Wheat Seed Detection and Counting Method Based on Improved YOLOv8 Model.

Wheat seed detection has important applications in calculating thousand-grain weight and crop breeding. In order to solve the problems of seed accumulation, adhesion, and occlusion that can lead to low counting accuracy, while ensuring fast detection speed with high accuracy, a wheat seed counting method is proposed to provide technical support for the development of the embedded platform of the seed counter. This study proposes a lightweight real-time wheat seed detection model, YOLOv8-HD, based on YOLOv8. Firstly, we introduce the concept of shared convolutional layers to improve the YOLOv8 detection head, reducing the number of parameters and achieving a lightweight design to improve runtime speed. Secondly, we incorporate the Vision Transformer with a Deformable Attention mechanism into the C2f module of the backbone network to enhance the network's feature extraction capability and improve detection accuracy. The results show that in the stacked scenes with impurities (severe seed adhesion), the YOLOv8-HD model achieves an average detection accuracy (mAP) of 77.6%, which is 9.1% higher than YOLOv8. In all scenes, the YOLOv8-HD model achieves an average detection accuracy (mAP) of 99.3%, which is 16.8% higher than YOLOv8. The memory size of the YOLOv8-HD model is 6.35 MB, approximately 4/5 of YOLOv8. The GFLOPs of YOLOv8-HD decrease by 16%. The inference time of YOLOv8-HD is 2.86 ms (on GPU), which is lower than YOLOv8. Finally, we conducted numerous experiments and the results showed that YOLOv8-HD outperforms other mainstream networks in terms of mAP, speed, and model size. Therefore, our YOLOv8-HD can efficiently detect wheat seeds in various scenarios, providing technical support for the development of seed counting instruments.

Machine learning-based models for the prediction of breast cancer recurrence risk.

Breast cancer is the most common malignancy diagnosed in women worldwide. The prevalence and incidence of breast cancer is increasing every year; therefore, early diagnosis along with suitable relapse detection is an important strategy for prognosis improvement. This study aimed to compare different machine algorithms to select the best model for predicting breast cancer recurrence. The prediction model was developed by using eleven different machine learning (ML) algorithms, including logistic regression (LR), random forest (RF), support vector classification (SVC), extreme gradient boosting (XGBoost), gradient boosting decision tree (GBDT), decision tree, multilayer perceptron (MLP), linear discriminant analysis (LDA), adaptive boosting (AdaBoost), Gaussian naive Bayes (GaussianNB), and light gradient boosting machine (LightGBM), to predict breast cancer recurrence. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and F1 score were used to evaluate the performance of the prognostic model. Based on performance, the optimal ML was selected, and feature importance was ranked by Shapley Additive Explanation (SHAP) values. Compared to the other 10 algorithms, the results showed that the AdaBoost algorithm had the best prediction performance for successfully predicting breast cancer recurrence and was adopted in the establishment of the prediction model. Moreover, CA125, CEA, Fbg, and tumor diameter were found to be the most important features in our dataset to predict breast cancer recurrence. More importantly, our study is the first to use the SHAP method to improve the interpretability of clinicians to predict the recurrence model of breast cancer based on the AdaBoost algorithm. The AdaBoost algorithm offers a clinical decision support model and successfully identifies the recurrence of breast cancer.

SYVN1-mediated ubiquitylation directs localization of MCT4 in the plasma membrane to promote the progression of lung adenocarcinoma.

Tumour cells mainly generate energy from glycolysis, which is commonly coupled with lactate production even under normoxic conditions. As a critical lactate transporter, monocarboxylate transporter 4 (MCT4) is highly expressed in glycolytic tissues, such as muscles and tumours. Overexpression of MCT4 is associated with poor prognosis for patients with various tumours. However, how MCT4 function is post-translationally regulated remains largely unknown. Taking advantage of human lung adenocarcinoma (LUAD) cells, this study revealed that MCT4 can be polyubiquitylated in a nonproteolytic manner by SYVN1 E3 ubiquitin ligase. The polyubiquitylation facilitates the localization of MCT4 into the plasma membrane, which improves lactate export by MCT4; in accordance, metabolism characterized by reduced glycolysis and lactate production is effectively reprogrammed by SYVN1 knockdown, which can be reversed by MCT4 overexpression. Biologically, SYVN1 knockdown successfully compromises cell proliferation and tumour xenograft growth in mouse models that can be partially rescued by overexpression of MCT4. Clinicopathologically, overexpression of SYVN1 is associated with poor prognosis in patients with LUAD, highlighting the importance of the SYVN1-MCT4 axis, which performs metabolic reprogramming during the progression of LUAD.

Two effective models based on comprehensive lipidomics and metabolomics can distinguish BC versus HCs, and TNBC versus non-TNBC.

BACKGROUND: Lipidomics and metabolomics are closely related to tumor phenotypes, and serum lipoprotein subclasses and small-molecule metabolites are considered as promising biomarkers for breast cancer (BC) diagnosis. This study aimed to explore potential biomarker models based on lipidomic and metabolomic analysis that could distinguish BC from healthy controls (HCs) and triple-negative BC (TNBC) from non-TNBC. METHODS: Blood samples were collected from 114 patients with BC and 75 HCs. A total of 112 types of lipoprotein subclasses and 30 types of small-molecule metabolites in the serum were detected by 1 H-NMR. All lipoprotein subclasses and small-molecule metabolites were subjected to a three-step screening process in the order of significance (p < 0.05), univariate regression (p < 0.1), and lasso regression (nonzero coefficient). Discriminant models of BC versus HCs and TNBC versus non-TNBC were established using binary logistic regression. RESULTS: We developed a valid discriminant model based on three-biomarker panel (formic acid, TPA2, and L6TG) that could distinguish patients with BC from HCs. The area under the receiver operating characteristic curve (AUC) was 0.999 (95% confidence interval [CI]: 0.995-1.000) and 0.990 (95% CI: 0.959-1.000) in the training and validation sets, respectively. Based on the panel (D-dimer, CA15-3, CEA, L5CH, glutamine, and ornithine), a discriminant model was established to differentiate between TNBC and non-TNBC, with AUC of 0.892 (95% CI: 0.778-0.967) and 0.905 (95% CI: 0.754-0.987) in the training and validation sets, respectively. CONCLUSION: This study revealed lipidomic and metabolomic differences between BC versus HCs and TNBC versus non-TNBC. Two validated discriminatory models established against lipidomic and metabolomic differences can accurately distinguish BC from HCs and TNBC from non-TNBC. IMPACT: Two validated discriminatory models can be used for early BC screening and help BC patients avoid time-consuming, expensive, and dangerous BC screening.

BCKDK alters the metabolism of non-small cell lung cancer.

BACKGROUND: Metabolic reprogramming is a major feature of many tumors including non-small cell lung cancer (NSCLC). Branched-chain α-keto acid dehydrogenase kinase (BCKDK) plays an important role in diabetes, obesity, and other diseases. However, the function of BCKDK in NSCLC is unclear. This study aimed to explore the function of BCKDK in NSCLC. METHODS: Metabolites in the serum of patients with NSCLC and the supernatant of NSCLC cell cultures were detected using nuclear magnetic resonance (NMR) spectroscopy. Colony formation, cell proliferation, and cell apoptosis were assessed to investigate the function of BCKDK in the progression of NSCLC. Glucose uptake, lactate production, cellular oxygen consumption rate, extracellular acidification rate, and reactive oxygen species (ROS) were measured to examine the function of BCKDK in glucose metabolism. The expression of BCKDK was measured using reverse transcriptase-polymerase chain reaction, western blot, and immunohistochemical assay. RESULTS: Compared with healthy controls and postoperative NSCLC patients, increased branched-chain amino acid (BCAA) and decreased citrate were identified in the serum of preoperative NSCLC patients. Upregulation of BCKDK affected the metabolism of BCAAs and citrate in NSCLC cells. Knockout of BCKDK decreased the proliferation and exacerbated apoptosis of NSCLC cells ex vivo, while increased oxidative phosphorylation and, ROS levels, and inhibited glycolysis. CONCLUSIONS: BCKDK may influence glycolysis and oxidative phosphorylation by regulating the degradation of BCAA and citrate, thereby affecting the progression of NSCLC.

Surgical treatment for primary angle closure-glaucoma: a Meta analysis.

AIM: To evaluate the efficacy and safety of trabeculectomy, phacotrabeculectomy plus intraocular lens implantation(phacotrab+IOL group) and phacoemulsification with IOL(phaco+IOL) in primary angle-closure glaucoma(PACG). METHODS: It was a systematic review and meta-analysis, randomized controlled trials(RCT) and clinical controlled trials(CCT) were collected through electronic searches of the Cochrane Library, PubMed, EMbase, Wanfang Database online, Chinese journal Full-text Database, Chinese Scientific Journals Full-text Database (from the date of building the database to October 2010) We also checked the bibliographies of retrieved articles. All the related data that matched our standards were abstracted. The quality of included trials was evaluated according to the Dutch Cochrane Centre. RevMan 5.0 software was used for Meta-analysis. RESULTS: A total of 5 RCT and 11 CCT involving 1495 eyes were included. The results of meta-analysis showed that phacotrab+IOL group was superior than trabeculectomy(trab group) (MD -3.93,95%CI [-7.31, -0.54]) which was also superior than phaco+IOL group(MD 0.52,95%CI [0.10, 0.95]) in decreasing Intraocular Pressure(IOP). Phacotrab group(MD -1.45,95%CI [-1.68, -1.22])and phaco group (MD-1.12,95%CI [-1.87, -0.37])are both deeper than trab group in the anterior chamber depth. In increasing the coefficient of outflow facility of aqueous humor(C values) there was no statistical difference in the three groups. And there was no statistical difference between phacotrab groups and phaco groups in visual acuity but phacotrab group was superior than phaco group (MD 1.07, 95%CI [0.73, 1.40])in the use of IOP-lowering drugs. There was no statistical difference among three groups. CONCLUSION: Current evidence suggests that phacotrab+ IOL group was superior than trab group which was also superior than phaco+IOL group in decreasing IOP. Phacotrab group and phaco group are both deeper than trab group in the anterior chamber depth. Phacotrab group was superior than phaco group in the use of IOP-lowering drugs.