Predictive value of HTS grade in patients with intrahepatic cholangiocarcinoma undergoing radical resection: a multicenter study from China.

BACKGROUND: Intrahepatic cholangiocarcinoma (ICC) is a highly malignant tumor with a poor prognosis. This study aimed to investigate whether Hemoglobin, Albumin, Lymphocytes, and Platelets (HALP) score and Tumor Burden Score (TBS) serves as independent influencing factors following radical resection in patients with ICC. Furthermore, we sought to evaluate the predictive capacity of the combined HALP and TBS grade, referred to as HTS grade, and to develop a prognostic prediction model. METHODS: Clinical data for ICC patients who underwent radical resection were retrospectively analyzed. Univariate and multivariate Cox regression analyses were first used to find influencing factors of prognosis for ICC. Receiver operating characteristic (ROC) curves were then used to find the optimal cut-off values for HALP score and TBS and to compare the predictive ability of HALP, TBS, and HTS grade using the area under these curves (AUC). Nomogram prediction models were constructed and validated based on the results of the multivariate analysis. RESULTS: Among 423 patients, 234 (55.3%) were male and 202 (47.8) were aged ≥ 60 years. The cut-off value of HALP was found to be 37.1 and for TBS to be 6.3. Our univariate results showed that HALP, TBS, and HTS grade were prognostic factors of ICC patients (all P < 0.05), and ROC results showed that HTS had the best predictive value. The Kaplan-Meier curve showed that the prognosis of ICC patients was worse with increasing HTS grade. Additionally, multivariate regression analysis showed that HTS grade, carbohydrate antigen 19-9 (CA19-9), tumor differentiation, and vascular invasion were independent influencing factors for Overall survival (OS) and that HTS grade, CA19-9, CEA, vascular invasion and lymph node invasion were independent influencing factors for recurrence-free survival (RFS) (all P < 0.05). In the first, second, and third years of the training group, the AUCs for OS were 0.867, 0.902, and 0.881, and the AUCs for RFS were 0.849, 0.841, and 0.899, respectively. In the first, second, and third years of the validation group, the AUCs for OS were 0.727, 0.771, and 0.763, and the AUCs for RFS were 0.733, 0.746, and 0.801, respectively. Through the examination of calibration curves and using decision curve analysis (DCA), nomograms based on HTS grade showed excellent predictive performance. CONCLUSIONS: Our nomograms based on HTS grade had excellent predictive effects and may thus be able to help clinicians provide individualized clinical decision for ICC patients.

Novel deep learning-based computer-aided diagnosis system for predicting inflammatory activity in ulcerative colitis.

BACKGROUND AND AIMS: Endoscopy is increasingly performed for evaluating patients with ulcerative colitis (UC). However, its diagnostic accuracy is largely affected by the subjectivity of endoscopists' experience and scoring methods, and scoring of selected endoscopic images cannot reflect the inflammation of the entire intestine. We aimed to develop an automatic scoring system using deep-learning technology for consistent and objective scoring of endoscopic images and full-length endoscopic videos of patients with UC. METHODS: We collected 5875 endoscopic images and 20 full-length videos from 332 patients with UC who underwent colonoscopy between January 2017 and March 2021. We trained the artificial intelligence (AI) scoring system using these images, which was then used for full-length video scoring. To more accurately assess and visualize the full-length intestinal inflammation, we divided the large intestine into a fixed number of "areas" (cecum, 20; transverse colon, 20; descending colon, 20; sigmoid colon, 15; rectum, 10). The scoring system automatically scored inflammatory severity of 85 areas from every video and generated a visualized result of full-length intestinal inflammatory activity. RESULTS: Compared with endoscopist scoring, the trained convolutional neural network achieved 86.54% accuracy in the Mayo-scored task, whereas the kappa coefficient was .813 (95% confidence interval [CI], .782-.844). The metrics of the Ulcerative Colitis Endoscopic Index of Severity-scored task were encouraging, with accuracies of 90.7%, 84.6%, and 77.7% and kappa coefficients of .822 (95% CI, .788-.855), .784 (95% CI, .744-.823), and .702 (95% CI, .612-.793) for vascular pattern, erosions and ulcers, and bleeding, respectively. The AI scoring system predicted each bowel segment's score and displayed distribution of inflammatory activity in the entire large intestine using a 2-dimensional colorized image. CONCLUSIONS: We established a novel deep learning-based scoring system to evaluate endoscopic images from patients with UC, which can also accurately describe the severity and distribution of inflammatory activity through full-length intestinal endoscopic videos.

[Effect of a Simple Home-Based Oral Care Regimen on Oral Mucositis in Patients With Oral Cavity and Nasopharyngeal Cancer: A Quasi-Experimental Study].

BACKGROUND: The majority of patients with oral cavity and nasopharyngeal cancer experience severe oral mucositis during concurrent radiochemotherapy. The effectiveness of routine nursing education remains limited. PURPOSE: To evaluate the effect of a simple home-based oral care regimen on oral mucositis. METHODS: A double-group quasi-experimental design was adopted in this study. The participants were all newly diagnosed patients with oral cavity and nasopharyngeal cancer who were scheduled to receive concurrent radiochemotherapy in a northern medical center. A total of 31 patients in the experimental group and 32 patients in the control group were enrolled as participants. The control group received routine care, while the experimental group received an additional six- to seven-week two-way interactive home-based oral care regimen. The measurement tools included a plaque record and oral assessment guide (OAG) implemented twice during the study period. Study data were collected at 8 time points, including before treatment, at 1-5 weeks of treatment, at the end of treatment, and at one-month post-treatment. Data analysis was performed using two-way repeated measures ANCOVA. RESULTS: After controlling for OAG score, nutrition, age, living habits, and oral hygiene, the development of mucositis was found to be significantly slower in the experimental group than in the control group during the traumatic phase (effect of group: F = 11.1, p < .01; effect of group x time: F = 3.5, p = .01). However, both groups reported a statistically similar rate of improvement during the repair phase (effect of group and group x time: F = 0.19, p = .67). CONCLUSIONS / IMPLICATIONS FOR PRACTICE: The simple home-based oral care regimen introduced in this study may be used to improve traumatic oral mucositis in patients with oral cavity and nasopharyngeal cancer. It is recommended that even after the completion of radiotherapy, medical staffs should continue to strengthen patients' execution of proper oral care to maintain the positive effect until the mucositis has abated.

Thyroid nodule recognition using a joint convolutional neural network with information fusion of ultrasound images and radiofrequency data.

OBJECTIVE: To develop a deep learning-based method with information fusion of US images and RF signals for better classification of thyroid nodules (TNs). METHODS: One hundred sixty-three pairs of US images and RF signals of TNs from a cohort of adult patients were used for analysis. We developed an information fusion-based joint convolutional neural network (IF-JCNN) for the differential diagnosis of malignant and benign TNs. The IF-JCNN contains two branched CNNs for deep feature extraction: one for US images and the other one for RF signals. The extracted features are fused at the backend of IF-JCNN for TN classification. RESULTS: Across 5-fold cross-validation, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) obtained by using the IF-JCNN with both US images and RF signals as inputs for TN classification were respectively 0.896 (95% CI 0.838-0.938), 0.885 (95% CI 0.804-0.941), 0.910 (95% CI 0.815-0.966), and 0.956 (95% CI 0.926-0.987), which were better than those obtained by using only US images: 0.822 (0.755-0.878; p = 0.0044), 0.792 (0.679-0.868, p = 0.0091), 0.866 (0.760-0.937, p = 0.197), and 0.901 (0.855-0.948, p = .0398), or RF signals: 0.767 (0.694-0.829, p < 0.001), 0.781 (0.685-0.859, p = 0.0037), 0.746 (0.625-0.845, p < 0.001), 0.845 (0.786-0.903, p < 0.001). CONCLUSIONS: The proposed IF-JCNN model filled the gap of just using US images in CNNs to characterize TNs, and it may serve as a promising tool for assisting the diagnosis of thyroid cancer. KEY POINTS: • Raw radiofrequency signals before ultrasound imaging of thyroid nodules provide useful information that is not carried by ultrasound images. • The information carried by raw radiofrequency signals and ultrasound images for thyroid nodules is complementary. • The performance of deep convolutional neural network for diagnosing thyroid nodules can be significantly improved by fusing US images and RF signals in the model as compared with just using US images.

Elevated serum triglyceride and low-density lipoprotein cholesterol promotes the formation of colorectal polyps.

BACKGROUND: Hyperlipidaemia may be a potential risk factor for the occurrence of intestinal polyps. This study aimed to evaluate correlation between lipidaemia and the formation of colorectal polyps. METHODS: One hundred and fourteen patients with colorectal polyps and forty-eight healthy controls were included in this study. Colonoscopies were performed for all patients and controls within 1 week before blood samples were taken. The concentrations of serum lipids and lipoproteins were measured simultaneously using an automatic biochemical analyser. The colorectal lesions were classified based on pathological characteristics, and four types were identified in the study: hyperplastic polyp (HP), tubular adenoma (TA), tubulovillous adenoma (TVA) and adenoma with high-grade dysplasia (A-HGD). Advanced adenoma was classified according to the number, size and histological type of polyps. RESULTS: The value of low-density lipoprotein cholesterol (LDL-C) was significantly higher in the group with advanced adenoma than in the controls (p < 0.05). Moreover, the LDL-C values in the HP and TA groups were higher when compared to that of controls (p < 0.05). Obesity, age, and increased TG and LDL-C were independent risk factors for the formation of colorectal polyps. The cut-off values of triglyceride (TG) and LDL-C to distinguish polyp patients from healthy controls were 0.96 mmol/L (AUC = 0.604, p = 0.036) and 3.05 mmol/L (AUC = 0.654, p = 0.002). The combined use of increased LDL-C and TG levels to distinguish polyp patients was effective, with a sensitivity of 50.0% and a specificity of 89.6% (AUC = 0.733, p < 0.01). CONCLUSIONS: Colorectal polyps are more often found in obese and older patients. Increased LDL-C and TG were correlated with the occurrence of polyps. Combination of the two serum indicators was useful to assess risk of colorectal lesions, maybe more effective in screening hyperplastic polyp, tubular adenoma and advanced adenoma.

Adipokines: New Therapeutic Target for Osteoarthritis?

PURPOSE OF THE REVIEW: Osteoarthritis (OA) is an aging-associated and injury-induced joint disease characterized by cartilage degradation, bone sclerosis, and persistent low-grade inflammation in the joint. Aging and injury are triggers of joint pathological changes mediated by pro-inflammatory factors, some of which are secreted by white adipose tissue. Adipokines including adiponectin, leptin, resistin, chemerin, IL-6, and TNF-α are major players not only during inflammation but also in metabolic regulation of joint cells including chondrocytes, osteoblasts, osteoclasts as well as mesenchymal stem cells. The purpose of this review is to summarize the signal transduction pathways of adipokines in the articular joint to provide new information on potential targets for intervention of OA. RECENT FINDINGS: The risk of knee osteoarthritis is associated with adipokine gene polymorphism. While the infrapatellar fat pad is a major source of adipokines in knee synovial fluid, adipocytes also accumulate in the bone marrow during aging and obesity. Adipokines can act as SASPs (senescence associated secretory phenotype factors) that participate in cellular senescence of chondrocytes, but they also regulate energy metabolism impacting bone remodeling. Thus, adipokines are closely related to the metabolic syndrome and degenerative pathological changes in cartilage and bone during OA. Modulating the effects of adipokines on different cell types in the intra-articular joint will be a promising new option for OA intervention.

Automatic Tracking of Muscle Cross-Sectional Area Using Convolutional Neural Networks with Ultrasound.

OBJECTIVES: The purpose of this study was to develop an automatic tracking method for the muscle cross-sectional area (CSA) on ultrasound (US) images using a convolutional neural network (CNN). The performance of the proposed method was evaluated and compared with that of the state-of-the art muscle segmentation method. METHODS: A real-time US image sequence was obtained from the rectus femoris muscle during voluntary contraction. A CNN was built to segment the rectus femoris muscle and calculate the CSA in each US frame. This network consisted of 2 stages: feature extraction and score map reconstruction. The training of the network was divided into 3 steps with output score map resolutions of one-fourth, one-half, and all of the original image. We evaluated the segmentation performance of our method with 5-fold cross-validation. The mean precision, recall, and dice similarity score were calculated. RESULTS: The mean precision, recall, and Dice's coefficient (DSC) ± SD were 0.936 ± 0.029, 0.882 ± 0.045, and 0.907 ± 0.023, respectively. Compared with the state-of-the-art muscle segmentation method (constrained mutual-information-based free-form deformation), the proposed method using CNN showed high performance. CONCLUSIONS: The automated method proposed in this study provides an accurate and efficient approach to the estimation of the muscle CSA during muscle contraction.

Gastroesophageal flap valve reflected EGJ morphology and correlated to acid reflux.

OBJECTIVE: The anatomy of esophagogastric junction (EGJ) serves as the anti-reflux barrier. The gastroesophageal flap valve (GEFV) is a component of EGJ. The aim of the current study was to assess its correlation with the esophageal acid exposure and the impact on anti-reflux barrier function by using the metrics of EGJ contraction. METHODS: Eighty three patients with typical GERD symptoms were included in the study. Upper endoscopy, high-resolution manometry (HRM) and 24 h multichannel intraluminal impedance-pH (MII-pH) monitoring were performed in all patients. GEFV was determined as four grades during endoscopic examination based on the Hill classification. The esophageal pressure topography (EPT) metrics defined in the updated Chicago Classification were measured by HRM, including integrated relaxation pressure (IRP), EGJ contractile index (EGJ-CI),expiratory EGJ pressure(EGJP-exp) and inspiratory EGJ pressure (EGJP-insp). RESULTS: The GEFV grade III and IV was more commonly found in patients with esophagitits (p < 0.05). The acid exposure time (AET%) and supine AET% were lower in patients with GEFV grade I (p < 0.01). There was weak correlation between AET% and GEFV grades (r = 0.27, p = 0.013). There were more EGJ morphology type III in patients with GEFV grade IV (p < 0.05).There were no significant differences on the values of four HRM metrics among the patients with different GEFV grades (p > 0.05). CONCLUSION: The GEFV grades were associated with acid reflux positively and could be a good reflection of EGJ morphology in HRM. But it had no impact on the four HRM metrics. Our research revealed that GEFV may play an assistant role in the anti-reflux barrier.

Motility characteristics in the transition zone in Gastroesophageal Reflux Disease (GORD) patients.

BACKGROUND: Defects in distal oesophageal peristalsis was thought to be an indication of incomplete bolus transit (BT). However, the role of transition zone (TZ) defects in the BT in gastroesophageal reflux disease (GORD) patients needs clarification. The aim of this study was to assess the TZ defects in GORD patients and to explore the relationship between TZ defects and BT. METHODS: One hundred and two patients with reflux symptoms and 20 healthy adults were included in the study. All subjects underwent upper gastrointestinal endoscopy, high resolution impedance manometry (HRiM) and 24-h ambulatory multichannel impedance-pH (MII-pH) monitoring. Patients were subgrouped into reflux oesophagitis (RE), non-erosive reflux disease (NERD), hypersensitive oesophagus (HO) and functional heartburn (FH) classified following MII-pH monitoring. Oesophageal pressure topography was analysed to define TZ defects by spatial or temporal TZ measurements exceeding 2 cm or 1 s, weak and fragmented swallows were excluded, and the association between TZ and BT was investigated. RESULTS: Following liquid swallows, there were no significant differences in TZ delay time and TZ length between groups (RE: 1.75 s (1.32-2.17) and 2.50 cm (2.40-3.20); NERD: 1.60 s (1.10-2.00) and 2.20 cm (2.10-2.65); HO: 1.60 s (1.30-1.80) and 2.70 cm (2.30-3.00); FH: 1.55 s (1.20-2.17) and 3.10 cm (2.25-5.00); Healthy volunteers: 1.50 s (1.20-1.90) and 2.30 cm (2.10-3.00). However, individuals with TZ defects had lower complete BT rates compared with those without TZ defects (p < 0.001). There were also significantly more incomplete BT in patients with RE, HO and FH than in healthy controls (p < 0.05). CONCLUSIONS: In GORD patients, TZ defects correlated with proximal bolus retention in the corresponding area independent of distal weak peristalsis.

Crosstalk Between circRNA and Tumor Microenvironment of Hepatocellular Carcinoma: Mechanism, Function and Applications.

Hepatocellular carcinoma (HCC) is one of the most common aggressive tumors in the world. Despite the availability of various treatments, its prognosis remains poor due to the lack of specific diagnostic indicators and the high heterogeneity of HCC cases. CircRNAs are noncoding RNAs with stable and highly specific expression. Extensive research evidence suggests that circRNAs mediate the pathogenesis and progression of HCC through acting as miRNA sponges, protein modulators, and translation templates. Tumor microenvironment (TME) has become a hotspot of immune-related research in recent years due to its effects on metabolism, secretion and immunity of HCC. Accordingly, understanding the role played by circRNAs in TME is important for the study of HCC. This review will discuss the crosstalk between circRNAs and TME in HCC. In addition, we will discuss the current deficiencies and controversies in research on circRNAs and predict future research directions.

Class A1 scavenger receptor antibody improves murine colitis by influencing macrophage and gut microbiota.

This study aimed to investigate whether class A1 scavenger receptor (SR-A1) regulated macrophage polarization and gut microbial alteration during intestinal inflammation of colitis. A murine colitis model was established by feeding with dextran sulfate sodium (DSS), and treatment groups were injected intravenously with SR-A1 antibody. Results showed a preventive effect on colitis symptoms and fewer inflammatory cell infiltrates in treatment groups. Down-regulation of inflammatory cytokines and up-regulation of anti-inflammatory cytokine related to macrophages were seen in murine PBMC and LPMC after injected with SR-A1 antibody. The percentage of M2 macrophages was also elevated in treatment groups. In addition, SR-A1 antibody treatment resulted in the decreased apoptosis and increased proliferation of colonic epithelial cells. Other findings indicated that SR-A1 antibody injection could mediate its anti-inflammatory effect via inhibiting TLR4-MyD88-NF-kB signaling pathway and alterating the gut microbiota composition. Our research identified SR-A1 as a potential therapeutic target in inflammatory bowel disease (IBD).

Bioactive poly(salicylic acid)-poly(citric acid) scaffolds improve diabetic wound repair via regulating HIF-1α, Nrf2 and macrophage.

Diabetic wounds environment is over-oxidized, over-inflammatory, leading to difficulties in regenerating blood vessels, and retardation of healing in diabetic wounds. Therefore, diabetic wounds can be treated from the perspective of scavenging oxidative free radicals and reducing the level of inflammation. Herein, we report a bioactive poly(salicylic acid)-poly(citric acid) (FPSa-PCG) hydrogel for diabetic wound repair. The FPSa-PCG hydrogel shows abilities of antioxidation, anti-inflammation, and regulation of macrophage phenotype. The FPSa-PCG hydrogel showed good biocompatibility, and obtain the abilities of promotion of macrophages migration, reduction of ROS generation, suppression of the M1-type macrophage polarization. FPSa and PCG could synergistically enhance the angiogenesis through upregulating the mRNA expression of HIF1Α, VEGF, and CD31 in endothelial cells and reduce the ROS level of macrophages through upregulating the mRNA expression of Nrf2. The in vivo diabetic wound model confirmed the promoting effect of FPSa-PCG hydrogel on wound closure in diabetes. The further studies found that FPSa-PCG hydrogel could induce the CD31 protein expression in the subcutaneous tissue and inhibit the TNF-a protein expression. This work shows that the simple composition FPSa-PCG hydrogel has a promising therapeutic potential in the treatment of diabetic wounds.

Comparison of Volatile Compounds among Four Types of Teas Analyzed Using Gas Chromatography-Ion Mobility Spectrometry.

Gas chromatography-ion mobility spectrometry (GC-IMS) is a smart method that has been applied to determine the volatile compounds in Chinese teas, but its use in comparing the volatile compounds of different types of tea has not been mentioned. In this study, the volatile compounds found in four types of samples (green, yellow, white, and black teas) made with fresh leaves of Camellia sinensis (L.) Kuntze 'Zhongcha 111' were analyzed using GC-IMS. The results showed that 93 volatile compounds were identified from our tea samples and that the average volume of aldehydes was higher than that for other compounds, especially in white tea. The different samples were successfully categorized using multivariate statistical analysis. Using partial least squares discriminant analysis (PLS-DA), we found 15 key compounds, including four differential components: (E)-2-hexenal, 2-furanmethanethio, 2-hexanol, and 1-octene. There were 29 common components, and their total content reached 386.0 µg/g. Moreover, the 3-methyl-2-butenal and dimethyl disulfide detected in the four samples were also differential compounds, varying according to the manufacturing technology. Thus, this study demonstrates that different types of teas can be discriminated easily using GC-IMS and that this is helpful to shorten the time for improving tea quality and developing new products.

A hybrid unsupervised clustering method for predicting the risk of dental implant loss.

OBJECTIVES: The aim of this study was to predict the risk of dental implant loss by clustering features associated with implant survival rates. MATERIALS AND METHODS: Multiple clinical features from 8513 patients who underwent single implant placement were retrospectively analysed. A hybrid method integrating unsupervised learning algorithms with survival analysis was employed for data mining. Two-step cluster, univariate Cox regression, and Kaplan‒Meier survival analyses were performed to identify the clustering features associated with implant survival rates. To predict the risk of dental implant loss, nomograms were constructed on the basis of time-stratified multivariate Cox regression. RESULTS: Six clusters with distinct features and prognoses were identified using two-step cluster analysis and Kaplan‒Meier survival analysis. Compared with the other clusters, only one cluster presented significantly lower implant survival rates, and six specific clustering features within this cluster were identified as high-risk factors, including age, smoking history, implant diameter, implant length, implant position, and surgical procedure. Nomograms were created to assess the impact of the six high-risk factors on implant loss for three periods: 1) 0-120 days, 2) 120-310 days, and 3) more than 310 days after implant placement. The concordance indices of the models were 0.642, 0.781, and 0.715, respectively. CONCLUSIONS: The hybrid unsupervised clustering method, which clusters and identifies high-risk clinical features associated with implant loss without relying on predefined labels or target variables, represents an effective approach for developing a visual model for predicting implant prognosis. However, further validation with a multimodal, multicentre, prospective cohort is needed. CLINICAL SIGNIFICANCE: Visual prognosis prediction utilizing this nomogram that predicts the risk of implant loss on the basis of clustering features can assist dentists in preoperative assessments and clinical decision-making, potentially improving dental implant prognosis.

RNA velocity prediction via neural ordinary differential equation.

RNA velocity is a crucial tool for unraveling the trajectory of cellular responses. Several approaches, including ordinary differential equations and machine learning models, have been proposed to interpret velocity. However, the practicality of these methods is constrained by underlying assumptions. In this study, we introduce SymVelo, a dual-path framework that effectively integrates high- and low-dimensional information. Rigorous benchmarking and extensive studies demonstrate that SymVelo is capable of inferring differentiation trajectories in developing organs, analyzing gene responses to stimulation, and uncovering transcription dynamics. Moreover, the adaptable architecture of SymVelo enables customization to accommodate intricate data and diverse modalities in forthcoming research, thereby providing a promising avenue for advancing our understanding of cellular behavior.

Comparative Analysis of Therapeutic Efficacy and Adverse Reactions among Various Thrombolytic Agents.

Thrombosis is a major health concern that contributes to the development of several cardiovascular diseases and a significant number of fatalities worldwide. While stent surgery is the current recommended treatment according to the guidelines, percutaneous coronary intervention (PCI) is the optimal approach for acute myocardial infarction (AMI). However, in remote areas with limited resources, PCI procedures may not be feasible, leading to a delay in treatment and irreversible outcomes. In such cases, preoperative thrombolysis becomes the primary choice for managing AMI in remote settings. The market for thrombolytic drugs is continuously evolving, and identifying a safe and effective thrombolytic agent for treating AMI is crucial. This study evaluated Urokinase, Alteplase, and Recombinant Human TNK Tissue-type Plasminogen Activator for Injection (rhTNK) as representatives of first-, second-, and third-generation thrombolytic drugs, respectively. The research included in vitro thrombolysis experiments, exposure of human cardiomyocytes, zebrafish tail vein injections, and vascular endothelial transgenic zebrafish models. The findings revealed that rhTNK is the most effective thrombolytic drug with the least adverse effects and lowest bleeding rate, highlighting its potential as the preferred treatment option for AMI. The order of thrombolytic effectiveness was Urokinase < Alteplase < rhTNK, with adverse effects on cardiomyocytes post-thrombolytic therapy ranking similarly as Urokinase < Alteplase < rhTNK, while the bleeding rate after thrombolysis followed the order of Urokinase > Alteplase > rhTNK.

Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff.

Existing salient object detection methods often adopt deeper and wider networks for better performance, resulting in heavy computational burden and slow inference speed. This inspires us to rethink saliency detection to achieve a favorable balance between efficiency and accuracy. To this end, we design a lightweight framework while maintaining satisfying competitive accuracy. Specifically, we propose a novel trilateral decoder framework by decoupling the U-shape structure into three complementary branches, which are devised to confront the dilution of semantic context, loss of spatial structure and absence of boundary detail, respectively. Along with the fusion of three branches, the coarse segmentation results are gradually refined in structure details and boundary quality. Without adding additional learnable parameters, we further propose Scale-Adaptive Pooling Module to obtain multi-scale receptive field. In particular, on the premise of inheriting this framework, we rethink the relationship among accuracy, parameters and speed via network depth-width tradeoff. With these insightful considerations, we comprehensively design shallower and narrower models to explore the maximum potential of lightweight SOD. Our models are proposed for different application environments: 1) a tiny version CTD-S (1.7M, 125FPS) for resource constrained devices, 2) a fast version CTD-M (12.6M, 158FPS) for speed-demanding scenarios, 3) a standard version CTD-L (26.5M, 84FPS) for high-performance platforms. Extensive experiments validate the superiority of our method, which achieves better efficiency-accuracy balance across five benchmarks.

Multi-layer-structured bioactive glass nanopowder for multistage-stimulated hemostasis and wound repair.

Current treatments for full-thickness skin injuries are still unsatisfactory due to the lack of hierarchically stimulated dressings that can integrate the rapid hemostasis, inflammation regulation, and skin tissue remodeling into the one system instead of single-stage boosting. In this work, a multilayer-structured bioactive glass nanopowder (BGN@PTE) is developed by coating the poly-tannic acid and ε-polylysine onto the BGN via facile layer-by-layer assembly as an integrative and multilevel dressing for the sequential management of wounds. In comparison to BGN and poly-tannic acid coated BGN, BGN@PTE exhibited the better hemostatic performance because of its multiple dependent approaches to induce the platelet adhesion/activation, red blood cells (RBCs) aggregation and fibrin network formation. Simultaneously, the bioactive ions from BGN facilitate the regulation of the inflammatory response while the poly-tannic acid and antibacterial ε-polylysine prevent the wound infection, promoting the wound healing during the inflammatory stage. In addition, BGN@PTE can serve as a reactive oxygen species scavenger, alleviate the oxidation stress in wound injury, induce the cell migration and angiogenesis, and promote the proliferation stage of wound repair. Therefore, BGN@PTE demonstrated the significantly higher wound repair capacity than the commercial bioglass dressing Dermlin™. This multifunctional BGN@PTE is a potentially valuable dressing for full-thickness wound management and may be expected to extend to the other wounds therapy.

Photoactivated MXene Nanosheets for Integrated Bone-Soft Tissue Therapy: Effect and Potential Mechanism.

The bone defects caused by trauma are inevitably accompanied by soft tissue damage. The development of multifunctional bioactive biomaterials with integrated bone and soft tissue regeneration is necessary and needed urgently in orthopedics. In this work, we found that the photoactivated MXene (Ti3C2Tx) nanosheet showed positive effects on promoting both bone and soft tissue regeneration. We further investigated the detailed effect and potential mechanism of photoactivated MXene on tissue regeneration. Photoactivated MXene shows a good thermal effect and robust antibacterial activity to inhibit the expression of inflammation factors and methicillin-resistant Staphylococcus aureus (MRSA) infection and induces the expression of pro-angiogenic factors and soft tissue wound repair. Photoactivated MXene can also regulate the osteogenic differentiation of adipose-derived stem cells (ADSCs) through the ERK signaling pathway by activating the heat shock protein 70 (HSP70) and enhancing the repair of bone tissue. This work sheds light on the development of bioactive MXene with photothermal activation as an efficient strategy for bone and soft tissue regeneration simultaneously.

Boosting Broader Receptive Fields for Salient Object Detection.

Salient Object Detection has boomed in recent years and achieved impressive performance on regular-scale targets. However, existing methods encounter performance bottlenecks in processing objects with scale variation, especially extremely large- or small-scale objects with asymmetric segmentation requirements, since they are inefficient in obtaining more comprehensive receptive fields. With this issue in mind, this paper proposes a framework named BBRF for Boosting Broader Receptive Fields, which includes a Bilateral Extreme Stripping (BES) encoder, a Dynamic Complementary Attention Module (DCAM) and a Switch-Path Decoder (SPD) with a new boosting loss under the guidance of Loop Compensation Strategy (LCS). Specifically, we rethink the characteristics of the bilateral networks, and construct a BES encoder that separates semantics and details in an extreme way so as to get the broader receptive fields and obtain the ability to perceive extreme large- or small-scale objects. Then, the bilateral features generated by the proposed BES encoder can be dynamically filtered by the newly proposed DCAM. This module interactively provides spacial-wise and channel-wise dynamic attention weights for the semantic and detail branches of our BES encoder. Furthermore, we subsequently propose a Loop Compensation Strategy to boost the scale-specific features of multiple decision paths in SPD. These decision paths form a feature loop chain, which creates mutually compensating features under the supervision of boosting loss. Experiments on five benchmark datasets demonstrate that the proposed BBRF has a great advantage to cope with scale variation and can reduce the Mean Absolute Error over 20% compared with the state-of-the-art methods.