raw data first. Then a second network is used to generate the CT image through mapping PET/CT images from the first scan to the delayed scan. The inputs of the second network are the two pseudo PET images from the first and delayed scans, and the CT image from the first scan. The labels are taken from the ground truth CT image in the delayed scan. The loss function contains an image similarity term and a regularization term, which reflect the anatomy matching accuracy and the smoothness of the non-rigid deformation field, respectively. RESULTS: We evaluated the proposed method with simulated and clinical PET/CT datasets. Standard Uptake Value was computed and compared with the gold standard (with coregistered CT for attenuation correction). The results show that the proposed supervised learning method can generate PET images with high quality and quantitative accuracy. For the test cases in our study, the average MAE and RMSE of the proposed supervised learning method were 4.61 and 22.75 respectively, and the average PSNR between the reconstructed PET image and the ground truth PET image was 62.13 dB. CONCLUSIONS: The proposed method is able to generate accurate CT images for attenuation correction in delayed PET scans. Experiments indicate that the proposed method outperforms traditional methods with respect to quantitative PET image accuracy.

Study of low-dose PET image recovery using supervised learning with CycleGAN.

PET is a popular medical imaging modality for various clinical applications, including diagnosis and image-guided radiation therapy. The low-dose PET (LDPET) at a minimized radiation dosage is highly desirable in clinic since PET imaging involves ionizing radiation, and raises concerns about the risk of radiation exposure. However, the reduced dose of radioactive tracers could impact the image quality and clinical diagnosis. In this paper, a supervised deep learning approach with a generative adversarial network (GAN) and the cycle-consistency loss, Wasserstein distance loss, and an additional supervised learning loss, named as S-CycleGAN, is proposed to establish a non-linear end-to-end mapping model, and used to recover LDPET brain images. The proposed model, and two recently-published deep learning methods (RED-CNN and 3D-cGAN) were applied to 10% and 30% dose of 10 testing datasets, and a series of simulation datasets embedded lesions with different activities, sizes, and shapes. Besides vision comparisons, six measures including the NRMSE, SSIM, PSNR, LPIPS, SUVmax and SUVmean were evaluated for 10 testing datasets and 45 simulated datasets. Our S-CycleGAN approach had comparable SSIM and PSNR, slightly higher noise but a better perception score and preserving image details, much better SUVmean and SUVmax, as compared to RED-CNN and 3D-cGAN. Quantitative and qualitative evaluations indicate the proposed approach is accurate, efficient and robust as compared to other state-of-the-art deep learning methods.

[Effects of glucose concentration fluctuation on function of cultured bovine arterial endothelial cells].

OBJECTIVE: To explore the effects of glucose concentration fluctuation on function of cultured bovine arterial endothelial cells and underlying mechanism. METHODS: The thoracic aorta of newborn calf was used for primary endothelial cells culture. Cells were divided into 3 groups and cultured for 48 h: control group (C, 5.5 mmol/L), constant high glucose group (HG, 30 mmol/L) and glucose fluctuation (GF, three circles of 2 h 30 mmol/L followed by 3 h 5.5 mmol/L, 30 mmol/L overnight, repeat the whole procedure on the following day) groups. The membranes fluidity of endothelial cells was detected by fluorescence polarization method. The contents of sorbierite, aldose reductase (AR), sorbitol dehydrogenase (SDH) and advanced glycation end products (AGEs) were measured. RAGE, eNOS and ET-1 mRNA expressions were detected by semi-quantitative RT-PCR. RESULTS: The membranes fluidity of endothelial cells in HG or GF group were significantly decreased compared with the control group (all P < 0.01) and significantly lower in GF group than those in HG group (all P < 0.01). Sorbierite, AR and AGEs concentrations were significantly higher in HG and GF groups than those in control group (all P < 0.01) and AR and AGEs concentrations were significantly higher in GF group than that in HG group (all P < 0.01). SDH of endothelial cells in HG or GF group were decreased compared with the control group and lower in GF group than in HG group (all P < 0.05). In addition, the mRNA levels of RAGE, eNOS and ET-1 were significantly upregulated compared with the control group (all P < 0.01). CONCLUSIONS: Glucose concentration fluctuation can result in more severe bovine arterial endothelial cells dysfunction than high glucose via activating polyols metabolic pathways, upregulating the expression of AGEs, eNOS and ET-1. Therefore, glucose concentration fluctuation might play a crucial role on macrovascular complications of diabetes.

[Protection of vascular endothelial cells from high glucose injury induced by quercetin].

OBJECTIVE: To evaluate the effects of quercetin on the high glucose-injured vascular endothelial cells (VECs). METHODS: Experiments were divided into control group, injured group and quercetin group. The cultured VECs were injured by high glucose. The proliferation of VECs was assessed by MTT assay. The amount of NO and lipid peroxidation (monitored as maloraldehyde, MDA) of VECs were assessed by fluorometric assay. The amount of lactate dehydrogenase (LDH) was assessed by spectrophotometric method. RESULTS: 10(-2), 10(-3), 10(-4), 10(-5) mg/ml quercetin increased the proliferation of high glucose-injured VECs. 10(-2), 10(-3) mg/ml quercetin reduced LDH release and MDA production, increased NO release. CONCLUSION: Quercetin can protect cultured VECs from being injured by high glucose.