Automatic Ultrasound Vessel Segmentation with Deep Spatiotemporal Context Learning

Jiang, Baichuan; Chen, Alvin; Bharat, Shyam; Miao, Zheng

doi:10.1007/978-3-030-87583-1_1

Cited by 5 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They reported comparable performance to a human operator. In addition, Jiang et al incorporated color Doppler images to train the VesNetSCT+ for small vessels, e.g., femoral and tibial artery [22]. Compared with classic approaches, learning-based approaches have demonstrated promising potential for realtime performance and unstructured segmentation results.…”

Section: Related Work a Cross-sectional Us Image Segmentationmentioning

confidence: 99%

Towards Autonomous Atlas-Based Ultrasound Acquisitions in Presence of Articulated Motion

Jiang

Gao

Xie

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Robotic ultrasound (US) imaging aims at overcoming some of the limitations of free-hand US examinations, e.g. difficulty in guaranteeing intra-and inter-operator repeatability. However, due to anatomical and physiological variations between patients and relative movement of anatomical substructures, it is challenging to robustly generate optimal trajectories to examine the anatomies of interest, in particular, when they comprise articulated joints. To address this challenge, this paper proposes a vision-based approach allowing autonomous robotic US limb scanning. To this end, an atlas MRI template of a human arm with annotated vascular structures is used to generate trajectories and register and project them onto patients' skin surfaces for robotic US acquisition. To effectively segment and accurately reconstruct the targeted 3D vessel, we make use of spatial continuity in consecutive US frames by incorporating channel attention modules into a U-Net-type neural network. The automatic trajectory generation method is evaluated on six volunteers with various articulated joint angles. In all cases, the system can successfully acquire the planned vascular structure on volunteers' limbs. For one volunteer the MRI scan was also available, which allows the evaluation of the average radius of the scanned artery from US images, resulting in a radius estimation (1.2±0.05 mm) comparable to the MRI ground truth (1.2 ± 0.04 mm).

show abstract

Section: Related Work a Cross-sectional Us Image Segmentationmentioning

confidence: 99%

Towards Autonomous Atlas-Based Ultrasound Acquisitions in Presence of Articulated Motion

Jiang

Gao

Xie

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Therefore, to capture this temporal pattern and the inherent 3D anatomical context information, we propose to incorporate a recurrent neural network (RNN) into a U-Net 10 type segmentation model for spatiotemporal context learning. Inspired by VesNet11 , the model architecture is shown in Fig.3below. The two input channels consist of the original B-Mode image channel and the aggregated feature map channel, which are stacked along the channel dimension.…”

mentioning

confidence: 99%

Feature-aggregated spatiotemporal spine surface estimation for wearable patch ultrasound volumetric imaging

Jiang

Moghekar³

et al. 2023

Medical Imaging 2023: Ultrasonic Imaging and Tomography

View full text Add to dashboard Cite

Clear identification of bone structures is crucial for ultrasound-guided lumbar interventions, but it can be challenging due to the complex shapes of the self-shadowing vertebra anatomy and the extensive background speckle noise from the surrounding soft tissue structures. Therefore, in this work, we will present our method for estimating the vertebra bone surfaces by using a spatiotemporal U-Net architecture learning from the B-Mode image and aggregated feature maps of hand-crafted filters. Additionally, we are integrating this solution with our patch-like wearable ultrasound system to capture the repeating anatomical patterns and image the bone surfaces from multiple insonification angles. 3D bone representations can then be created for interventional guidance. The methods are evaluated on spine phantom image data collected by our proposed “Patch” scanner, and our systematic ablation experiment shows that improved accuracy can be achieved with the proposed architecture. Equipped with this surface estimation network, our wearable ultrasound system can potentially provide intuitive and accurate interventional guidance for clinicians in an augmented reality setting.

show abstract

Motion Magnification in Robotic Sonography: Enabling Pulsation-Aware Artery Segmentation

Huang,

Bi,

Navab

et al. 2023

2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Automatic Ultrasound Vessel Segmentation with Deep Spatiotemporal Context Learning

Cited by 5 publications

References 26 publications

Towards Autonomous Atlas-Based Ultrasound Acquisitions in Presence of Articulated Motion

Towards Autonomous Atlas-Based Ultrasound Acquisitions in Presence of Articulated Motion

Feature-aggregated spatiotemporal spine surface estimation for wearable patch ultrasound volumetric imaging

Motion Magnification in Robotic Sonography: Enabling Pulsation-Aware Artery Segmentation

Contact Info

Product

Resources

About