NCCU-Prof.Chung-Ming Lo-- Fully Automated System for Stroke Ultrasound Imaging Recognition and Report Generation

Exhibitor: NATIONAL TSING HUA UNIVERSITY GLOBAL RESEARCH & INDUSTRY ALLIANCE

Booth No: N415A

Characteristic

【Characteristic】
"Based on the ground truth from the clinical examination report, the vision transformer (ViT) features extracted from all CCD images (513 stroke and 458 normal images) were combined in machine learning classifiers to generate the likelihood of ischemic stroke for each image. The pretrained weights from ImageNet reduced the time-consuming training process. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve were calculated to evaluate the stroke prediction model. The chi-square test, DeLong test, and Bonferroni correction for multiple comparisons were applied to deal with the type-I error. Only p values equal to or less than 0.00125 were considered to be statistically significant.
The proposed CAD system achieved an accuracy of 89%, a sensitivity of 94%, a specificity of 84%, and an area under the receiver operating characteristic curve of 0.95, outperforming the convolutional neural networks AlexNet (82%, p < 0.001), Inception-v3 (78%, p < 0.001), ResNet101 (84%, p < 0.001), and DenseNet201 (85%, p < 0.01). The computational time in model training was only 30 s, which would be efficient and practical in clinical use."

【R & D team/Company Profile】
Inventor : Chung-Ming Lo
Our team is led by Professor Chung-Ming Lo, who obtained his Ph.D. in Computer Science from National Taiwan University in 2013. He currently serves as an Associate Professor at the Graduate Institute of Library, Information, and Archival Studies and as the Head of the Research and Development Division at the Social Data Center, National Chengchi University. Professor Lo has extensive experience in AI diagnostics and medical image processing, having published over a hundred academic papers and patents. As an academic editor for the SCI journal PLOS ONE, he frequently reviews papers from 50 different SCI journals. His research expertise includes image recognition, multimedia information systems, deep learning, and artificial intelligence. Our team is dedicated to advancing AI technology applications in medical imaging and diagnostics and has received numerous national and international academic awards.

【Contact window】
Chung-Ming Lo
buddylo@nccu.edu.tw