Search

Colonoscopy is one of the main methods to detect colon polyps, and its detection is widely used to prevent and diagnose colon cancer. With the rapid development of computer vision, deep learning-based semantic segmentation methods for colon polyps have been widely researched. However, the accuracy and stability of some methods in colon polyp segmentation tasks show potential for further improvement. In addition, the issue of selecting appropriate sub-models in ensemble learning for the colon polyp segmentation task still needs to be explored. In order to solve the above problems, we first implement the utilization of multi-complementary high-level semantic features through the Multi-Head Control Ensemble. Then, to solve the sub-model selection problem in training, we propose SDBH-PSO Ensemble for sub-model selection and optimization of ensemble weights for different datasets. The experiments were conducted on the public datasets CVC-ClinicDB, Kvasir, CVC-ColonDB, ETIS-LaribPolypDB and PolypGen. The results show that the DET-Former, constructed based on the Multi-Head Control Ensemble and the SDBH-PSO Ensemble, consistently provides improved accuracy across different datasets. Among them, the Multi-Head Control Ensemble demonstrated superior feature fusion capability in the experiments, and the SDBH-PSO Ensemble demonstrated excellent sub-model selection capability. The sub-model selection capabilities of the SDBH-PSO Ensemble will continue to have significant reference value and practical utility as deep learning networks evolve. [ABSTRACT FROM AUTHOR]

The biological mechanisms triggered by low-dose exposure still need to be explored in depth. In this study, the potential mechanisms of low-dose radiation when irradiating the BEAS-2B cell lines with a Cs-137 gamma-ray source were investigated through simulations and experiments. Monolayer cell population models were constructed for simulating and analyzing distributions of nucleus-specific energy within cell populations combined with the Monte Carlo method and microdosimetric analysis. Furthermore, the 10 × Genomics single-cell sequencing technology was employed to capture the heterogeneity of individual cell responses to low-dose radiation in the same irradiated sample. The numerical uncertainties can be found both in the specific energy distribution in microdosimetry and in differential gene expressions in radiation cytogenetics. Subsequently, the distribution of nucleus-specific energy was compared with the distribution of differential gene expressions to guide the selection of differential genes bioinformatics analysis. Dose inhomogeneity is pronounced at low doses, where an increase in dose corresponds to a decrease in the dispersion of cellular-specific energy distribution. Multiple screening of differential genes by microdosimetric features and statistical analysis indicate a number of potential pathways induced by low-dose exposure. It also provides a novel perspective on the selection of sensitive biomarkers that respond to low-dose radiation. [ABSTRACT FROM AUTHOR]