Browsing by Author "Chen, Kuan-Chou"

Now showing 1 - 2 of 2

Optical imaging of ovarian cancer using a matrix metalloproteinase-3-sensitive near-infrared fluorescent probe
(2018-02-01)
Wang, Kuo-Hwa
;
Wang, Yung-Ming
;
Chiu, Li-Hsuan
;
Chen, Tze-Chien
;
Tsai, Yu-Hui
Epithelial ovarian cancer (EOC) is the seventh most common cancer among women worldwide. The 5-year survival rate for women with EOC is only 30%-50%, which is largely due to the typically late diagnosis of this condition. EOC is difficult to detect in its early stage because of its asymptomatic nature. Recently, near-infrared fluorescent (NIRF) imaging has been developed as a potential tool for detecting EOC at the molecular level. In this study, a NIRF-sensitive probe was designed to detect matrix metalloproteinase (MMP) activity in ovarian cancer cells. A cyanine fluorochrome was conjugated to the amino terminus of a peptide substrate with enzymatic specificity for MMP-3. To analyze the novel MMP-3 probe, an in vivo EOC model was established by subcutaneously implanting SKOV3 cells, a serous-type EOC cell line, in mice. This novel MMP-3-sensitive probe specifically reacted with only the active MMP-3 enzyme, resulting in a significantly enhanced NIRF emission intensity. Histological analysis demonstrated that MMP-3 expression and activity were enhanced in the stromal cells surrounding the ovarian cancer cells. These studies establish a molecular imaging reporter for diagnosing early-stage EOC. Additional studies are required to confirm the early-stage activity of MMP-3 in EOC and its diagnostic and prognostic significance.
RECOGNIZING CHINESE TEXTS WITH 3D CONVOLUTIONAL NEURAL NETWORK
(2019-01-01)
Chen, Kuan-Chou
;
Lin, Guan-Ting
;
Lin, Che-Tsung
;
Guo, Jiun-In
;
交大名義發表
In this paper, we propose a deep learning system to localize and recognize Chinese texts in scenes with signage and road marks through 3D convolutional neural network. The proposed system adopts YOLO for detecting target location and exploits 3D convolutional neural network for recognizing the contents. The proposed design outperforms the existing designs based on LSTM and achieves real-time processing performance, which is feasible to be implemented on embedded platforms. The proposed system reaches over 90% accuracy in recognizing Chinese texts on bird's-eye viewing road marks in a self-driving vehicle equipped with a fisheye camera. In addition, this system can achieve 20 fps execution speed with NVIDIA DIGITS DevBox with 1080Ti GPU, which is fast enough for autonomous driving applications.