Explore the vast range of titles available.

Path planning in complex, dynamic environments presents a significant challenge. Deep Reinforcement Learning (DRL) offers an end-to-end solution but suffers from critical sample inefficiency and a “cold-start” problem. Imitation Learning (IL) accelerates training but is constrained by a performance ceiling and poor generalization. To address these limitations, we propose a novel Imitation–Reinforcement Hybrid Machine Learning Algorithm (Hybrid IL-RL). This framework balances exploration and performance via a two-stage process: First, an offline pre-training phase uses Behavioral Cloning (BC) with “non-expert” A* data from static environments for a “warm start”. Second, an online fine-tuning phase uses a DRL algorithm (SAC) to adapt this policy in complex, dynamic environments, allowing the agent to surpass the teacher’s limitations. Simulation experiments validate the approach. The framework demonstrates significantly faster convergence than DRL algorithms trained from scratch. Most critically, in the dynamic environment, our Hybrid IL-RL algorithm achieved the highest success rate (82.4%), while pure IL methods (BC, GAIL) failed due to poor generalization (e.g., 82.1% collision rate) and pure DRL methods struggled (approx. 51–56% success rate). Our results confirm the hybrid framework effectively solves the cold-start problem while using DRL to break the IL performance ceiling.

Saliency detection is a key research topic in the field of computer vision. Humans can be accurately and quickly mesmerized by an area of interest in complex and changing scenes through the visual perception area of the brain. Although existing saliency-detection methods can achieve competent performance, they have deficiencies such as unclear margins of salient objects and the interference of background information on the saliency map. In this study, to improve the defects during saliency detection, a multiscale cascaded attention network was designed based on ResNet34. Different from the typical U-shaped encoding–decoding architecture, we devised a contextual feature extraction module to enhance the advanced semantic feature extraction. Specifically, a multiscale cascade block (MCB) and a lightweight channel attention (CA) module were added between the encoding and decoding networks for optimization. To address the blur edge issue, which is neglected by many previous approaches, we adopted the edge thinning module to carry out a deeper edge-thinning process on the output layer image. The experimental results illustrate that this method can achieve competitive saliency-detection performance, and the accuracy and recall rate are improved compared with those of other representative methods.

Background Osteosarcoma (OS) mainly happens in children and youths. Surgery, radiotherapy and chemotherapy are the common therapies for osteosarcoma treatment but all their anti-tumor effects are limited. In recent years, a new cellular therapy, CAR-T, a cellular immunotherapy with genetically engineered T cells bearing chimeric antigen receptor targeting specific tumor-associated antigen, has been proved to be an effective therapy against acute lymphoblastic leukemia. Thus, CAR-T is a potentially effective therapy for osteosarcoma treatment. Methods A CAR gene targeting B7-H3 antigen was constructed into lentiviral vector through molecular biology techniques. Then, the CAR gene was transferred to T cells through lentiviral delivery system, and the CAR-T cells were largely expanded using in vitro culture technology. The in vitro anti-tumor effect of CAR-T cells was evaluated through Real Time Cell Analysis system (RTCA) and ELISA assay. The in vivo anti-tumor capabilities of CAR-T cells were evaluated using the patient-derived xenografts (PDX) model of osteosarcoma. Results The third-generation CAR-T cells we constructed could target the B7-H3 antigen, and the phenotype of CAR-T cells was consistent with normal T cells; The CAR-T cells showed superior antitumor effects both in vitro and in vivo . Conclusion Our study showed that B7-H3 targeted CAR-T cells had high anti-tumor efficacy against osteosarcoma both in vitro and in vivo , which proved that B7-H3 targeted CAR-T therapy is potentially effective for osteosarcoma treatment.

Ascophyllum nodosum, a brown algae abundantly found along the North Atlantic coast, is recognized for its high polysaccharide content. In this study, we investigated the anti-hyperlipidemic effect of fucoidans derived from A. nodosum, aiming to provide information for their potential application in anti-hyperlipidemic therapies and to explore comprehensive utilization of this Iceland brown seaweed. The crude fucoidan prepared from A. nodosum was separated using a diethylethanolamine column, resulting in two fucoidan fractions, AFC-1 and AFC-2. Both fractions were predominantly composed of fucose and xylose. AFC-1 exhibited a higher sulfate content of 27.8% compared to AFC-2 with 17.0%. AFC-2 was primarily sulfated at the hydroxy group of C2, whereas AFC-1 was sulfated at both the hydroxy groups of C2 and C4. To evaluate the anti-hyperlipidemic effect, a hyperlipidemia mouse model was established by feeding mice a high-fat diet. The effects of AFC-1, AFC-2, and the crude extract were investigated, with the drug atorvastatin used as a positive comparison. Among the different fucoidan fractions and doses, the high dose of AFC-2 administration demonstrated the most significant anti-hyperlipidemic effect across various aspects, including physiological parameters, blood glucose levels, lipid profile, histological analysis, and the activities of oxidative stress-related enzymes and lipoprotein-metabolism-related enzymes (p < 0.05 for the final body weight and p < 0.01 for the rest indicators, compared with the model group), and its effect is comparable to the atorvastatin administration. Furthermore, fucoidan administration resulted in a lower degree of loss in gut flora diversity compared to atorvastatin administration. These findings highlight the significant biomedical potential of fucoidans derived from A. nodosum as a promising therapeutic solution for hypolipidemia.

The hypoxic tumor microenvironment (TME) significantly impacts the effectiveness of various therapies on breast cancer. Conventional chemotherapeutic agents are unable to target hypoxic tumor tissue specifically, leading to reduced treatment efficacy and severe systemic toxicity. In order to improve drug targeting ability, we developed a bioactive biomotors system (MDPP@Bif) for chemoimmunotherapy against breast cancer. Utilizing the self-driving properties of the anaerobic ( , Bif), both doxorubicin (DOX) and anti-programmed cell death protein ligand-1 (αPD-L1) antibody can be delivered simultaneously to tumor tissues to exert an anti-tumor effect on breast cancer. The physicochemical properties of diverse nano-formulations were systematically characterized. In vitro anti-tumor efficacy of the MDPP@Bif biomotors was assessed through comprehensive biological evaluations, including 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assays, live/dead staining, c cellular uptake analysis, apoptosis quantification, and wound healing assays to evaluate the in vitro anti-tumor activity of the MDPP@Bif biomotors. Furthermore, the therapeutic potential of the MDPP@Bif biohybrids was validated in vivo using a murine breast cancer model by monitoring of tumor growth kinetics, body weight fluctuations, and survival outcomes. Immunofluorescence staining was also used to further validate T-cells infiltration in the tumor tissues. The developed MDPP@Bif biomotors can actively colonize hypoxic tumor tissues through Bif's inherent targeting ability, releasing DOX to inhibit tumor growth. The released αPD-L1 antibody specifically binds to PD-L1, reducing immune escape and activating T cells. The concentration of DOX in tumor tissues of the MDPP@Bif group was 2.5 times higher than in tumors treated with free DOX, significantly prolonging the median survival of mice to 62 days and reducing the toxic side effects of DOX. The novel bacteria-propelled biomotor MDPP@Bif shows great potential in treating solid tumors through synergistic chemotherapy and immunotherapy.

A worldwide outbreak of coronavirus disease (COVID-19), since 2019, has brought a disaster to people all over the world. Many researchers carried out clinical epidemiological studies on patients with COVID-19 previously, but risk factors for patients with different levels of severity are still unclear. 562 patients with laboratory-confirmed COVID-19 from 12 hospitals in China were included in this retrospective study. Related clinical information, therapies, and imaging data were extracted from electronic medical records and compared between patients with severe and non-severe status. We explored the risk factors associated with different severity of COVID-19 patients by logistic regression methods. Based on the guideline we cited, 509 patients were classified as non-severe and 53 were severe. The age range of whom was 5-87 years, with a median age of 47 (IQR 35.0-57.0). And the elderly patients (older than 60 years old) in non-severe group were more likely to suffer from fever and asthma, accompanied by higher level of D-dimer, red blood cell distribution width and low-density lipoprotein. Furthermore, we found that the liver and kidney function of male patients was worse than that of female patients in both severe and non-severe groups with different age levels, while the severe females had faster ESR and lower inflammatory markers. Of major laboratory markers in non-severe cases, baseline albumin and the lymphocyte percentage were higher, while the white blood cell and the neutrophil count were lower. In addition, severe patients were more likely to be accompanied by an increase in cystatin C, mean hemoglobin level and a decrease in oxygen saturation. Besides that, advanced age and indicators such as count of white blood cell, glucose were proved to be the most common risk factors preventing COVID-19 patients from aggravating. The potential risk factors found in our study have shown great significance to prevent COVID-19 patients from aggravating and turning to critical cases during treatment. Meanwhile, focusing on gender and age factors in groups with different severity of COVID-19, and paying more attention to specific clinical symptoms and characteristics, could improve efficacy of personalized intervention to treat COVID-19 effectively.

Background. Coronavirus disease 2019 (COVID-19) has been a global threat that pushes healthcare to its limits. Hypertension is one of the most common risk factors for cardiovascular complications in COVID-19 and is strongly associated with disease severity and mortality. To date, clinical mechanisms by which hypertension leads to increased risk in COVID-19 are still unclear. Furthermore, additional factors might increase these risks, such as the consideration of age and sex, which are of interest when in search of personalized treatments for hypertensive COVID-19 patients. Methods. We conducted a retrospective cohort study of 543 COVID-19 patients in seven provinces of China to examine the epidemiological and clinical characteristics of COVID-19 in this population and to determine risk factors of hypertensive COVID-19 patients. We also used univariable and multivariable logistic regression methods to explore the risk factors associated with hypertensive COVID-19 patients in different age and sex subgroups. Results. Among the enrolled COVID-19 patients, the median age was 47 years (interquartile range (IQR) 34.0–57.0), and 99 patients (18.23%) were over 60 years old. With regard to comorbidities, 91 patients (16.75%) were diagnosed with hypertension, followed by diabetes, coronary disease, and cerebrovascular disease. Of the hypertensive COVID-19 patients, 51 (56.04%) were male. Multivariable analysis showed that old age, comorbid diabetes or coronary heart disease on admission, increased D-dimer, increased glucose, and decreased lymphocyte count were independent risk factors associated with hypertensive COVID-19 patients. Elevated total bilirubin (odds ratio [OR]: 1.014, 95% confidence interval [CI]: 0.23–1.05; p=0.043) and triglycerides (OR: 1.173, 95% CI: 0.049–1.617; p=0.007) were found to be associated with elderly hypertensive COVID-19 patients. In addition, we found that decreased lymphocytes, basophil, high-density lipoprotein, and increased fibrinogen and creatinine were related to a higher risk of disease severity in male patients. The most common abnormal clinical findings pertaining to female hypertensive COVID-19 patients were hemoglobin, total bile acid, total protein, and low-density lipoprotein. Conclusions. Factors associated with increased risk of hypertensive COVID-19 patients were identified. Results to the different age and sex subgroups in our study will allow for better possible personalized care and also provide new insights into specific risk stratification, disease management, and treatment strategies for COVID-19 patients with hypertension in the future.

Background and Purpose. Diabetes is common in COVID-19 patients and associated with unfavorable outcomes. We aimed to describe the characteristics and identify the risk factors for COVID-19 patients complicated with diabetes. Methods. In this multicenter retrospective study, patients with COVID-19 in China were included and classified into two groups according to whether they were complicated with diabetes or not. Demographic symptoms and laboratory data were extracted from medical records. Univariable and multivariable logistic regression methods were used to explore the risk factors. Results. 538 COVID-19 patients were finally included in this study, of whom 492 were nondiabetes and 46 were diabetes. The median age was 47 years (IQR 35.0-56.0). And the elderly patients with diabetes were more likely to have dry cough, and the alanine aminotransferase, lactate dehydrogenase, Ca, and mean hemoglobin recovery rate were higher than the other groups. Furthermore, we also found the liver and kidney function of male patients was worse than that of female patients, while female cases should be paid more attention to the occurrence of bleeding and electrolyte disorders. Moreover, advance age, blood glucose, gender, prothrombin time, and total cholesterol could be considered as risk factors for COVID-19 patients with diabetes through the multivariable logistic regression model in our study. Conclusion. The potential risk factors found in our study showed a major piece of the complex puzzle linking diabetes and COVID-19 infection. Meanwhile, focusing on gender and age factors in COVID-19 patients with or without diabetes, specific clinical characteristics, and risk factors should be paid more attention by clinicians to figure out a targeted intervention to improve clinical efficacy worldwide.

With the advancement of artificial intelligence, CNNs have been successfully introduced into the discipline of medical data analyzing. Clinically, automatic pulmonary nodules detection remains an intractable issue since those nodules existing in the lung parenchyma or on the chest wall are tough to be visually distinguished from shadows, background noises, blood vessels, and bones. Thus, when making medical diagnosis, clinical doctors need to first pay attention to the intensity cue and contour characteristic of pulmonary nodules, so as to locate the specific spatial locations of nodules. To automate the detection process, we propose an efficient architecture of multi-task and dual-branch 3D convolution neural networks, called DBPNDNet, for automatic pulmonary nodule detection and segmentation. Among the dual-branch structure, one branch is designed for candidate region extraction of pulmonary nodule detection, while the other incorporated branch is exploited for lesion region semantic segmentation of pulmonary nodules. In addition, we develop a 3D attention weighted feature fusion module according to the doctor’s diagnosis perspective, so that the captured information obtained by the designed segmentation branch can further promote the effect of the adopted detection branch mutually. The experiment has been implemented and assessed on the commonly used dataset for medical image analysis to evaluate our designed framework. On average, our framework achieved a sensitivity of 91.33% false positives per CT scan and reached 97.14% sensitivity with 8 FPs per scan. The results of the experiments indicate that our framework outperforms other mainstream approaches. Graphical Abstract

The Pubugou dam is located on the Dadu River in China, with a height of 186 m. The fracturing body at 780 m upstream of its right bank poses a major threat to the downstream reservoir area’s safety as well as the operation of the dam. In this study, a multi-source three-dimensional monitoring mode of space-ground-body is built using synthetic aperture radar, surface sensing, and rock mass stress monitoring. This makes it possible to keep an eye on the entire fracturing body in real time. This study proposes a GCPs selection method that combines the high coherence, small deformation reference points obtained by PS-InSAR inversion and stable deformation points, and realizes the high-precision bank slope deformation time series data acquisition method. It addresses the issue of strong subjectivity in the selection of ground control points (GCPs) in the SBAS-InSAR solution process in mountainous areas. The change in multiple scattering wave velocity and the evolution of the rock mass state inside the slope are both extracted using the seismic background noise cross-correlation technique. Through time series analysis and comparison of various monitoring data, the three-dimensional deformation characteristics, instability mechanism, and significant influence of rainfall on the deformation development of the fracturing body are summarized. Additionally, the adaptability, advantages, and disadvantages of various monitoring modes are evaluated. For the crucial slope of the project, a more trustworthy monitoring method will be available thanks to the mutual integration of the space-ground-body monitoring mode and data.