Multi-domain medical image translation generation for lung image classification based on generative adversarial networks.

OBJECTIVE: Lung image classification-assisted diagnosis has a large application market. Aiming at the problems of poor attention to existing translation models, the insufficient ability of key transfer and generation, insufficient quality of generated images, and lack of detailed features, this paper conducts research on lung medical image translation and lung image classification based on generative adversarial networks. METHODS: This paper proposes a medical image multi-domain translation algorithm MI-GAN based on the key migration branch. After the actual analysis of the imbalanced medical image data, the key target domain images are selected, the key migration branch is established, and a single generator is used to complete the medical image multi-domain translation. The conversion between domains ensures the attention performance of the medical image multi-domain translation model and the quality of the synthesized images. At the same time, a lung image classification model based on synthetic image data augmentation is proposed. The synthetic lung CT medical images and the original real medical images are used as the training set together to study the performance of the auxiliary diagnosis model in the classification of normal healthy subjects, and also of the mild and severe COVID-19 patients. RESULTS: Based on the chest CT image dataset, MI-GAN has completed the mutual conversion and generation of normal lung images without disease, viral pneumonia and Mild COVID-19 images. The synthetic images GAN-test and GAN-train indicators reached, respectively 92.188% and 85.069%, compared with other generative models in terms of authenticity and diversity, there is a considerable improvement. The accuracy rate of pneumonia diagnosis of the lung image classification model is 93.85%, which is 3.1% higher than that of the diagnosis model trained only with real images; the sensitivity of disease diagnosis is 96.69%, a relative improvement of 7.1%. 1%, the specificity was 89.70%; the area under the ROC curve (AUC) increased from 94.00% to 96.17%. CONCLUSION: In this paper, a multi-domain translation model of medical images based on the key transfer branch is proposed, which enables the translation network to have key transfer and attention performance. It is verified on lung CT images and achieved good results. The required medical images are synthesized by the above medical image translation model, and the effectiveness of the synthesized images on the lung image classification network is verified experimentally.

Classification of lungs infected COVID-19 images based on inception-ResNet.

OBJECTIVE: Nowadays, COVID-19 is spreading rapidly worldwide, and seriously threatening lives . From the perspective of security and economy, the effective control of COVID-19 has a profound impact on the entire society. An effective strategy is to diagnose earlier to prevent the spread of the disease and prompt treatment of severe cases to improve the chance of survival. METHODS: The method of this paper is as follows: Firstly, the collected data set is processed by chest film image processing, and the bone removal process is carried out in the rib subtraction module. Then, the set preprocessing method performed histogram equalization, sharpening, and other preprocessing operations on the chest film. Finally, shallow and high-level feature mapping through the backbone network extracts the processed chest radiographs. We implement the self-attention mechanism in Inception-Resnet, perform the standard classification, and identify chest radiograph diseases through the classifier to realize the auxiliary COVID-19 diagnosis process at the medical level, all in an effort to further enhance the classification performance of the convolutional neural network. Numerous computer simulations demonstrate that the Inception-Resnet convolutional neural network performs CT image categorization and enhancement with greater efficiency and flexibility than conventional segmentation techniques. RESULTS: The experimental COVID-19 CT dataset obtained in this paper is the new data for CT scans and medical imaging of normal, early COVID-19 patients and severe COVID-19 patients from Jinyintan hospital. The experiment plots the relationship between model accuracy, model loss and epoch, using ACC, TPR, SPE, F1 score and G-mean to measure the image maps of patients with and without the disease. Statistical measurement values are obtained by Inception-Resnet are 88.23%, 83.45%, 89.72%, 95.53% and 88.74%. The experimental results show that Inception-Resnet plays a more effective role than other image classification methods in evaluation indicators, and the method has higher robustness, accuracy and intuitiveness. CONCLUSION: With CT images in the clinical diagnosis of COVID-19 images being widely used and the number of applied samples continuously increasing, the method in this paper is expected to become an additional diagnostic tool that can effectively improve the diagnostic accuracy of clinical COVID-19 images.

High glucose and palmitic acid induces neuronal senescence by NRSF/REST elevation and the subsequent mTOR-related autophagy suppression.

Cell senescence is a basic aging mechanism. Previous studies have found that the cellular senescence in adipose tissue and other tissues, such as the pancreas, muscle and liver, is associated with the pathogenesis and progression of type 2 diabetes; however, strong evidence of whether diabetes directly causes neuronal senescence in the brain is still lacking. In this study, we constructed a high glucose and palmitic acid (HGP) environment on PC12 neuronal cells and primary mouse cortical neurons to simulate diabetes. Our results showed that after HGP exposure, neurons exhibited obvious senescence-like phenotypes, including increased NRSF/REST level, mTOR activation and cell autophagy suppression. Downregulation of NRSF/REST could remarkably alleviate p16, p21 and γH2A.X upregulations induced by HGP treatment, and enhance mTOR-autophagy of neurons. Our results suggested that the diabetic condition could directly induce neuronal senescence, which is mediated by the upregulation of NRSF/REST and subsequent reduction of mTOR-autophagy.

Knockdown of NRSF Alleviates Ischemic Brain Injury and Microvasculature Defects in Diabetic MCAO Mice.

Diabetes is one of the well-established risk factors of stroke and is associated with a poor outcome in patients with stroke. Previous studies have shown that the expression of neuron restrictive silencer factor (NRSF) is elevated in diabetes as well as ischemic stroke. However, the role of NRSF in regulating an outcome of diabetic ischemic stroke has not been completely understood. Here, we hypothesized that diabetes-induced NRSF elevation can aggravate brain injury and cognition impairment in ischemic stroke. The diabetic ischemic stroke mice model was established by 8 weeks of high-fat-diet feeding and 5 days of streptozotocin injection followed by 30 min of middle cerebral artery occlusion (MCAO). We found that diabetes enhanced the MCAO-induced elevation of NRSF in the hippocampus in accompany with an elevation of its corepressors, HDAC1, and mSin3A, and decrease of ß-TrCP. By using histological/immunofluorescence staining and neurobehavioral testing, our results showed that the brain damage and learning/memory impairment were aggravated in diabetic ischemic mice but significantly attenuated after stereotaxic injection of NRSF-shRNA. Meanwhile, by performing whole-brain clearing with PEGASOS, microvascular reconstruction, western blotting, and ELISA, we found that NRSF-shRNA markedly alleviated the vasculature disorders and rescued the suppression of NRP-1, VEGF, and VEGFR2 in the hippocampus of diabetic ischemic mice. Therefore, our results demonstrated for the first time that the elevation of hippocampal NRSF plays an important role in alleviating brain injury and cognitive disabilities in diabetic ischemic mice, potentially via the reduction of NRP-1/VEGF signaling.

Serum Heparanase: A New Clinical Biomarker Involved in Senile Metabolic Inflammatory Syndrome.

AIM: Metabolic inflammation syndrome (MIS) can lead to a series of complications, but its exact inflammatory mechanism is still unclear. The aim of this study was to explore the correlation between heparanase (HPA) and MIS, and the close relationship between HPA and other chronic low-grade inflammation index, such as C-reactive protein (CRP) and interleukin-6 (IL-6). METHODS: A total of 105 patients with MIS in the physical examination population of Huashan Hospital affiliated to Fudan University from May to June 2018 were selected as the MIS group, and 52 patients who were relatively healthy during the same period were used as the control group. The basic clinical data of the selected candidates were collected, the levels of serum HPA, CRP and IL-6 were measured by ELISA, and the levels of blood glucose and blood lipids were also detected. RESULTS: Compared with the control group, the levels of HPA, CRP, IL-6, FBG, HbA1C, and TG of MIS group were all significantly elevated (all P<0.05), and HDL-C levels were considerably reduced (P<0.05). Correlation analysis showed that there was a noticeably positive correlation between serum HPA level and CRP, IL-6 levels (P<0.05). CONCLUSION: Higher HPA levels might play a certain role in the occurrence and development of MIS. There was a certain close correlation between serum HPA level and CRP and IL-6 levels, and which indicated that HPA was involved in the chronic low-grade inflammatory reaction process of MIS.

A novel palmitic acid hydroxy stearic acid (5-PAHSA) plays a neuroprotective role by inhibiting phosphorylation of the m-TOR-ULK1 pathway and regulating autophagy.

AIMS: Type 2 diabetes mellitus (T2DM) can lead to brain dysfunction and a series of neurological complications. Previous research demonstrated that a novel palmitic acid (5-PAHSA) exerts effect on glucose tolerance and chronic inflammation. Autophagy was important in diabetic-related neurodegeneration. The aim of the present study was to investigate whether 5-PAHSA has specific therapeutic effects on neurological dysfunction in diabetics, particularly with regard to autophagy. METHODS: 5-PAHSA was successfully synthesized according to a previously described protocol. We then carried out a series of in vitro and in vivo experiments using PC12 cells under diabetic conditions, and DB/DB mice, respectively. PC12 cells were treated with 5-PAHSA for 24 h, while mice were administered with 5-PAHSA for 30 days. At the end of each experiment, we analyzed glucolipid metabolism, autophagy, apoptosis, oxidative stress, cognition, and a range of inflammatory factors. RESULTS: Although there was no significant improvement in glucose metabolism in mice administered with 5-PAHSA, ox-LDL decreased significantly following the administration of 5-PAHSA in serum of DB/DB mice (p < 0.0001). We also found that the phosphorylation of m-TOR and ULK-1 was suppressed in both PC12 cells and DB/DB mice following the administration of 5-PAHSA (p < 0.05 and p < 0.01), although increased levels of autophagy were only observed in vitro (p < 0.05). Following the administration of 5-PAHSA, the concentration of ROS decreased in PC12 cells and the levels of CRP increased in high-dose group of 5-PAHSA (p < 0.01). There were no significant changes in terms of apoptosis, other inflammatory factors, or cognition in DB/DB mice following the administration of 5-PAHSA. CONCLUSION: We found that 5-PAHSA can enhance autophagy in PC12 cells under diabetic conditions. Our data demonstrated that 5-PAHSA inhibits phosphorylation of the m-TOR-ULK1 pathway and suppressed oxidative stress in PC12 cells, and exerted influence on lipid metabolism in DB/DB mice.