Neural network combining with clinical ultrasonography: A new approach for classification of salivary gland tumors.

OBJECTIVE: Little information is available about deep learning methods used in ultrasound images of salivary gland tumors. We aimed to compare the accuracy of the ultrasound-trained model to computed tomography or magnetic resonance imaging trained model. MATERIALS AND METHODS: Six hundred and thirty-eight patients were included in this retrospective study. There were 558 benign and 80 malignant salivary gland tumors. A total of 500 images (250 benign and 250 malignant) were acquired in the training and validation set, then 62 images (31 benign and 31 malignant) in the test set. Both machine learning and deep learning were used in our model. RESULTS: The test accuracy, sensitivity, and specificity of our final model were 93.5%, 100%, and 87%, respectively. There were no over fitting in our model as the validation accuracy was similar with the test accuracy. CONCLUSIONS: The sensitivity and specificity were comparable with current MRI and CT images using artificial intelligence.

[Prezygotic reproductive isolation of two sympatric species of Ligularia weeds in eastern Qinghai-Tibet Plateau, China]. / 青藏高原东缘同域分布的2种橐吾属杂草的合子前生殖隔离.

Reproductive isolation, the key process to prevent interspecific hybridization and keep the completeness and independence of species, is crucial to the formation and maintenance of biodiversity. The forming steps, methods and intensities of reproductive isolation between different species are not completely the same. Literatures on reproductive isolation between species provide valuable evidence for speciation and its maintenance. Flowering phenology, flowering-visiting insects, and pollen-stigma compatibility were observed for Ligularia virgaurea and L. sagitta, two species of weeds sympatrically distributed in eastern Qinghai-Tibet Plateau. The characteristics of reproductive isolation mechanism of both species and its role in reproductive isolation were also studied. The results showed that the flowering period of L. virgaurea was 20 d earlier than that of L. sagitta. Although the full-blooming period separated, there was a roughly 10 d overlap between the two species. Meanwhile, the pollens and stigmas of the two species were both viability in the overlapped 10 d. L. virgaurea and L. sagitta shared the same types of pollinating insects, which was a generalized pollination type. Besides, the flower-visiting behavior towards the two species from the pollinators was similar, along with the interleaved access between the two species. There was no complete time isolation and no complete pollinator isolation between the two species, but the stigma had poor compatibility towards heterogenic pollen. The germination of pollen on stigma and growth of the pollen tube was hampered. Furthermore, the rejection of pollen-stigma was likely to be an important prezygotic reproductive isolation between L. virgaurea and L. sagitta, thus avoiding the natural hybridization and maintaining the diversity and genetic stability of the two species.