A deep image classification model based on prior feature knowledge embedding and application in medical diagnosis.

Aiming at the problem of image classification with insignificant morphological structural features, strong target correlation, and low signal-to-noise ratio, combined with prior feature knowledge embedding, a deep learning method based on ResNet and Radial Basis Probabilistic Neural Network (RBPNN) is proposed model. Taking ResNet50 as a visual modeling network, it uses feature pyramid and self-attention mechanism to extract appearance and semantic features of images at multiple scales, and associate and enhance local and global features. Taking into account the diversity of category features, channel cosine similarity attention and dynamic C-means clustering algorithms are used to select representative sample features in different category of sample subsets to implicitly express prior category feature knowledge, and use them as the kernel centers of radial basis probability neurons (RBPN) to realize the embedding of diverse prior feature knowledge. In the RBPNN pattern aggregation layer, the outputs of RBPN are selectively summed according to the category of the kernel center, that is, the subcategory features are combined into category features, and finally the image classification is implemented based on Softmax. The functional module of the proposed method is designed specifically for image characteristics, which can highlight the significance of local and structural features of the image, form a non-convex decision-making area, and reduce the requirements for the completeness of the sample set. Applying the proposed method to medical image classification, experiments were conducted based on the brain tumor MRI image classification public dataset and the actual cardiac ultrasound image dataset, and the accuracy rate reached 85.82% and 83.92% respectively. Compared with the three mainstream image classification models, the performance indicators of this method have been significantly improved.

Selected Phytoestrogens Distinguish Roles of ERα Transactivation and Ligand Binding for Anti-Inflammatory Activity.

Estrogen receptor α (ERα) is a ligand-activated transcriptional activator that is also involved vascular inflammation and atherosclerosis. Whether different ligands may affect this activity has not been explored. We screened a panel of phytoestrogens for their role in ERα binding and transcriptional transcription, and correlated the findings to anti-inflammatory activities in vascular endothelial cells stably expressing either a wild-type or mutant form of ERα deficient in its membrane association. Taxifolin and silymarin were "high binders" for ERα ligand binding; quercetin and curcumin were "high activators" for ERα transactivation. Using these phytoestrogens as functional probes, we found, in endothelial cells expressing wild-type ERα, the ERα high activator, but not the ERα high binder, promoted ERα nuclear translocation, estrogen response element (ERE) reporter activity, and the downstream gene expression. In endothelial cells expressing membrane association-deficient mutant ERα, the ERα nuclear translocation was significantly enhanced by taxifolin and silymarin, which still failed to activate ERα. Inflammation response was examined using the systemic or vascular inflammation inducers lipopolysaccharide or oxidized low-density lipoprotein. In both cases, only the ERα high activator inhibited nuclear translocation of nuclear factor κB, JNK, and p38, and the production of inflammatory cytokines IL-1ß and TNFα. We confirm a threshold nuclear accumulation of ERα is necessary for its transactivation. The anti-inflammatory activity of phytoestrogens is highly dependent on ERα transactivation, less so on the ligand binding, and independent of its membrane association. A pre-examination of phytoestrogens for their mode of ERα interaction could facilitate their development as better targeted receptor modifiers.

Phytochemical and Pharmacological Studies on the Genus Psoralea: A Mini Review.

The genus Psoralea, which belongs to the family Fabaceae, comprises ca. 130 species distributed all over the world, and some of the plants are used as folk medicine to treat various diseases. Psoralea corylifolia is a typical example, whose seeds have been widely used in many traditional Chinese medicine formulas for the treatment of various diseases such as leucoderma and other skin diseases, cardiovascular diseases, nephritis, osteoporosis, and cancer. So, the chemical and pharmacological studies on this genus were performed in the past decades. Here, we give a mini review on this genus about its phytochemical and pharmacological studies from 1910 to 2015.