Classification of field wheat varieties based on a lightweight G-PPW-VGG11 model.

Introduction: In agriculture, especially wheat cultivation, farmers often use multi-variety planting strategies to reduce monoculture-related harvest risks. However, the subtle morphological differences among wheat varieties make accurate discrimination technically challenging. Traditional variety classification methods, reliant on expert knowledge, are inefficient for modern intelligent agricultural management. Numerous existing classification models are computationally complex, memory-intensive, and difficult to deploy on mobile devices effectively. This study introduces G-PPW-VGG11, an innovative lightweight convolutional neural network model, to address these issues. Methods: G-PPW-VGG11 ingeniously combines partial convolution (PConv) and partially mixed depthwise separable convolution (PMConv), reducing computational complexity and feature redundancy. Simultaneously, incorporating ECANet, an efficient channel attention mechanism, enables precise leaf information capture and effective background noise suppression. Additionally, G-PPW-VGG11 replaces traditional VGG11's fully connected layers with two pointwise convolutional layers and a global average pooling layer, significantly reducing memory footprint and enhancing nonlinear expressiveness and training efficiency. Results: Rigorous testing showed G-PPW-VGG11's superior performance, with an impressive 93.52% classification accuracy and only 1.79MB memory usage. Compared to VGG11, G-PPW-VGG11 showed a 5.89% increase in accuracy, 35.44% faster inference, and a 99.64% reduction in memory usage. G-PPW-VGG11 also surpasses traditional lightweight networks in classification accuracy and inference speed. Notably, G-PPW-VGG11 was successfully deployed on Android and its performance evaluated in real-world settings. The results showed an 84.67% classification accuracy with an average time of 291.04ms per image. Discussion: This validates the model's feasibility for practical agricultural wheat variety classification, establishing a foundation for intelligent management. For future research, the trained model and complete dataset are made publicly available.

[Predictive value of placenta-derived RASSF1A sequence expression in maternal plasma for pre-eclampsia].

OBJECTIVE: To investigate the expression of placenta-derived RASSF1A gene in maternal plasma during first and second trimesters, and to explore its value for the prediction of pre-eclampsia. METHODS: For 325 pregnant women of the first trimester, free DNA of plasma samples was extracted at 7-12, 13-18, and 19-24 gestational weeks, respectively. Methylation-sensitive restriction enzyme digestion followed by fluorescence quantitative PCR (MSRE+ PCR) was employed for analyzing the concentrations of hypermethylated RASSF1A gene. Blood pressure, proteinuria and clinical feature were monitored at the same time. Those who had subsequently developed pre-eclampsia were selected as the pre-eclamptic group, 30 normal pregnant women were selected as the control group. Hypermethylated RASSF1A gene in maternal plasma was retrospectively analyzed. The relationship between clinical classification, type of pre-eclampsia and concentrations of the gene were further analyzed. RESULTS: Twenty-six out of the 325 pregnant women developed pre-eclampsia as their only complication. At 13-18 gestational weeks, the mean concentrations of fetus-specific RASSF1A sequences were 141.62 copies/mL in maternal plasma of pre-eclamptic pregnancies, which was significantly greater than that of the controls (98.90 copies/mL). Fetus-derived RASSF1A levels were 2.03 fold higher in pre-eclamptic subjects than controls at 19-24 gestational weeks. There was a significant difference in the level of hypermethylated RASSF1A gene between the mild and severe pre-clamptic subjects at 13-24 gestational weeks (P< 0.05). The concentrations of the sequences were significantly higher in early-onset severe pre-eclampsia than late-onset severe pre-eclampsia at 19-24 gestational weeks (P< 0.05). CONCLUSION: Altered expression of hypermethylated RASSF1A gene may be detected in maternal plasma during second trimester, which has important significance for early prediction of pre-eclampsia.

Effect of blockage of costimulatory signal on murine abortion-prone model.

BACKGROUND: Inhibition of the key costimulatory signals results in T cell anergy, indicating the alloantigen-specific immunologic unresponsiveness. In this study, the effect of blockage of costimulatory signal CD(86) on murine abortion-prone model was studied. METHODS: Thirty CBA/J female mice cohabitated with DBA/2 male or BALB/c male mice were investigated. CBA/J x DBA/2 matings were used as the abortion-prone model, and CBA/J x BALB/c matings were used as the normal pregnant model. The abortion-prone models were divided into experimental and control groups, and the normal pregnant models were set as a normal group (10 mice in each group). The mice in the experimental group were treated with anti-mouse CD(86) monoclonal antibody (mAb) (100 microg) on day 4.5 of gestation, while the controls received irrelevant-isotype matched rat IgG(2b). As for the normal group, nothing was given to the mice. The mice were killed on day 13.5 of gestation, embryo resorption rate and the expression of transforming growth factor beta(1) (TGF-beta(1)), plasminogen activator inhibitor 1 (PAI-1), and matrix metalloproteinase 9 (MMP-9) were detected. Then the data were analyzed by Chi-square test and Fisher's exact test. RESULTS: The embryo resorption rate in the experimental (8.2%) and normal groups (7.7%) was significantly lower than that of the control (23.5%, P < 0.05). No significant difference was detected between the experimental and normal groups (P > 0.05). The positive expression rates of TGF-beta(1) and PAI-1 proteins in the experimental and normal groups were significantly higher than those in the control group (P < 0.05). The positive expression rate of MMP-9 protein in the experimental and normal groups was significantly lower than that in the control group (P < 0.05). No significant difference in the positive expression rates of the three proteins was detected between the experimental and normal groups (P > 0.05). CONCLUSIONS: Blockage of costimulatory signal CD(86) at early pregnancy can treat uncertain recurrent spontaneous abortion by stimulating the expression of TGF-beta(1), MMP-9 and PAI-1 and reducing the embryo resorption rate.