Pose Estimation of 2D Ultrasound Probe from Ultrasound Image Sequences Using CNN and RNN

2021 ◽  
pp. 96-105
Author(s):  
Kanta Miura ◽  
Koichi Ito ◽  
Takafumi Aoki ◽  
Jun Ohmiya ◽  
Satoshi Kondo
2021 ◽  
Vol 7 (1) ◽  
pp. 158-161
Author(s):  
Ana Estrada Lugo ◽  
Niclas Bockelmann ◽  
Felix von Haxthausen

Abstract This work compares three different approaches to automatically segment the femoral artery from 2D ultrasound images. Two of the architectures follow a sequential structure, where each ultrasound image is considered a slice of the whole vessel volume, and its previous segmentation result will be part of the input, thus leading to a spatial prior. The Dice score on test data show a better performance on the baseline U-Net (0.819) compared to the sequential U-Net approaches (0.633, 0.725) for the femoral artery segmentation. This could be attributed to the misalignment of the slices being used in those networks. A possible improvement could be assumed in the implementation of a spatially calibrated and tracked ultrasound probe. Overall, these results indicate promising approaches for an automatic segmentation of the femoral artery using 2D ultrasound data.


Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6613
Author(s):  
Taehyung Kim ◽  
Dong-Hyun Kang ◽  
Shinyong Shim ◽  
Maesoon Im ◽  
Bo Kyoung Seo ◽  
...  

This study aims at creating low-cost, three-dimensional (3D), freehand ultrasound image reconstructions from commercial two-dimensional (2D) probes. The low-cost system that can be attached to a commercial 2D ultrasound probe consists of commercial ultrasonic distance sensors, a gimbal, and an inertial measurement unit (IMU). To calibrate irregular movements of the probe during scanning, relative position data were collected from the ultrasonic sensors that were attached to a gimbal. The directional information was provided from the IMU. All the data and 2D ultrasound images were combined using a personal computer to reconstruct 3D ultrasound image. The relative position error of the proposed system was less than 0.5%. The overall shape of the cystic mass in the breast phantom was similar to those from 2D and sections of 3D ultrasound images. Additionally, the pressure and deformations of lesions could be obtained and compensated by contacting the probe to the surface of the soft tissue using the acquired position data. The proposed method did not require any initial marks or receivers for the reconstruction of a 3D ultrasound image using a 2D ultrasound probe. Even though our system is less than $500, a valuable volumetric ultrasound image could be provided to the users.


Author(s):  
Smruti Mahapatra ◽  
Tarana Parvez Kaovasia ◽  
Sufia Ainechi ◽  
Ana Ainechi ◽  
Molly Acord ◽  
...  

Abstract Standard diagnostic ultrasound imaging procedures heavily rely on a sonographer for image acquisition. Given the ultrasound probe is manually manipulated by the sonographer, there is a potential for noise artifacts like blurry acquired images caused by involuntary hand movements. Certain surgical procedures can also cause patients to exhibit involuntary “jumping” movements while on the operating table leading to further deterioration in ultrasound image quality. In this study, we attempt to mitigate these problems by fabricating a 3D-printed ultrasound probe holder. Due to the lightweight nature of the device, it can attach to surgical retractors without influencing the functionality of the retractor. Therefore, the 3D printed probe holder not only reduces relative motion between the probe and the patient, but also reduce the need for a sonographer during complex surgeries.


Sign in / Sign up

Export Citation Format

Share Document