Deep learning model for diagnosis of venous thrombosis from lower extremity peripheral ultrasound imaging
Po-Wei Chen,
Bor-Yann Tseng,
Zhu-Han Yang,
Chi-Hua Yu,
Keng-Tse Lin,
Jhen-Nong Chen,
Ping-Yen Liu
Affiliations
Po-Wei Chen
Institute of Clinical Medicine, College of Medicine, National Cheng Kung University, Tainan 704, Taiwan; Division of Cardiology, Department of Internal Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan 704, Taiwan
Bor-Yann Tseng
Department of Engineering Science, National Cheng Kung University, No. 1, University Road, Tainan 701, Taiwan
Zhu-Han Yang
Department of Engineering Science, National Cheng Kung University, No. 1, University Road, Tainan 701, Taiwan
Chi-Hua Yu
Department of Engineering Science, National Cheng Kung University, No. 1, University Road, Tainan 701, Taiwan; Corresponding author
Keng-Tse Lin
Department of Engineering Science, National Cheng Kung University, No. 1, University Road, Tainan 701, Taiwan
Jhen-Nong Chen
Department of Engineering Science, National Cheng Kung University, No. 1, University Road, Tainan 701, Taiwan
Ping-Yen Liu
Institute of Clinical Medicine, College of Medicine, National Cheng Kung University, Tainan 704, Taiwan; Division of Cardiology, Department of Internal Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan 704, Taiwan; Corresponding author
Summary: Deep vein thrombosis (DVT) causes significant healthcare burdens worldwide. This study aims to establish a deep learning model for the diagnosis of DVT from the assessment of vein compressibility. Considering the complexity of ultrasound images, convolutional neural networks with UNet and residual neural network (ResNet) are established for image segmentation, from venous duplex ultrasonographic video images, obtained through standard and portable handheld ultrasound methods. To further evaluate the similarity between the predicted and ground truth images, the structural similarity index (SSIM) is employed. Our deep learning model achieves over 90% accuracy, providing an innovative tool for both images and videos. This study harnesses the power of machine learning to develop an automatic labeling tool that can diagnose DVT by analyzing ultrasonography images. To make the tool more accessible to front-line clinicians, a user-friendly application is created to quickly assess possible clinical severity and enable prompt medical intervention, reducing disease progression.
