Phytochemicals derived from Nicotiana tabacum L. plant contribute to pharmaceutical development.

The Nicotiana tabacum L. plant, a medicinal resource, holds significant potential for benefiting human health, as evidenced by its use in Native American and ancient Chinese cultures. Modern medical and pharmaceutical studies have investigated that the abundant and distinctive function metabolites in tobacco including nicotine, solanesol, cembranoid diterpenes, essential oil, seed oil and other tobacco extracts, avoiding the toxic components of smoke, mainly have the anti-oxidation, anti-lipid production, pro-lipid oxidation, pro-insulin sensitivity, anti-inflammation, anti-apoptosis and antimicrobial activities. They showed potential pharmaceutical value mainly as supplements or substitutes for treating neurodegenerative diseases including Alzheimer's and Parkinson's disease, inflammatory diseases including colitis, arthritis, sepsis, multiple sclerosis, and myocarditis, and metabolic syndrome including Obesity and fatty liver. This review comprehensively presents the research status and the molecular mechanisms of tobacco and its metabolites basing on almost all the English and Chinese literature in recent 20 years in the field of medicine and pharmacology. This review serves as a foundation for future research on the medicinal potential of tobacco plants.

DBH-YOLO: a surgical instrument detection method based on feature separation in laparoscopic surgery.

PURPOSE: Accurately locating and analysing surgical instruments in laparoscopic surgical videos can assist doctors in postoperative quality assessment. This can provide patients with more scientific and rational solutions for healing surgical complications. Therefore, we propose an end-to-end algorithm for the detection of surgical instruments. METHODS: Dual-Branched Head (DBH) and Overall Intersection over Union Loss (OIoU Loss) are introduced to solve the problem of inaccurate surgical instrument detection, both in terms of localization and classification. An effective method (DBHYOLO) for the detection for laparoscopic surgery in complex scenarios is proposed. This study manually annotates a new laparoscopic gastric cancer resection surgical instrument location dataset LGIL, which provides a better validation platform for surgical instrument detection methods. RESULTS: The proposed method's performance was tested using the m2cai16-tool-locations, LGIL, and Onyeogulu datasets. The mean Average Precision (mAP) values obtained were 96.8%, 95.6%, and 98.4%, respectively, which were higher than the other classical models compared. The improved model is more effective than the benchmark network in distinguishing between surgical instrument classes with high similarity and avoiding too many missed detection cases. CONCLUSIONS: In this paper, the problem of inaccurate detection of surgical instruments is addressed from two different perspectives: classification and localization. And the experimental results on three representative datasets verify the performance of DBH-YOLO. It is shown that this method has a good generalization capability.

Knowledge, attitudes, practices, and self-efficacy of the Chinese public regarding cardiopulmonary resuscitation: an online cross-sectional survey.

Objective: To evaluate the current status of Chinese public's knowledge, attitudes, practices (KAP) and self-efficacy regarding cardiopulmonary resuscitation (CPR), and to analyze the factors that influence KAP and self-efficacy. Methods: An online cross-sectional survey was conducted from February to June 2022 in Mainland China via a self-designed self-filled questionnaire. Potential participants were recruited through WeChat by convenience sampling and snowball sampling methods. Descriptive and quantitative analyses were used for statistical analysis. Results: The survey included 4,450 participants from 31 provinces, autonomous regions, or municipalities across Mainland China, aged 18 or above. The public's average understanding (clear and very clear) of the knowledge regarding CPR was 67.4% (3,000/4,450), with an average proportion of positive attitudes at 96.8% (4,308/4,450). In practice, the average proportion of good practices was 92.8% (4,130/4,450), while the percentage of good self-efficacy averaged at 58.9% (2,621/4,450), only 42.4% (1,885/4,450) of the participants had confidence in the correct use of automated external defibrillator (AED). Pearson correlation analysis showed a significantly positive correlation among knowledge, attitude, practice, and self-efficacy (p < 0.01). Multiple linear regression analysis revealed that several factors have a significant influence on the public's CPR KAP and self-efficacy, including ever having received CPR training (p < 0.001), hearing about AED (p < 0.001), performing CPR on others (p < 0.001), hearing about CPR (p < 0.001), occupation (p < 0.001), personal health status (p < 0.001), education level (p < 0.001), gender (p < 0.001), and encountering someone in need of CPR (p = 0.021). Conclusion: The Chinese public demonstrates good knowledge of CPR, positive attitude, and high willingness to perform CPR. However, there is still room for improvement in the mastery of some professional knowledge points related to CPR and AED. It should be noted that knowledge, attitude, practice, and self-efficacy are interrelated and influence each other. Factors such as prior CPR training, hearing about AED, having performed CPR before, hearing about CPR, occupation, personal health status, education level, gender, and having encountered someone in need of CPR have a significant impact on the public's KAP and self-efficacy.

TFCNet: A texture-aware and fine-grained feature compensated polyp detection network.

PURPOSE: Abnormal tissue detection is a prerequisite for medical image analysis and computer-aided diagnosis and treatment. The use of neural networks (CNN) to achieve accurate detection of intestinal polyps is beneficial to the early diagnosis and treatment of colorectal cancer. Currently, image detection models using multi-scale feature processing perform well in polyp detection. However, these methods do not fully consider the misalignment of information in the process of feature scale change, resulting in the loss of fine-grained features, and eventually cause the missed and false detection of targets. METHOD: To solve this problem, a texture-aware and fine-grained feature compensated polyp detection network (TFCNet) is proposed in this paper. Firstly, design Texture Awareness Module (TAM) to excavate the rich texture information from the low-level layers and utilize high-level semantic information for background suppression, thereby capturing purer fine-grained features. Secondly, the Texture Feature Enhancement Module (TFEM) is designed to enhance the low-level texture information in TAM, and the enhanced texture features were fused with the high-level features. By making full use of the low-level texture features and multi-scale context information, the semantic consistency and integrity of the features were ensured. Finally, the Residual Pyramid Splittable Attention Module (RPSA) is designed to balance the loss of channel information caused by skip connections, and further improve the detection performance of the network. RESULTS: Experimental results on 4 datasets demonstrate that the TFCNet network outperforms existing methods. Particularly, on the large dataset PolypSets, the mAP@0.5-0.95 has been improved to 88.9%. On the small datasets CVC-ClinicDB and Kvasir, the mAP@0.5-0.95 is increased by 2% and 1.6%, respectively, compared to the baseline, showcasing a significant superiority over competing methods.

A Novel Multi-compartment Rotating Bioreactor for Improving ADSC--Spheroid Formation and its Application in Neurogenic Erectile Dysfunction.

OBJECTIVE: The aim of this study was to construct a multicompartment synchronous rotating bioreactor (MCSRB) for batch-production of homogenized adipose-derived stem cell (ADSC) microspheres and treat neurogenic erectile dysfunction (ED). METHODS: Firstly, an MCSRB was constructed using a centrifugal device and hinged trays. Secondly, influence factors (density, rotational speed) on the formation of ADSC-spheroids were explored. Finally, a neurogenic ED model was established to verify the effectiveness and safety of ADSC-spheroids for ED treatment. RESULTS: An MCSRB promoted ADSCs to gather microspheres, most of which were 90-130 µm in diameter. Supernatant from three-dimensional culture led to a significant increase in cytokine expression in ADSCs and migration rate in human umbilical vein endothelial cells (HUVECs) compared to control groups. The erectile function and pathological changes of the penis were improved in the ADSC-spheroids treatment group compared to the traditional ADSCs treatment group (p < 0.01). CONCLUSION: Efficient, batch, controlled and homogenized production of ADSC stem cell microspheres, and effective improvement of erectile dysfunction in neurogenic rats can be achieved using the MCSRB device.

PVGAN: A Pathological Voice Generation Model Incorporating a Progressive Nesting Strategy.

The voice generation task is to solve the problem of limited samples in the voice dataset using computer technology. By increasing the number of samples, the accuracy of voice disorder diagnosis can be improved, which has a wide range of application value in medical diagnosis and other fields. At present, there are insufficient models for detailed features such as pitch, timbre, and different frequency components in pathological voice data. Therefore, this paper proposes a PVGAN network for learning different frequency information of audio to generate pathological voice data. The proposed network captures the multi-scale features and different periodic patterns of audio signals by designing multiscale perceptual residual blocks and periodic discriminators. At the same time, a progressive nesting strategy was proposed to combine the generator and the discriminator to improve the learning ability of different resolution information. In addition, a latent mapping network is designed to fuse the latent vector with the condition information to generate sound features related to specific diseases or pathological states. The loss function is optimized to further improve the model performance. On the Saarbruecken Voice Database(SVD), the average values of each index of the data generated after training with different pathological types as conditional information are similar to the original data. Finally, the generated data were used to expand the SVD dataset, and the accuracy of the two classification experiments was improved to a certain extent.

Feature selection based on unsupervised clustering evaluation for predicting neoadjuvant chemoradiation response for patients with locally advanced rectal cancer.

Accurate response prediction allows for personalized cancer treatment of locally advanced rectal cancer (LARC) with neoadjuvant chemoradiation. In this work, we designed a convolutional neural network (CNN) feature extractor with switchable 3D and 2D convolutional kernels to extract deep learning features for response prediction. Compared with radiomics features, convolutional kernels may adaptively extract local or global image features from multi-modal MR sequences without the need of feature predefinition. We then developed an unsupervised clustering based evaluation method to improve the feature selection operation in the feature space formed by the combination of CNN features and radiomics features. While normal process of feature selection generally includes the operations of classifier training and classification execution, the process needs to be repeated many times after new feature combinations were found to evaluate the model performance, which incurs a significant time cost. To address this issue, we proposed a cost effective process to use a constructed unsupervised clustering analysis indicator to replace the classifier training process by indirectly evaluating the quality of new found feature combinations in feature selection process. We evaluated the proposed method using 43 LARC patients underwent neoadjuvant chemoradiation. Our prediction model achieved accuracy, area-under-curve (AUC), sensitivity and specificity of 0.852, 0.871, 0.868, and 0.735 respectively. Compared with traditional radiomics methods, the prediction models (AUC = 0.846) based on deep learning-based feature sets are significantly better than traditional radiomics methods (AUC = 0.714). The experiments also showed following findings: (1) the features with higher predictive power are mainly from high-order abstract features extracted by CNN on ADC images and T2 images; (2) both ADC_Radiomics and ADC_CNN features are more advantageous for predicting treatment responses than the radiomics and CNN features extracted from T2 images; (3) 3D CNN features are more effective than 2D CNN features in the treatment response prediction. The proposed unsupervised clustering indicator is feasible with low computational cost, which facilitates the discovery of valuable solutions by highlighting the correlation and complementarity between different types of features.

Intraocular Lens Power Calculation in Eyes After Myopic Laser Refractive Surgery and Radial Keratotomy: Bayesian Network Meta-analysis.

PURPOSE: To compare the accuracy of formulas for calculating intraocular lens power in eyes after myopic laser refractive surgery or radial keratotomy. DESIGN: Bayesian network meta-analysis. METHODS: PubMed, Embase, the Cochrane Data Base of Systematic Reviews, and the Cochrane Central Register of Controlled Trials databases were searched for retrospective and prospective clinical studies published from January 1, 2012, to August 24, 2022. The outcome measurement was the percentage of eyes with a predicted error within the target refractive range (±0.50 diopter [D] or ±1.00 D). RESULTS: Our meta-analysis includes 24 studies of 1172 eyes after myopic refractive surgery that use 12 formulas for intraocular lens power calculation. (1) A network meta-analysis showed that Barrett true-K no history, the optical coherence tomography (OCT) formula, and the Masket formula had a significantly higher percent of eyes within ±0.50 D of the goal than the Haigis-L formula, whereas the Wang-Koch-Maloney formula showed the poor predictability. Using an error criterion of within ±1.00 D, the same 3 formulas performed slightly better than the Haigis-L formula. Based on performance using both prediction error criteria, the Barrett true-K no history formula, OCT formula, and Masket formula showed the highest probability of ranking as the top 3 among the 12 methods. (2) A direct meta-analysis with a subset of 4 studies and 5 formulas indicated that formulas did not differ in percent success for either the ±0.5 D or ±1.0 D error range in eyes that had undergone radial keratotomy. CONCLUSIONS: The OCT, Masket, and Barrett true-K no history formulas are more accurate for eyes with previous myopic laser refractive surgery, whereas no significant difference was found among the formulas for eyes that had undergone radial keratotomy.

The ribosomal protein P0A is required for embryo development in rice.

BACKGROUND: The P-stalk is a conserved and vital structural element of ribosome. The eukaryotic P-stalk exists as a P0-(P1-P2)2 pentameric complex, in which P0 function as a base structure for incorporating the stalk onto 60S pre-ribosome. Prior studies have suggested that P0 genes are indispensable for survival in yeast and animals. However, the functions of P0 genes in plants remain elusive. RESULTS: In the present study, we show that rice has three P0 genes predicted to encode highly conserved proteins OsP0A, OsP0B and OsP0C. All of these P0 proteins were localized both in cytoplasm and nucleus, and all interacted with OsP1. Intriguingly, the transcripts of OsP0A presented more than 90% of the total P0 transcripts. Moreover, knockout of OsP0A led to embryo lethality, while single or double knockout of OsP0B and OsP0C did not show any visible defects in rice. The genomic DNA of OsP0A could well complement the lethal phenotypes of osp0a mutant. Finally, sequence and syntenic analyses revealed that OsP0C evolved from OsP0A, and that duplication of genomic fragment harboring OsP0C further gave birth to OsP0B, and both of these duplication events might happen prior to the differentiation of indica and japonica subspecies in rice ancestor. CONCLUSION: These data suggested that OsP0A functions as the predominant P0 gene, playing an essential role in embryo development in rice. Our findings highlighted the importance of P0 genes in plant development.

The clinical utility of metagenomic next-generation sequencing for the diagnosis of central nervous system infectious diseases.

BACKGROUND: To evaluate the clinical utility of metagenomic next-generation sequencing (mNGS) for the diagnosis of central nervous system infections (CNSI). METHODS: Cerebrospinal fluid (CSF) from 54 patients who were high-level clinical suspicion of CNSI was collected and sent for mNGS and conventional tests from January 2019 to March 2022. RESULTS: Twenty out of 54 patients were diagnosed with CNSI and 34 non-CNSI. Among the 34 non-CNSI, one was false positive by mNGS. Among the 20 CNSI, 11 had presumed viral encephalitis and/or meningitis, 5 had presumed bacterial meningitis, 2 had presumed TMB, 1 had Crytococcus meningitis and 1 had neurosyphilis. The sensitivity of viral encephalitis and/or meningitis was 0.73 (8/11); 10 virus were detected; 9/10 was dsDNA; 1/10 was ssRNA. SSRN ranged from 1 to 13. The accuracy rate was 0.4, the accuracy rate was positively correlated with SSRN (r = 0.738, P = 0.015), SSRN ≥ 1, the accuracy rate was 0.4; SSRN ≥ 3, the accuracy rate was 0.66; SSRN ≥ 4, the accuracy rate was 0.75; SSRN ≥ 6, the accuracy rate was 1. The sensitivity of bacterial meningitis was 1. Seven kinds of bacteria were detected, among which 3/7 were gram positive, 3/7 were gram negative, and 1/7 was infected NTM (nontuberculous mycobacteria). The accuracy rate was 0.43 (3/7). The sensitivity of TBM was 0.66 (2/3), the accuracy rate was 1. The sensitivity of Crytococcus meningitis was 1, the accuracy rate was 0.5. PPV (positive predictive value) of mNGS was 0.94, NPV (negative predictive value) of mNGS was 0.89, specificity was 0.97 and sensitivity was 0.8. The AUG for CSF mNGS diagnosis of CNSI was 0.89 (95% CI = 0.78-0.99) Headache, meningeal irritation sign and image of meninges abnormal were correlated with the sensitivity of mNGS (r = 0.451, 0.313, 0.446; p = 0.001, 0.021, 0.001); CSF Glucose and CSF Chloride were negatively correlated with sensitivity of mNGS (r = -0.395, -0.462; p = 0.003, ＜ 0.001). CONCLUSION: mNGS is a detection means with high sensitivity, wide coverage and strong timeliness, which can help clinicians to identify the pathogen diagnosis quickly, conduct targeted anti-infection treatment early and reduce antibiotic abuse. The pathogen which causing low CSF Glucose, low CSF Chloride or meninges infections was more likely to be detected by mNGS. It may be related to growth and structural characteristics of the pathogen and blood-brain barrier damage.

A subregion-based survival prediction framework for GBM via multi-sequence MRI space optimization and clustering-based feature bundling and construction.

Aiming at accurate survival prediction of Glioblastoma (GBM) patients following radiation therapy, we developed a subregion-based survival prediction framework via a novel feature construction method on multi-sequence MRIs. The proposed method consists of two main steps: (1) a feature space optimization algorithm to determine the most appropriate matching relation derived between multi-sequence MRIs and tumor subregions, for using multimodal image data more reasonable; (2) a clustering-based feature bundling and construction algorithm to compress the high-dimensional extracted radiomic features and construct a smaller but effective set of features, for accurate prediction model construction. For each tumor subregion, a total of 680 radiomic features were extracted from one MRI sequence using Pyradiomics. Additional 71 geometric features and clinical information were collected resulting in an extreme high-dimensional feature space of 8231 to train and evaluate the survival prediction at 1 year, and the more challenging overall survival prediction. The framework was developed based on 98 GBM patients from the BraTS 2020 dataset under five-fold cross-validation, and tested on an external cohort of 19 GBM patients randomly selected from the same dataset. Finally, we identified the best matching relationship between each subregion and its corresponding MRI sequence, a subset of 235 features (out of 8231 features) were generated by the proposed feature bundling and construction framework. The subregion-based survival prediction framework achieved AUCs of 0.998 and 0.983 on the training and independent test cohort respectively for 1 year survival prediction, compared to AUCs of 0.940 and 0.923 for survival prediction using the 8231 initial extracted features for training and validation cohorts respectively. Finally, we further constructed an effective stacking structure ensemble regressor to predict the overall survival with the C-index of 0.872. The proposed subregion-based survival prediction framework allow us to better stratified patients towards personalized treatment of GBM.

Role of mechanotransduction mediated by YAP/TAZ in the treatment of neurogenic erectile dysfunction with low-intensity pulsed ultrasound.

BACKGROUND: Erectile dysfunction (ED) and weakness of the penis are processes related to hemodynamic alteration. Low-intensity pulsed ultrasound (LIPUS), as a new mechanical modality for the treatment of ED, deserves to be explored in depth for the biomechanical mechanisms it exerts. OBJECTIVE: The aim of this study was to explore the role of YAP/TAZ-mediated mechanotransduction in mechanical therapy for the treatment of neurogenic erectile dysfunction (NED). MATERIALS AND METHODS: Forty-two male SD rats (12 w old) were randomly divided into sham-operated (n = 14), bilateral cavernous nerve injury (BCNI, n = 14), and LIPUS-treated (n = 14) groups. Intracavernosal pressure/mean arterial pressure (ICP/MAP) was measured 14 and 28 days after treatment. Penile tissue specimens were collected for pathological examination, and the changes in YAP, TAZ, connective tissue growth factor (CTGF), CYR61, LATS1, and p38 mitogen-activated protein kinase expression levels were assessed by Western blot, real-time quantitative polymerase chain reaction (RT-qPCR) and immunological staining. RESULTS: Compared with BCNI, LIPUS significantly improved ICP/MAP levels and enhanced histopathological changes. The penile expression levels of YAP, TAZ, CTGF, and CYR61 were significantly downregulated in the BCNI group (p < 0.01), and LIPUS upregulated the expression levels of these proteins (p < 0.05). The expression levels of p-LATS1 and LATS1 were not significantly different among the groups (p > 0.05). Interestingly, the expression level of p-p38/p38 significantly increased in BCNI rats (p < 0.05), which was reversed by LIPUS treatment (p < 0.05). However, the p38 inhibitor SB203580 did not change the expression of YAP/TAZ in rat primary smooth muscle cells or mouse MOVAS cells (p > 0.05). DISCUSSION AND CONCLUSION: LIPUS can effectively improve penile erectile function in NED rats. The underlying mechanism may be related to the regulation of YAP/TAZ-mediated mechanotransduction. However, the upstream regulatory signal may differ from the classical Hippo pathway.

Endophthalmitis Secondary to Fish Tank Granuloma.

This case report describes an uncommon case of endophthalmitis secondary to fish tank granuloma.

Dissolved biochar fractions and solid biochar particles inhibit soil acidification induced by nitrification through different mechanisms.

Biochar can inhibit soil acidification by decreasing the H+ input from nitrification and improving soil pH buffering capacity (pHBC). However, biochar is a complex material and the roles of its different components in inhibiting soil acidification induced by nitrification remain unclear. To address this knowledge gap, dissolved biochar fractions (DBC) and solid biochar particles (SBC) were separated and mixed thoroughly with an amended Ultisol. Following a urea addition, the soils were subjected to an incubation study. The results showed that both the DBC and SBC inhibited soil acidification by nitrification. The DBC inhibited soil acidification by decreasing the H+ input from nitrification, while SBC enhanced the soil pHBC. The DBC from peanut straw biochar (PBC) and rice straw biochar (RBC) decreased the H+ release by 16 % and 18 % at the end of incubation. The decrease in H+ release was attributed to the inhibition of soil nitrification and net mineralization caused by the toxicity of the phenols in DBC to soil bacteria. The abundance of ammonia-oxidizing bacteria (AOB) and total bacteria decreased by >60 % in the treatments with DBC. The opposite effects were observed in the treatments with SBC. Soil pHBC increased by 7 % and 19 % after the application of solid RBC and PBC particles, respectively. The abundance of carboxyl on the surface of SBC was mainly responsible for the increase in soil pHBC. Generally, the mixed application of DBC and SBC was more effective at inhibiting soil acidification than their individual applications. The negative impacts of dissolved biochar components on soil microorganisms need to be closely monitored.

[Electroencephalogram Features of Anti-N-Methyl-D-Aspartate Receptor Encephalitis and Their Value for Clinical Assessment].

Objective: To analyze the electroencephalogram (EEG) features of anti-N-methyl-D-aspartate receptor encephalitis (anti-NMDARE) and to study the clinical assessment value of the degree of EEG background slowing and the presence of δ brush. Methods: We enrolled 52 patients with anti-NMDARE and collected their clinical data, including age, sex, form of disease onset, status of tumor comorbidity, auxiliary examination findings (cerebrospinal fluid [CSF] anti-methyl-D-aspartate receptor antibody titers, magnetic resonance imaging [MRI] reports, and EEG results), treatment status, and follow-up after discharge. The degree of EEG background abnormality and the presence of δ brush in the EEG of patients with different clinical features were analyzed. Results: Among the 52 patients, 7 (14%) had normal EEG, and 45 (87%), abnormal EEG, including 25 (48%) with mild abnormalities, 11 (21%) with moderate abnormalities, and 9 (17%) with severe abnormalities. δ brush was seen in 6 (12%) patients. At the time of EEG, 32 (62%) patients were in the mild condition group and 20 (38%) patients were in the severe condition group. After 1 year of follow-up, there were 45 (86%) patients in the good prognosis group and 7 (14%) patients in the poor prognosis group. The exacerbation of EEG background abnormalities and the presence of δ brush were indications for an increase in the proportion of patients who were in severe condition, who needed ICU admission, and who had poor prognosis ( P<0.01). The worse the EEG background abnormalities, the higher the proportion of CSF antibody titers>1∶10 ( P=0.035), and the higher the proportion of patients initiating second-line immunotherapy ( P=0.008). The δ brush was seen a higher proportion in patients with comorbid tumors ( P=0.012). The probability of δ brush presence was higher in the first-time diagnosis cases than that in recurrent cases ( P=0.023). Conclusions: The degree of EEG slowing and the presence of δ brush have shown consistent performance in assessing patients' condition and predicting prognosis. The slower the EEG, the more severe the disease, and the worse the prognosis. The presence of δ brush indicates severe disease and poor prognosis. EEG slowing is correlated with the immune status of patients with anti-NMDARE. The slower the EEG, the more severe the immune abnormalities. In clinical practice, patient EEG should be under dynamic monitoring in order to evaluate the effect of immunotherapy. If EEG slowing is not improved, enhanced immunotherapy should be considered as early as possible. The δ brush is seen at a higher proportion in patients with comorbid tumors. Therefore, active efforts should be made to screen for tumors when δ brush is present.

A multi-objective based radiomics feature selection method for response prediction following radiotherapy.

Objective.Radiomics contains a large amount of mineable information extracted from medical images, which has important significance in treatment response prediction for personalized treatment. Radiomics analyses generally involve high dimensions and redundant features, feature selection is essential for construction of prediction models.Approach.We proposed a novel multi-objective based radiomics feature selection method (MRMOPSO), where the number of features, sensitivity, and specificity are jointly considered as optimization objectives in feature selection. The MRMOPSO innovated in the following three aspects: (1) Fisher score to initialize the population to speed up the convergence; (2) Min-redundancy particle generation operations to reduce the redundancy between radiomics features, a truncation strategy was introduced to further reduce the number of features effectively; (3) Particle selection operations guided by elitism strategies to improve local search ability of the algorithm. We evaluated the effectiveness of the MRMOPSO by using a multi-institution oropharyngeal cancer dataset from The Cancer Imaging Archive. 357 patients were used for model training and cross validation, an additional 64 patients were used for evaluation.Main results.The area under the curve (AUC) of our method achieved AUCs of 0.82 and 0.84 for cross validation and independent dataset, respectively. Compared with classical feature selection methods, the AUC of MRMOPSO is significantly higher than the Lasso (AUC = 0.74,p-value = 0.02), minimal-redundancy-maximal-relevance criterion (mRMR) (AUC = 0.73,p-value = 0.05), F-score (AUC = 0.48,p-value < 0.01), and mutual information (AUC = 0.69,p-value < 0.01) methods. Compared to single-objective methods, the AUC of MRMOPSO is 12% higher than those of the genetic algorithm (GA) (AUC = 0.68,p-value = 0.02) and particle swarm optimization algorithm (AUC = 0.72,p-value = 0.05) methods. Compared to other multi-objective feature selection methods, the AUC of MRMOPSO is 14% higher than those of multiple objective particle swarm optimization (MOPSO) (AUC = 0.68,p-value = 0.02) and nondominated sorting genetic algorithm II (NSGA2) (AUC = 0.70,p-value = 0.03).Significance.We proposed a multi-objective based radiomics feature selection method. Compared to conventional feature reduction algorithms, the proposed algorithm effectively reduced feature dimension, and achieved superior performance, with improved sensitivity and specificity, for response prediction in radiotherapy.

A survival prediction model via interpretable machine learning for patients with oropharyngeal cancer following radiotherapy.

PURPOSE: To explore interpretable machine learning (ML) methods, with the hope of adding more prognosis value, for predicting survival for patients with Oropharyngeal-Cancer (OPC). METHODS: A cohort of 427 OPC patients (Training 341, Test 86) from TCIA database was analyzed. Radiomic features of gross-tumor-volume (GTV) extracted from planning CT using Pyradiomics, and HPV p16 status, etc. patient characteristics were considered as potential predictors. A multi-level dimension reduction algorithm consisting of Least-Absolute-Selection-Operator (Lasso) and Sequential-Floating-Backward-Selection (SFBS) was proposed to effectively remove redundant/irrelevant features. The interpretable model was constructed by quantifying the contribution of each feature to the Extreme-Gradient-Boosting (XGBoost) decision by Shapley-Additive-exPlanations (SHAP) algorithm. RESULTS: The Lasso-SFBS algorithm proposed in this study finally selected 14 features, and our prediction model achieved an area-under-ROC-curve (AUC) of 0.85 on the test dataset based on this feature set. The ranking of the contribution values calculated by SHAP shows that the top predictors that were most correlated with survival were ECOG performance status, wavelet-LLH_firstorder_Mean, chemotherapy, wavelet-LHL_glcm_InverseVariance, tumor size. Those patients who had chemotherapy, with positive HPV p16 status, and lower ECOG performance status, tended to have higher SHAP scores and longer survival; who had an older age at diagnosis, heavy drinking and smoking pack year history, tended to lower SHAP scores and shorter survival. CONCLUSION: We demonstrated predictive values of combined patient characteristics and imaging features for the overall survival of OPC patients. The multi-level dimension reduction algorithm can reliably identify the most plausible predictors that are mostly associated with overall survival. The interpretable patient-specific survival prediction model, capturing correlations of each predictor and clinical outcome, was developed to facilitate clinical decision-making for personalized treatment.

Temporal-based Swin Transformer network for workflow recognition of surgical video.

PURPOSE: Surgical workflow recognition has emerged as an important part of computer-assisted intervention systems for the modern operating room, which also is a very challenging problem. Although the CNN-based approach achieves excellent performance, it does not learn global and long-range semantic information interactions well due to the inductive bias inherent in convolution. METHODS: In this paper, we propose a temporal-based Swin Transformer network (TSTNet) for the surgical video workflow recognition task. TSTNet contains two main parts: the Swin Transformer and the LSTM. The Swin Transformer incorporates the attention mechanism to encode remote dependencies and learn highly expressive representations. The LSTM is capable of learning long-range dependencies and is used to extract temporal information. The TSTNet organically combines the two components to extract spatiotemporal features that contain more contextual information. In particular, based on a full understanding of the natural features of the surgical video, we propose a priori revision algorithm (PRA) using a priori information about the sequence of the surgical phase. This strategy optimizes the output of TSTNet and further improves the recognition performance. RESULTS: We conduct extensive experiments using the Cholec80 dataset to validate the effectiveness of the TSTNet-PRA method. Our method achieves excellent performance on the Cholec80 dataset, which accuracy is up to 92.8% and greatly exceeds the state-of-the-art methods. CONCLUSION: By modelling remote temporal information and multi-scale visual information, we propose the TSTNet-PRA method. It was evaluated on a large public dataset, showing a high recognition capability superior to other spatiotemporal networks.

The Indicative Value of Serum Tumor Markers for Metastasis and Stage of Non-Small Cell Lung Cancer.

Objective: This study aimed to explore the roles of serum tumor markers for metastasis and stage of non-small cell lung cancer (NSCLC). Methods: This study recruited 3272 NSCLC patients admitted to the Tianjin Union Medical Center and the Tianjin Medical University Cancer Institute and Hospital. The predictive abilities of some serum tumor markers (carcinoembryonic antigen (CEA), squamous cell carcinoma antigen (SCC-Ag), cytokeratin-19 fragment (CYFRA 21-1), neuron-specific enolase (NSE), pro-gastrin-releasing peptide (ProGRP), total prostate-specific antigen (TPSA) and carbohydrate antigen 199 (CA199)) for NSCLC metastasis (intrapulmonary, lymphatic and distant metastasis) and clinical stage were analyzed. Results: Tumor markers exhibited different numerical and proportional distributions in NSCLC patients. Elevated CEA, CYFRA 21-1 and CA199 levels were indicative of tumor metastasis and stage. Increased CEA and CA199 provided an accurate prediction of intrapulmonary and distant metastasis with the area under the receiver operator characteristic curve (AUC) of 0.69 both (p < 0.001); Increased CEA, CYFRA 21-1 and CA199 provided an accurate prediction of lymphatic metastasis with the AUC of 0.62 (p < 0.001). Conclusion: Combined detection of serum tumor markers can indicate tumor metastasis and stage in NSCLC patients.

Effect of theaflavin-3,3'-digallate on leptin-deficient induced nonalcoholic fatty liver disease might be related to lipid metabolism regulated by the Fads1/PPARδ/Fabp4 axis and gut microbiota.

Nonalcoholic fatty liver disease (NAFLD), one of the risk factors for hepatitis, cirrhosis, and even hepatic carcinoma, has been a global public health problem. The polyphenol compound theaflavin-3,3'-digallate (TF3), mainly extracted from black tea, has been reported to produce an effect on hypoglycemic and antilipid deposition in vitro. In our study, we further investigated the function and novel mechanisms of TF3 in protecting NAFLD in vivo. By using leptin-deficient obese (ob/ob) mice with NAFLD symptoms, TF3 treatment prevented body weight and waistline gain, reduced lipid accumulation, and alleviated liver function injury, as well as decreased serum lipid levels and TG levels in livers in ob/ob mice, observing no side effects. Furthermore, the transcriptome sequencing of liver tissue showed that TF3 treatment corrected the expression profiles of livers in ob/ob mice compared with that of the model group. It is interesting to note that TF3 might regulate lipid metabolism via the Fads1/PPARδ/Fabp4 axis. In addition, 16S rRNA sequencing demonstrated that TF3 increased the abundance of Prevotellaceae_UCG-001, norank_f_Ruminococcaceae, and GCA-900066575 and significantly decreased that of Parvibacter. Taken together, the effect of TF3 on NAFLD might be related to lipid metabolism regulated by the Fads1/PPARδ/Fabp4 axis and gut microbiota. TF3 might be a promising candidate for NAFLD therapy.