No abstract

Elastography ultrasound (EUS) imaging is a vital ultrasound imaging modality. The current use of EUS faces many challenges, such as vulnerability to subjective manipulation, echo signal attenuation, and unknown risks of elastic pressure in certain delicate tissues. The hardware requirement of EUS also hinders the trend of miniaturization of ultrasound equipment. Here we show a cost-efficient solution by designing a deep neural network to synthesize virtual EUS (V-EUS) from conventional B-mode images. A total of 4580 breast tumor cases were collected from 15 medical centers, including a main cohort with 2501 cases for model establishment, an external dataset with 1730 cases and a portable dataset with 349 cases for testing. In the task of differentiating benign and malignant breast tumors, there is no significant difference between V-EUS and real EUS on high-end ultrasound, while the diagnostic performance of pocket-sized ultrasound can be improved by about 5% after V-EUS is equipped.

A changing climate has been posing significant impacts on vegetation growth, especially in the Yellow River Basin (YRB) where agriculture and ecosystems are extremely vulnerable. In this study, the data for normalized difference vegetation index (NDVI) obtained from moderate-resolution imaging spectroradiometer (MODIS) sensors and climate data (precipitation and temperature) derived from the national meteorological stations were employed to examine the spatiotemporal differences in vegetation growth and its reaction to climate changes in the YRB from 2000‒2019, using several sophisticated statistical methods. The results showed that both NDVI and climatic variables exhibited overall increasing trends during this period, and positive correlations at different significant levels were found between temperature/precipitation and NDVI. Furthermore, NDVI in spring had the strongest response to temperature/precipitation, and the correlation coefficient of NDVI with temperature and precipitation was 0.485 and 0.726, respectively. However, an opposite situation was detected in autumn (September to November) since NDVIs exhibited the weakest responses to temperatures/precipitation, and the NDVI’s correlation with both temperature and precipitation was 0.13. This indicated that, compared to other seasons, increasing the temperature and precipitation has the most significant effect on NDVI in spring (March to May). Except for a few places in the northern, southern, and southwestern regions of the YRB, NDVI was positively correlated with precipitation in most areas. There was an inverse relationship between NDVI and temperature in most parts of the central YRB, especially in summer (June to August) and growing season (May to September); however, there was a positive correlation in most areas of the YRB in spring. Finally, continuous attention must be given to the influence of other factors in the YRB.