Portable Ultrasound Research System for Use in Automated Bladder Monitoring with Machine-Learning-Based Segmentation

We developed a new mobile ultrasound device for long-term and automated bladder monitoring without user interaction consisting of 32 transmit and receive electronics as well as a 32-element phased array 3 MHz transducer. The device architecture is based on data digitization and rapid transfer to a consumer electronics device (e.g., a tablet) for signal reconstruction (e.g., by means of plane wave compounding algorithms) and further image processing. All reconstruction algorithms are implemented in the GPU, allowing real-time reconstruction and imaging. The system and the beamforming algorithms were evaluated with respect to the imaging performance on standard sonographical phantoms (CIRS multipurpose ultrasound phantom) by analyzing the resolution, the SNR and the CNR. Furthermore, ML-based segmentation algorithms were developed and assessed with respect to their ability to reliably segment human bladders with different filling levels. A corresponding CNN was trained with 253 B-mode data sets and 20 B-mode images were evaluated. The quantitative and qualitative results of the bladder segmentation are presented and compared to the ground truth obtained by manual segmentation.

Rectus Femoris Mimicking Ultrasound Phantom for Muscle Mass Assessment: Design, Research, and Training Application

Ultrasound has become widely used as a means to measure the rectus femoris muscle in the acute and chronic phases of critical illness. Despite its noninvasiveness and accessibility, its accuracy highly depends on the skills of the technician. However, few ultrasound phantoms for the confirmation of its accuracy or to improve technical skills exist. In this study, the authors created a novel phantom model and used it for investigating the accuracy of measurements and for training. Study 1 investigated how various conditions affect ultrasound measurements such as thickness, cross-sectional area, and echogenicity. Study 2 investigated if the phantom can be used for the training of various health care providers in vitro and in vivo. Study 1 showed that thickness, cross-sectional area, and echogenicity were affected by probe compression strength, probe angle, phantom compression, and varying equipment. Study 2 in vitro showed that using the phantom for training improved the accuracy of the measurements taken within the phantom, and Study 2 in vivo showed the phantom training had a short-term effect on improving the measurement accuracy in a human volunteer. The new ultrasound phantom model revealed that various conditions affected ultrasound measurements, and phantom training improved the measurement accuracy.

Sodium Alginate Ultrasound Phantom for Medical Education

The ultrasound phantoms used to educate medical students should not only closely mimic the ultrasound characteristics of human soft tissues but also be inexpensive and easy to manufacture. I have been studying handmade ultrasound phantoms and proposed an ultrasound phantom comprising calcium alginate hydrogel that met these requirements but caused a speckle pattern similar to that observed in ultrasound images of liver. In this study, I show that adding ethanol to the precursors used to fabricate the phantom reduces the speckle pattern. The ultrasound propagation velocity and attenuation coefficient of the phantom were 1561 ± 8 m/s and 0.54 ± 0.18 dB/cm/MHz, respectively (mean ± standard deviation), which are within the ranges of those in human soft tissues (1530-1600 m/s and 0.3-1.0 dB/cm/MHz, respectively). This phantom is easy to fabricate without special equipment, is inexpensive, and is suitable for elementary training on ultrasound diagnosis, operation of ultrasound-guided needles, and blind catheter insertion.

Rectus Femoris Mmimicking Ultrasound Phantom for Muscle Mass Assessment: Design, Research, and Training Application

Ultrasound has become widely used as a mean to measure the rectus femoris muscle in the acute and chronic phase of critical illness. Despite its noninvasiveness and accessibility, its accuracy highly depends on the skills of the technician. However, few ultrasound phantoms for the confirmation of its accuracy or to improve technical skills exist. In this study, we created a novel phantom model and used it for investigating the accuracy of measurements and for training. Study 1 investigated how various conditions affect ultrasound measurements such as thickness, cross-sectional area, and echogenicity. Study 2 investigated if the phantom can be used for training of various health care providers in vitro and vivo. Study 1 showed that thickness, cross-sectional area, and echogenicity were affected by probe compression strength, probe angle, phantom compression, and varying equipment. Study 2 in vitro showed that using the phantom for training improved the accuracy of the measurements taken within phantom, and Study 2 in vivo showed the phantom training had a short-term effect on improving the measurement accuracy in a human volunteer. The new ultrasound phantom model revealed that various conditions affected ultrasound measurements, and phantom training improved the measurement accuracy.

An Affordable and Easily Recreated Ultrasound Phantom for DVT

Evaluating a patient for a deep vein thrombosis (DVT) using ultrasound is a common procedure in the emergency department. Teaching a clinician to identify a DVT on ultrasound is often done on a phantom, which is a synthetic model intended to simulate a clinical condition. Traditional commercial ultrasound phantoms modeling a DVT exist, but can be prohibitively expensive. We have created a DVT phantom by embedding a water-filled balloon containing a smaller balloon filled with water and an acrylic polymer in a gelatin-psyllium hydrophilic mucilloid fiber mixture. This phantom is durable, easily created, and affordable. It provides clinicians the ability to learn to identify a DVT on a phantom prior to performing the procedure on a patient.