KM04416 suppressed lung adenocarcinoma progression by promoting immune infiltration.

OBJECTIVES: Lung adenocarcinoma (LUAD) is a malignant tumor originating from the bronchial mucosa or glands of the lung, with the fastest increasing morbidity and mortality. Therefore, the prognosis of lung cancer remains poor. Glycerol-3-phosphate dehydrogenase 2 (GPD2) is a widely existing protein pattern sequence in biology and is closely related to tumor progression. The therapy values of GPD2 inhibitor in LUAD were unclear. Therefore, we aimed to analyze the therapy values of GPD2 inhibitor in LUAD. MATERIALS AND METHODS: The Cancer Genome Atlas (TCGA)-LUAD database was used to analyze the expression levels of GPD2 in LUAD tissues. The relationship between GPD2 expression and LUAD patient survival was analyzed by Kaplan-Meier method. Moreover, KM04416 as a target inhibitor of GPD2 was used to further investigate the therapy value of GPD2 inhibitor in LUAD cells lines (A549 cell and H1299 cell). The TISIDB website was used to investigate the associations between GPD2 expression and immune cell infiltration in LUAD. RESULTS: The results showed that GPD2 is overexpressed in LUAD tissues and significantly associated with poor survival. KM04416 can suppress the progression of LUAD cells by targeting GPD2. Low expression of GPD2 is related to high infiltration of immune cells. CONCLUSIONS: In summary, our present study found that targeting inhibition of GPD2 by KM04416 can suppress LUAD progression via adjusting immune cell infiltration.

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.

Simulator study of young driver's instinctive response of lower extremity to a collision.

OBJECTIVE: A driver's instinctive response of the lower extremity in braking movement consists of two parts, including reaction time and braking reaction behavior. It is critical to consider these two components when conducting studies concerning driver's brake movement intention and injury analysis. The purposes of this study were to investigate the driver reaction time to an oncoming collision and muscle activation of lower extremity muscles at the collision moment. The ultimate goal is to provide data that aid in both the optimization of intervention time of an active safety system and the improvement of precise protection performance of a passive safety system. METHOD: A simulated collision scene was constructed in a driving simulator, and 40 young volunteers (20 male and 20 female) were recruited for tests. Vehicle control parameters and electromyography characteristics of eight muscles of the lower extremity were recorded. The driver reaction time was divided into pre-motor time (PMT) and muscle activation time (MAT). Muscle activation level (ACOL) at the collision moment was calculated and analysed. RESULTS: PMT was shortest for the tibialis anterior (TA) muscle (243∼317 ms for male and 278∼438 ms for female). Average MAT of the TA ranged from 28-55 ms. ACOL was large (5∼31% for male and 5∼23% for female) at 50 km/h, but small (<12%) at 100 km/h. ACOL of the gluteus maximus was smallest (<3%) in the 25 and 100 km/h tests. ACOL of RF of men was significantly smaller than that of women at different speeds. CONCLUSIONS: Ankle dorsiflexion is firstly activated at the beginning of the emergency brake motion. Males showed stronger reaction ability than females, as suggested by male's shorter PMT. The detection of driver's brake intention is upwards of 55ms sooner after introducing the electromyography. Muscle activation of the lower extremity is an important factor for 50 km/h collision injury analysis. For higher speed collisions, this might not be a major factor. The activations of certain muscles may be ignored for crash injury analysis at certain speeds, such as gluteus maximus at 25 or 100 km/h. Furthermore, the activation of certain muscles should be differentiated between males and females during injury analysis.

Experimal study of young male drivers' responses to vehicle collision using EMG of lower extremity.

A driver's response to a front-coming vehicle collision consists of braking reaction time and braking behavior. The purpose was to investigate drivers' responses at different speeds, relative distances, and particularly the behavior on the accelerator at the collision moment. Twelve young men participated in driving simulator tests. Vehicle parameters and electromyograms (EMGs) of the drivers' tibialis anterior muscles were recorded and responses were analyzed. The drivers' braking reaction time windows were divided into pre-motor time, muscle activation time, accelerator release time, and movement time. By comparing the reaction times and collision times, braking behaviors were investigated. It was found that movement times (r = -0.281) decreased with speed. Pre-motor times (r = 0.326) and muscle activation times (r = 0.281) increased with relative distance. At the collision moment, the probability of the driver's lower extremity being on the accelerator, in the air, and on the brake pedal was 7.4%, 18.9%, and 73.7%, respectively. With higher speeds and smaller distances, the lower extremity was more likely to be in the air or even on the accelerator in different muscle activation states. The driver will collide in normal driving postures which muscles are not or not fully activated in very urgent situation.

Study of cervical muscle response and injury of driver during a frontal vehicle collision.

Frontal vehicle collisions can cause injury to a driver's cervical muscles resulting from intense changes in muscle strain and muscle load. This study investigated the influence of collision forces in a sled test environment using a modified Hybrid III 50th percentile dummy equipped with simulated spring-type muscles. Cervical muscle responses including strain and load of the sternocleidomastoid (SCM), splenius capitis (SPL), and trapezius (TRP) were analyzed, and muscle injury was assessed. The SCM, SPL, and TRP suffered average peak muscle strains of 21%, 40%, and 23%, respectively, exceeding the injury threshold. The average peak muscle loads of the SCM, SPL and TRP were 11 N, 25 N, and 25 N, respectively, lower than the ultimate failure load. The SPL endured the largest injury, while the injuries to the SCM and TRP were relatively small. This is a preliminary study to assess the cervical muscle of driver during a frontal vehicle collision. This study provides a foundation for investigating the muscle response and injury in sled test environments, which can lead to the improvement of occupant protections.