Header menu link for other important links
Segmentation of Vascular Regions in Ultrasound Images: A Deep Learning Approach
D. Mishra, , M. Sarkar, S. Manohar, A.S. Soin
Published in Institute of Electrical and Electronics Engineers Inc.
Volume: 2018-May
Vascular region segmentation in ultrasound images is necessary for applications like automatic registration, and surgical navigation. In this paper, a pipelined network comprising of a convolutional neural network (CNN) followed by unsupervised clustering is proposed to perform vessel segmentation in liver ultrasound images. The work is motivated by the tremendous success of CNNs in object detection and localization. CNN here is trained to localize vascular regions, which are subsequently segmented by the clustering. The proposed network results in 99.14% pixel accuracy and 69.62% mean region intersection over union on 132 images. These values are better than some existing methods. © 2018 IEEE.
About the journal
JournalData powered by TypesetProceedings - IEEE International Symposium on Circuits and Systems
PublisherData powered by TypesetInstitute of Electrical and Electronics Engineers Inc.