Search

Due to its decade‐long progression, colorectal cancer (CRC) is most suitable for population screening to achieve a significant reduction in its incidence and mortality. DNA methylation has emerged as a potential marker for the early detection of CRC. However, the current mainstream methylation detection method represented by bisulfite conversion has issues such as tedious operation, DNA damage, and unsatisfactory sensitivity. Herein, a new high‐performance CRC screening tool based on the promising specific terminal‐mediated polymerase chain reaction (STEM‐PCR) strategy is developed. CRC‐related methylation‐specific candidate CpG sites are first prescreened through The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases using self‐developed bioinformatics. Next, 9 homebrew colorectal cancer DNA methylated STEM‒PCR assays (ColoC‐mSTEM) with high sensitivity (0.1%) and high specificity are established to identify candidate sites. The clinical diagnostic performance of these selected methylation sites is confirmed and validated by a case‐control study. The optimized diagnostic model has an overall sensitivity of 94.8% and a specificity of 95.0% for detecting early‐stage CRC. Taken together, ColoC‐mSTEM, based on a single methylation‐specific site, is a promising diagnostic approach for the early detection of CRC which is perfectly suitable for the screening needs of CRC in primary healthcare institutions. [ABSTRACT FROM AUTHOR]

Intelligent rice disease recognition methods based on deep neural networks can predict the degree of disease on the basis of, for example, the number of disease spots on an image, so that preventive measures can be taken. Currently, intelligent recognition methods for rice diseases suffer from the disadvantages of poor versatility and low accuracy. This paper uses eight common image classification networks to classify and identify four rice diseases. ResNet50 was selected as the feature extraction network and an enhanced feature fusion and target adaptive network (EFFTAN), referred to as EFFTAN, is proposed. The EFFTAN was used to detect four rice spot diseases in the rice leaf disease image samples dataset; the mean average precision of the final detection was 95.3%, and effective detection was also achieved for the dense spot features. [ABSTRACT FROM AUTHOR]

Wheat rust is one of the important factors leading to wheat yield decline. The traditional method of artificial identification of wheat rust remains inefficient. With the development of unmanned technology, unmanned aerial vehicles (UAVs) with advanced deep vision models can be used to monitor wheat growth, hence enabling timely disease detection and deployment of corresponding treatment measures. However, due to the limitation of embedded system hardware, it is a challenge to deploy a high‐accuracy and lightweight wheat rust detection model in an embedded system. In this paper, a training method based on transfer learning and sharpness‐aware minimization (SAM) is proposed to improve the accuracy of lightweight models. Specifically, the initial model is pretrained on an ImageNet dataset, and then the classifier of the model is fine‐tuned on the wheat rust training set; to prevent the risk of overfitting, the SAM method is applied to adjust the global parameters of the model. The experimental results on the Yellow‐Rust‐19 dataset show that the training method can effectively improve the accuracy of the wheat rust detection model, which is 3.56% higher than the existing methods. In addition, the parameter scale and computing resource requirements of four lightweight models are compared. The results indicate that MobileNetV3‐Small can achieve satisfactory accuracy with low requirements for storage and computing resource, and a detection frame rate of 101.36 frames per second in the Raspberry Pi, which is suitable for the unmanned detection of wheat rust. [ABSTRACT FROM AUTHOR]