Nailfold capillaroscopy is a reliable way to detect and analyze microvascular abnormalities. It is safe, simple, noninvasive, and inexpensive. Among all the capillaroscopic abnormalities, nailfold microhemorrhages are closely associated with early vascular damages and might be present in numerous diseases such as glaucoma, diabetes mellitus, and systemic sclerosis. Segmentation of nailfold microhemorrhages provides valuable pathological information that may lead to further investigations. A novel deep learning architecture named DAFM-Net is proposed for the accurate segmentation in this study. The network mainly consists of U-shape backbone, dual attention fusion module, and group normalization layer. The U-shape backbone generates rich hierarchical representations while the dual attention fusion module utilizes the captured features for fine adjustment. Group normalization is introduced as an effective normalization method to effectively improve the convergence ability of our deep neural network. The effectiveness of the proposed model is validated through ablation studies and segmentation experiments; the proposed method DAFM-Net achieves competitive performance for nailfold microhemorrhage segmentation with an IOU score of 78.03% and Dice score of 87.34% compared to the ground truth.

Surface-enhanced Raman spectroscopy was employed to measure lettuce seeds at five different germination stages. The experimental results show that 85% of the spectra of normally germinating seeds exhibited consistency in both peak positions and quantities at the same germination stage, while spectra from seeds that failed to germinate normally demonstrated significant differences compared to the normal ones. These data indicate that the surface-enhanced Raman spectrum of seeds could serve as an effective method for detecting seed germination rates.

In the originally published version of this article