Proceedings ArticleDOI
Segmentation of Vascular Regions in Ultrasound Images: A Deep Learning Approach
TLDR
A pipelined network comprising of a convolutional neural network followed by unsupervised clustering is proposed to perform vessel segmentation in liver ultrasound images, motivated by the tremendous success of CNNs in object detection and localization.Abstract:
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.read more
Citations
More filters
Journal ArticleDOI
Automated vessel segmentation in lung CT and CTA images via deep neural networks.
Wenjun Tan,Wenjun Tan,luyu zhou,luyu zhou,Xiaoshuo Li,Xiaoshuo Li,xiaoyu yang,Yufei Chen,Jinzhu Yang,Jinzhu Yang +9 more
TL;DR: Wang et al. as discussed by the authors reviewed 12 different pulmonary vascular segmentation algorithms of lung CT and CTA images and then objectively evaluated and compared their performances in terms of Dice coefficient, over segmentation rate and under segmentation performance.
Book ChapterDOI
MR-to-US Registration Using Multiclass Segmentation of Hepatic Vasculature with a Reduced 3D U-Net.
Bart R. Thomson,Jasper N. Smit,Oleksandra Ivashchenko,Niels F. M. Kok,Koert F. D. Kuhlmann,T.J.M. Ruers,Matteo Fusaglia +6 more
TL;DR: A workflow consisting of multi-class segmentation combined with selective non-rigid registration that leads to sufficient accuracy for integration in computer assisted liver surgery is developed using a reduced 3D U-Net for segmentation, followed by non- Rigid coherent point drift (CPD) registration.
Proceedings ArticleDOI
Vessel lumen segmentation in internal carotid artery ultrasounds with deep convolutional neural networks
TL;DR: This work represents a first successful step towards the automated identification of the vessel lumen in carotid artery ultrasound images and is an important first step in creating a system that can independently evaluate carOTid ultrasounds.
Journal ArticleDOI
Deep learning for image-based liver analysis - A comprehensive review focusing on malignant lesions
Shanmugapriya Survarachakan,Pravda Jith Ray Prasad,Rabia Naseem,Javier Pérez de Frutos,Rahul Prasanna Kumar,Thomas Langø,Faouzi Alaya Cheikh,Ole Jakob Elle,Frank Lindseth +8 more
TL;DR: In this paper , the analysis using deep learning of focal liver lesions, with a special interest in hepatocellular carcinoma and metastatic cancer; and structures like the parenchyma or the vascular system.
Journal ArticleDOI
A new deep learning method for displacement tracking from ultrasound RF signals of vascular walls.
Chenhui Xiao,Zhenzhou Li,Jianfeng Lu,Jinyan Wang,Haoteng Zheng,Bi Zuyue,Mengyang Chen,Rui Mao,Minhua Lu +8 more
TL;DR: This study proposed a new method based on deep learning (DL) to track the displacement of the vessel wall from the ultrasound radio-frequency (RF) signals, which is a key technique to achieve quantitative measurement of vascular biomechanics.
References
More filters
Journal ArticleDOI
A Neuromorphic Chip Optimized for Deep Learning and CMOS Technology With Time-Domain Analog and Digital Mixed-Signal Processing
TL;DR: The time-domain neural network (TDNN), which employs time- domain analog and digital mixed-signal processing (TDAMS) that uses delay time as the analog signal, is proposed, which exploits energy-efficient analog computing, but also enables fully spatially unrolled architecture by the hardware-efficient feature of TDAMS.
Journal ArticleDOI
Automatic registration between 3D intra-operative ultrasound and pre-operative CT images of the liver based on robust edge matching
TL;DR: Experimental results show that automatic registration can be successfully achieved between 3D B-mode US and CT images even with a large initial misalignment.