Full-automated system for the segmentation of the common carotid artery in ultrasound images

Christodoulou, Lakis; Loizou, Christos P.; Spyrou, Christina; Kasparis, Takis; Pantziaris, M.

doi:10.1109/isccsp.2012.6217824

Cited by 9 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is sufficient to retrain the UNet rather than the entire RL agent because the training time is much shorter. there are already a plethora of mature segmentation techniques [29], [30].…”

Section: B Multi-modality State Representation 1) State Embedding Fro...mentioning

confidence: 99%

VesNet-RL: Simulation-based Reinforcement Learning for Real-World US Probe Navigation

Yuan¹,

Jiang²,

Gao³

et al. 2022

Preprint

View full text Add to dashboard Cite

Ultrasound (US) is one of the most common medical imaging modalities since it is radiation-free, low-cost, and realtime. In freehand US examinations, sonographers often navigate a US probe to visualize standard examination planes with rich diagnostic information. However, reproducibility and stability of the resulting images often suffer from intra-and inter-operator variation. Reinforcement learning (RL), as an interaction-based learning method, has demonstrated its effectiveness in visual navigating tasks; however, RL is limited in terms of generalization. To address this challenge, we propose a simulation-based RL framework for real-world navigation of US probes towards the standard longitudinal views of vessels. A UNet is used to provide binary masks from US images; thereby, the RL agent trained on simulated binary vessel images can be applied in real scenarios without further training. To accurately characterize actual states, a multi-modality state representation structure is introduced to facilitate the understanding of environments. Moreover, considering the characteristics of vessels, a novel standard view recognition approach based on the minimum bounding rectangle is proposed to terminate the searching process. To evaluate the effectiveness of the proposed method, the trained policy is validated virtually on 3D volumes of a volunteer's in-vivo carotid artery, and physically on custom-designed gel phantoms using robotic US. The results demonstrate that proposed approach can effectively and accurately navigate the probe towards the longitudinal view of vessels.

show abstract

“…It is sufficient to retrain the UNet rather than the entire RL agent because the training time is much shorter. there are already a plethora of mature segmentation techniques [29], [30].…”

Section: B Multi-modality State Representation 1) State Embedding Fro...mentioning

confidence: 99%

VesNet-RL: Simulation-based Reinforcement Learning for Real-World US Probe Navigation

Yuan¹,

Jiang²,

Gao³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Furthermore, the authors of [ 18 ] attempted to implement a fully automated segmentation system using adaptive snake’s contour as well as level set segmentation. When comparing both techniques together the authors found out that the snake’s contour method outperformed the level set segmentation.…”

Section: Related Workmentioning

confidence: 99%

Encoder-Decoder Architecture for Ultrasound IMC Segmentation and cIMT Measurement

Al-Mohannadi

Al-Maadeed

Elharrouss

et al. 2021

Sensors

View full text Add to dashboard Cite

Cardiovascular diseases (CVDs) have shown a huge impact on the number of deaths in the world. Thus, common carotid artery (CCA) segmentation and intima-media thickness (IMT) measurements have been significantly implemented to perform early diagnosis of CVDs by analyzing IMT features. Using computer vision algorithms on CCA images is not widely used for this type of diagnosis, due to the complexity and the lack of dataset to do it. The advancement of deep learning techniques has made accurate early diagnosis from images possible. In this paper, a deep-learning-based approach is proposed to apply semantic segmentation for intima-media complex (IMC) and to calculate the cIMT measurement. In order to overcome the lack of large-scale datasets, an encoder-decoder-based model is proposed using multi-image inputs that can help achieve good learning for the model using different features. The obtained results were evaluated using different image segmentation metrics which demonstrate the effectiveness of the proposed architecture. In addition, IMT thickness is computed, and the experiment showed that the proposed model is robust and fully automated compared to the state-of-the-art work.

show abstract

“…Previously it was shown that cross-sectional Doppler results in accurate velocity estimates, without requiring a specific probe orientation [11] . In this case, the intersection of the ultrasound plane and the cylindrical vessel results in an ellipse, of which the parameters are used to estimate the Doppler angle: cos ( ˆ α) = cos ( arcsin (b/a )) cos (β ) , (2) where a and b are the semi-major and semi minor axis of the ellipse, respectively, and β is the rotation of the ellipse as depicted in Fig. 1 .…”

Section: Introductionmentioning

confidence: 99%

“…The output of the Hough transform can also be used to initialize a snake to further improve the segmentation result [18] , where the basic concept is to fit a contour to local image information, such as gradient. Typically, such parametric active contours are implemented by finding the contour that minimizes the sum of an internal energy (quantifying the continuity and smoothness of the contour) and external energy that attracts the contour to edges in the image [2,6,[19][20][21][22][23] . As a result, these methods have the drawback that they require careful initialization and often require extensive tuning of parameters for convergence.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised domain adaptation method for segmenting cross-sectional CCA images

Knippenberg

Sloun

Mischi

et al. 2022

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Full-automated system for the segmentation of the common carotid artery in ultrasound images

Cited by 9 publications

References 8 publications

VesNet-RL: Simulation-based Reinforcement Learning for Real-World US Probe Navigation

VesNet-RL: Simulation-based Reinforcement Learning for Real-World US Probe Navigation

Encoder-Decoder Architecture for Ultrasound IMC Segmentation and cIMT Measurement

Unsupervised domain adaptation method for segmenting cross-sectional CCA images

Contact Info

Product

Resources

About