3篇
您的检索式：作者名="Wang Shaode"
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Transferring deep neural networks for the differentiation of mammographic breast lesions显示文摘Machine learning can help differentiating benign and malignant lesions seen on mammographic images. Conventional models require handcrafting features for lesion representation. Due to insufficient medical instances, the performance of convolutional neural networks(CNNs) can be further increased. This study makes use of transfer learning for mammographic breast lesion diagnosis and deep neural network(DNN) models pre-trained with large-scale natural images are employed. The diagnosis performance is evaluated with the prediction accuracy(ACC) and the area under the curve(AUC) on average. A histologically verified database is analyzed which contains 406 lesions(230 benign and 176 malignant). Involved models include transferred DNNs(GoogLeNet and AlexNet), shallow CNNs(CNN2 and CNN3) that are fully trained with medical instances and boosted by support vector machine(SVM), and two conventional methods which combine handcrafted features and SVM for lesion diagnosis. Experimental results indicate that GoogLeNet achieves the best performance(ACC=0.81, AUC=0.88), followed by AlexNet(ACC=0.79, AUC=0.83) and CNN3(ACC=0.73, AUC=0.82). Knowledge transfer can improve the mammographic breast cancer diagnosis, while its wide application still requires further verification in medical imaging domain. | YU ShaoDe LIU LingLing WANG ZhaoYang DAI GuangZhe XIE YaoQin | 2019 | Science China(Technological Sciences)2019，62，3： | 5 |
| 2 | Ultrafast multi-target control of tightly focused light fields显示文摘The control of ultrafast optical field is of great interest in developing ultrafast optics as well as the investigation on vari-ous light-matter interactions with ultrashort pulses.However,conventional spatial encoding approaches have only lim-ited steerable targets usually neglecting the temporal effect,thus hindering their broad applications.Here we present a new concept for realizing ultrafast modulation of multi-target focal fields based on the facile combination of time-depend-ent vectorial diffraction theory with fast Fourier transform.This is achieved by focusing femtosecond pulsed light carrying vectorial-vortex by a single objective lens under tight focusing condition.It is uncovered that the ultrafast temporal de-gree of freedom within a configurable temporal duration(~400 fs)plays a pivotal role in determining the rich and exotic features of the focused optical field at one time,namely,bright-dark alternation,periodic rotation,and longitudinal/trans-verse polarization conversion.The underlying control mechanisms have been unveiled.Besides being of academic in-terest in diverse ultrafast spectral regimes,these peculiar behaviors of the space-time evolutionary beams may underpin prolific ultrafast-related applications such as multifunctional integrated optical chip,high-efficiency laser trapping,micro-structure rotation,super-resolution optical microscopy,precise optical measurement,and liveness tracking. | Yanxiang Zhang Xiaofei Liu Han Lin Dan Wang Ensi Cao Shaoding Liu Zhongquan Nie Baohua Jia | 2022 | Opto-Electronic Advances2022，5，3： | 2 |
| 3 | Interconnection between north China and Central China Power networks显示文摘 | Wang Shaode Liu Jianqin Zheng Yingfen Lin Tingwei | 2000 | Electricity2000，，3： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员