EcoDetect-YOLO: A Lightweight, High-Generalization Methodology for Real-Time Detection of Domestic Waste Exposure in Intricate Environmental Landscapes.

In response to the challenges of accurate identification and localization of garbage in intricate urban street environments, this paper proposes EcoDetect-YOLO, a garbage exposure detection algorithm based on the YOLOv5s framework, utilizing an intricate environment waste exposure detection dataset constructed in this study. Initially, a convolutional block attention module (CBAM) is integrated between the second level of the feature pyramid etwork (P2) and the third level of the feature pyramid network (P3) layers to optimize the extraction of relevant garbage features while mitigating background noise. Subsequently, a P2 small-target detection head enhances the model's efficacy in identifying small garbage targets. Lastly, a bidirectional feature pyramid network (BiFPN) is introduced to strengthen the model's capability for deep feature fusion. Experimental results demonstrate EcoDetect-YOLO's adaptability to urban environments and its superior small-target detection capabilities, effectively recognizing nine types of garbage, such as paper and plastic trash. Compared to the baseline YOLOv5s model, EcoDetect-YOLO achieved a 4.7% increase in mAP0.5, reaching 58.1%, with a compact model size of 15.7 MB and an FPS of 39.36. Notably, even in the presence of strong noise, the model maintained a mAP0.5 exceeding 50%, underscoring its robustness. In summary, EcoDetect-YOLO, as proposed in this paper, boasts high precision, efficiency, and compactness, rendering it suitable for deployment on mobile devices for real-time detection and management of urban garbage exposure, thereby advancing urban automation governance and digital economic development.

Perioperative Toripalimab Plus Chemotherapy for Patients With Resectable Non-Small Cell Lung Cancer: The Neotorch Randomized Clinical Trial.

Importance: Adjuvant and neoadjuvant immunotherapy have improved clinical outcomes for patients with early-stage non-small cell lung cancer (NSCLC). However, the optimal combination of checkpoint inhibition with chemotherapy remains unknown. Objective: To determine whether toripalimab in combination with platinum-based chemotherapy will improve event-free survival and major pathological response in patients with stage II or III resectable NSCLC compared with chemotherapy alone. Design, Setting, and Participants: This randomized clinical trial enrolled patients with stage II or III resectable NSCLC (without EGFR or ALK alterations for nonsquamous NSCLC) from March 12, 2020, to June 19, 2023, at 50 participating hospitals in China. The data cutoff date for this interim analysis was November 30, 2022. Interventions: Patients were randomized in a 1:1 ratio to receive 240 mg of toripalimab or placebo once every 3 weeks combined with platinum-based chemotherapy for 3 cycles before surgery and 1 cycle after surgery, followed by toripalimab only (240 mg) or placebo once every 3 weeks for up to 13 cycles. Main Outcomes and Measures: The primary outcomes were event-free survival (assessed by the investigators) and the major pathological response rate (assessed by blinded, independent pathological review). The secondary outcomes included the pathological complete response rate (assessed by blinded, independent pathological review) and adverse events. Results: Of the 501 patients randomized, 404 had stage III NSCLC (202 in the toripalimab + chemotherapy group and 202 in the placebo + chemotherapy group) and 97 had stage II NSCLC and were excluded from this interim analysis. The median age was 62 years (IQR, 56-65 years), 92% of patients were male, and the median follow-up was 18.3 months (IQR, 12.7-22.5 months). For the primary outcome of event-free survival, the median length was not estimable (95% CI, 24.4 months-not estimable) in the toripalimab group compared with 15.1 months (95% CI, 10.6-21.9 months) in the placebo group (hazard ratio, 0.40 [95% CI, 0.28-0.57], P < .001). The major pathological response rate (another primary outcome) was 48.5% (95% CI, 41.4%-55.6%) in the toripalimab group compared with 8.4% (95% CI, 5.0%-13.1%) in the placebo group (between-group difference, 40.2% [95% CI, 32.2%-48.1%], P < .001). The pathological complete response rate (secondary outcome) was 24.8% (95% CI, 19.0%-31.3%) in the toripalimab group compared with 1.0% (95% CI, 0.1%-3.5%) in the placebo group (between-group difference, 23.7% [95% CI, 17.6%-29.8%]). The incidence of immune-related adverse events occurred more frequently in the toripalimab group. No unexpected treatment-related toxic effects were identified. The incidence of grade 3 or higher adverse events, fatal adverse events, and adverse events leading to discontinuation of treatment were comparable between the groups. Conclusions and Relevance: The addition of toripalimab to perioperative chemotherapy led to a significant improvement in event-free survival for patients with resectable stage III NSCLC and this treatment strategy had a manageable safety profile. Trial Registration: ClinicalTrials.gov Identifier: NCT04158440.

Exosomal HMGB3 released by glioma cells confers the activation of NLRP3 inflammasome and pyroptosis in tumor-associated macrophages.

BACKGROUND: Previous evidences has highlighted the pivotal role of NOD-like receptor family pyrin domain-containing 3 (NLRP3)-mediated inflammasomes and pyroptosis activation in driving tumor malignancy and shaping the tumor microenvironment. Herein, we aimed to elucidate the impact of high-mobility group box 3 (HMGB3) released in glioma-derived exosomes on macrophage infiltration in gliomas, NLRP3 inflammasome activation and polarization. METHODS: Transcripts and protein levels of HMGB3, and cytokines associated with macrophage phenotypes and pyroptosis were assessed in glioma tissues and cell lines (U251, LN229, T98G, A172) using qRT-PCR and/or Western blot analysis. Exosomes secreted from LN229 and NHA cells were isolated via differential ultracentrifugation and characterized by transmission electron microscopy (TEM), nanoparticle tracking analysis (NTA), and analysis of exosome-related markers. PKH67 staining was employed to examine exosomes uptake by THP-1 differentiated macrophages. Flow cytometry was utilized to assess macrophage pyroptotic rates and polarization-related markers. RESULTS: HMGB3 expression was elevated in glioma tissues, serum samples and tumor cell lines. Kaplan-Meier curves revealed a positive correlation between higher HMGB3 expression and poor overall survival and recurrence-free survival. Moreover, glioma tissues with increased HMGB3 expression exhibited significant upregulation of M2 macrophages markers (CD68, CD206, Arg1) and NLRP3 inflammasome components (NLRP3, IL-1ß, ASC), suggesting that HMGB3 was closely associated with macrophage infiltration and NLRP3 inflammasome activation. Notably, HMGB3 was found to be enriched in glioma cell- secreted exosomes and could be internalized by macrophages. Knockdown of HMGB3 in glioma cell exosomes could restrain M2 macrophage polarization, NLRP3 inflammasome activation and pyroptosis. CONCLUSION: These findings suggested that glioma cells secreted exosomal HMGB3 could facilitate macrophage M2 polarization, pyroptosis and inflammatory infiltration, indicating HMGB3 might be a poor prognosis factor for glioma.

ZNF384 transcriptionally activated MGST1 to confer TMZ resistance of glioma cells by negatively regulating ferroptosis.

BACKGROUND: Drug resistance is one of the major reasons of the poor prognosis and recurs frequently in glioma. Ferroptosis is considered to be a new therapeutic strategy for glioma. METHODS: Microsomal glutathione S-transferase 1 (MGST1) expression in glioma samples was ensured through GAPIA database, qRT-PCR, western blotting assay and immunohistochemistry. The interaction between zinc finger protein 384 (ZNF384) and MGST1 promoter was analyzed through UCSC and JASPAR databases and further verified by ChIP and luciferase reporter assay. Cell viability and IC50 value of temozolomide (TMZ) was measured by CCK-8 assay. The production of MDA, GSH and ROS and the level of Fe2+ were determined using the corresponding kit. RESULTS: MGST1 expression was increased in clinical glioma tissues and glioma cells. MGST1 expression was increased but ferroptosis was suppressed in TMZ-resistant cells when contrasted to parent cells. MGST1 silencing downregulated IC50 value of TMZ and cell viability but facilitated ferroptosis in TMZ-resistant cells and parent glioma cells. Moreover, our data indicated that ZNF384 interacted with MGST1 promoter and facilitated MGST1 expression. ZNF384 was also increased expression in TMZ-resistant cells, and showed a positive correlation with MGST1 expression in clinical level. ZNF384 decreasing enhanced the sensitivity of resistant cells to TMZ, while the effect of ZNF384 could be reversed by overexpression of MGST1. CONCLUSION: MGST1 transcription is regulated by transcription factor ZNF384 in TMZ-resistant cells. ZNF384 confers the resistance of glioma cells to TMZ through inhibition of ferroptosis by positively regulating MGST1 expression. The current study may provide some new understand to the mechanism of TMZ resistance in glioma.

Deep learning-assisted detection and segmentation of intracranial hemorrhage in noncontrast computed tomography scans of acute stroke patients: a systematic review and meta-analysis.

BACKGROUND: Deep learning (DL)-assisted detection and segmentation of intracranial hemorrhage stroke in noncontrast computed tomography (NCCT) scans are well-established, but evidence on this topic is lacking. MATERIALS AND METHODS: PubMed and Embase databases were searched from their inception to November 2023 to identify related studies. The primary outcomes included sensitivity, specificity, and the Dice Similarity Coefficient (DSC); while the secondary outcomes were positive predictive value (PPV), negative predictive value (NPV), precision, area under the receiver operating characteristic curve (AUROC), processing time, and volume of bleeding. Random-effect model and bivariate model were used to pooled independent effect size and diagnostic meta-analysis data, respectively. RESULTS: A total of 36 original studies were included in this meta-analysis. Pooled results indicated that DL technologies have a comparable performance in intracranial hemorrhage detection and segmentation with high values of sensitivity (0.89, 95% CI: 0.88-0.90), specificity (0.91, 95% CI: 0.89-0.93), AUROC (0.94, 95% CI: 0.93-0.95), PPV (0.92, 95% CI: 0.91-0.93), NPV (0.94, 95% CI: 0.91-0.96), precision (0.83, 95% CI: 0.77-0.90), DSC (0.84, 95% CI: 0.82-0.87). There is no significant difference between manual labeling and DL technologies in hemorrhage quantification (MD 0.08, 95% CI: -5.45-5.60, P =0.98), but the latter takes less process time than manual labeling (WMD 2.26, 95% CI: 1.96-2.56, P =0.001). CONCLUSION: This systematic review has identified a range of DL algorithms that the performance was comparable to experienced clinicians in hemorrhage lesions identification, segmentation, and quantification but with greater efficiency and reduced cost. It is highly emphasized that multicenter randomized controlled clinical trials will be needed to validate the performance of these tools in the future, paving the way for fast and efficient decision-making during clinical procedure in patients with acute hemorrhagic stroke.

Deep learning-based quantification of total bleeding volume and its association with complications, disability, and death in patients with aneurysmal subarachnoid hemorrhage.

OBJECTIVE: The relationships between immediate bleeding severity, postoperative complications, and long-term functional outcomes in patients with aneurysmal subarachnoid hemorrhage (aSAH) remain uncertain. Here, the authors apply their recently developed automated deep learning technique to quantify total bleeding volume (TBV) in patients with aSAH and investigate associations between quantitative TBV and secondary complications, adverse long-term functional outcomes, and death. METHODS: Electronic health record data were extracted for adult patients admitted to a single institution within 72 hours of aSAH onset between 2018 and 2021. An automatic deep learning model was used to fully segment and quantify TBV on admission noncontrast head CT images. Patients were subgrouped by TBV quartile, and multivariable logistic regression, restricted cubic splines, and subgroup analysis were used to explore the relationships between TBV and each clinical outcome. RESULTS: A total of 819 patients were included in the study. Sixty-six (8.1%) patients developed hydrocephalus, while 43 (5.3%) experienced rebleeding, 141 (17.2%) had delayed cerebral ischemia, 88 (10.7%) died in the 12 months after discharge, and 208 (25.7%) had a modified Rankin Scale score ≥ 3 12 months after discharge. On multivariable analysis, patients in the highest TBV quartile (> 37.94 ml) had an increased risk of hydrocephalus (adjusted OR [aOR] 4.38, 95% CI 1.61-11.87; p = 0.004), rebleeding (aOR 3.26, 95% CI 1.03-10.33; p = 0.045), death (aOR 6.92, 95% CI 1.89-25.37; p = 0.004), and 12-month disability (aOR 3.30, 95% CI 1.62-6.72; p = 0.001) compared with the lowest TBV quantile (< 8.34 ml). The risks of hydrocephalus (nonlinear, p = 0.025), rebleeding, death, and disability (linear, p > 0.05) were positively associated with TBV by restricted cubic splines. In subgroup analysis, TBV had a stronger effect on 12-month outcome in female than male patients (p for interaction = 0.0499) and on rebleeding prevalence in patients with endovascular coiling than those with surgical clipping (p for interaction = 0.008). CONCLUSIONS: Elevated TBV is associated with a greater risk of hydrocephalus, rebleeding, death, and poor prognosis.

Comprehensive analyses of m1A regulator-mediated modification patterns determining prognosis in lower-grade glioma (running title: m1A in LGG).

N1-methyladenosine (m1A) modification is a crucial post-transcriptional regulatory mechanism of messenger RNA (mRNA) in living organisms. Few studies have focused on analysis of m1A regulators in lower-grade gliomas (LGG). We employed the Nonnegative Matrix Factorization (NMF) technique on The Cancer Genome Atlas (TCGA) dataset to categorize LGG patients into 2 groups. These groups exhibited substantial disparities in terms of both overall survival (OS) and levels of infiltrating immune cells. We collected the significantly differentially expressed immune-related genes between the 2 clusters, and performed LASSO regression analysis to obtain m1AScores, and established an m1A-related immune-related gene signature (m1A-RIGS). Next, we categorized all patients with LGG into high- and low-risk subgroups, predictive significance of m1AScore was confirmed by conducting univariate/multivariate Cox regression analyses. Additionally, we confirmed variations in immune-related cells and ssGSEA and among the high-/low-risk subcategories in the TCGA dataset. Finally, our study characterized the effects of MSR1 and BIRC5 on LGG cells utilizing Edu assay and flow cytometry to explore the effects of modulation of these genes on glioma. The results of this study suggested that m1A-RIGS may be an excellent prognostic indicator for patients with LGG, and could also promote development of novel immune-based treatment strategies for LGG. Additionally, BIRC5 and MSR1 may be potential therapeutic targets for LGG.

Explainable machine learning in outcome prediction of high-grade aneurysmal subarachnoid hemorrhage.

OBJECTIVE: Accurate prognostic prediction in patients with high-grade aneruysmal subarachnoid hemorrhage (aSAH) is essential for personalized treatment. In this study, we developed an interpretable prognostic machine learning model for high-grade aSAH patients using SHapley Additive exPlanations (SHAP). METHODS: A prospective registry cohort of high-grade aSAH patients was collected in one single-center hospital. The endpoint in our study is a 12-month follow-up outcome. The dataset was divided into training and validation sets in a 7:3 ratio. Machine learning algorithms, including Logistic regression model (LR), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost), were employed to develop a prognostic prediction model for high-grade aSAH. The optimal model was selected for SHAP analysis. RESULTS: Among the 421 patients, 204 (48.5%) exhibited poor prognosis. The RF model demonstrated superior performance compared to LR (AUC = 0.850, 95% CI: 0.783-0.918), SVM (AUC = 0.862, 95% CI: 0.799-0.926), and XGBoost (AUC = 0.850, 95% CI: 0.783-0.917) with an AUC of 0.867 (95% CI: 0.806-0 .929). Primary prognostic features identified through SHAP analysis included higher World Federation of Neurosurgical Societies (WFNS) grade, higher modified Fisher score (mFS) and advanced age, were found to be associated with 12-month unfavorable outcome, while the treatment of coiling embolization for aSAH drove the prediction towards favorable prognosis. Additionally, the SHAP force plot visualized individual prognosis predictions. CONCLUSIONS: This study demonstrated the potential of machine learning techniques in prognostic prediction for high-grade aSAH patients. The features identified through SHAP analysis enhance model interpretability and provide guidance for clinical decision-making.

Endosome-microautophagy targeting chimera (eMIATAC) for targeted proteins degradation and enhance CAR-T cell anti-tumor therapy.

Rationale: Since oncogene expression products often exhibit upregulation or abnormally activated activity, developing a technique to regulate abnormal protein levels represent a viable approach for treating tumors and protein abnormality-related diseases. Methods: We first screened out eMIATAC components with high targeted degradation efficiency and explored the mechanism by which eMIATAC induced target protein degradation, and verified the degradation efficiency of the target protein by protein imprinting and flow cytometry. Next, we recombined eMIATAC with some controllable elements to verify the regulatable degradation performance of the target protein. Subsequently, we constructed eMIATAC that can express targeted degradation of AKT1 and verified its effect on GBM cell development in vitro and in vivo. Finally, we concatenated eMIATAC with CAR sequences to construct CAR-T cells with low BATF protein levels and verified the changes in their anti-tumor efficacy. Results: we developed a system based on the endosome-microautophagy-lysosome pathway for degrading endogenous proteins: endosome-MicroAutophagy TArgeting Chimera (eMIATAC), dependent on Vps4A instead of lysosomal-associated membrane protein 2A (LAMP2A) to bind to the chaperone Hsc70 and the protein of interest (POI). The complex was then transported to the lysosome by late endosomes, where degradation occurred similarly to microautophagy. The eMIATACs demonstrated accuracy, efficiency, reversibility, and controllability in degrading the target protein EGFP. Moreover, eMIATAC exhibited excellent performance in knocking down POI when targeting endogenous proteins in vivo and in vitro. Conclusions: The eMIATACs could not only directly knock down abnormal proteins for glioma treatment but also enhance the therapeutic effect of CAR-T cell therapy for tumors by knocking down T cell exhaustion-related proteins. The newly developed eMIATAC system holds promise as a novel tool for protein knockdown strategies. By enabling direct control over endogenous protein levels, eMIATAC has the potential to revolutionize treatment for cancer and genetic diseases.