Search NASA⌕ Search

SEARCH · Search NASA

Results for “Ultrasound imaging”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Performance Comparison of Object Detection Networks for Shrapnel Identification in Ultrasound Images

Ultrasound imaging is a critical tool for triaging and diagnosing subjects but only if images can be properly interpreted. Unfortunately, in remote or military medicine situations, the expertise to interpret images can be lacking. Machine-learning image interpretation models that are explainable to the end user and deployable in real time with ultrasound equipment have the potential to solve this problem. We have previously shown how a YOLOv3 (You Only Look Once) object detection algorithm can be used for tracking shrapnel, artery, vein, and nerve fiber bundle features in a tissue phantom. However, real-time implementation of an object detection model requires optimizing model inference time. Here, we compare the performance of five different object detection deep-learning models with varying architectures and trainable parameters to determine which model is most suitable for this shrapnel-tracking ultrasound image application. We used a dataset of more than 16,000 ultrasound images from gelatin tissue phantoms containing artery, vein, nerve fiber, and shrapnel features for training and evaluating each model. Every object detection model surpassed 0.85 mean average precision except for the detection transformer model. Overall, the YOLOv7tiny model had the higher mean average precision and quickest inference time, making it the obvious model choice for this ultrasound imaging application. Other object detection models were overfitting the data as was determined by lower testing performance compared with higher training performance. In summary, the YOLOv7tiny object detection model had the best mean average precision and inference time and was selected as optimal for this application. Next steps will implement this object detection algorithm for real-time applications, an important next step in translating AI models for emergency and military medicine.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2009

Method and system to synchronize acoustic therapy with ultrasound imaging

Interference in ultrasound imaging when used in connection with high intensity focused ultrasound (HIFU) is avoided by employing a synchronization signal to control the HIFU signal. Unless the timing of the HIFU transducer is controlled, its output will substantially overwhelm the signal produced by ultrasound imaging system and obscure the image it produces. The synchronization signal employed to control the HIFU transducer is obtained without requiring modification of the ultrasound imaging system. Signals corresponding to scattered ultrasound imaging waves are collected using either the HIFU transducer or a dedicated receiver. A synchronization processor manipulates the scattered ultrasound imaging signals to achieve the synchronization signal, which is then used to control the HIFU bursts so as to substantially reduce or eliminate HIFU interference in the ultrasound image. The synchronization processor can alternatively be implemented using a computing device or an application-specific circuit.

Owen, Neil↗
DOE OSTI2022

An image classification deep-learning algorithm for shrapnel detection from ultrasound images

Ultrasound imaging is essential for non-invasively diagnosing injuries where advanced diagnostics may not be possible. However, image interpretation remains a challenge as proper expertise may not be available. In response, artificial intelligence algorithms are being investigated to automate image analysis and diagnosis. Here, we highlight an image classification convolutional neural network for detecting shrapnel in ultrasound images. As an initial application, different shrapnel types and sizes were embedded first in a tissue mimicking phantom and then in swine thigh tissue. The algorithm architecture was optimized stepwise by minimizing validation loss and maximizing F1 score. The final algorithm design trained on tissue phantom image sets had an F1 score of 0.95 and an area under the ROC curve of 0.95. It maintained higher than a 90% accuracy for each of 8 shrapnel types. When trained only on swine image sets, the optimized algorithm format had even higher metrics: F1 and area under the ROC curve of 0.99. Overall, the algorithm developed resulted in strong classification accuracy for both the tissue phantom and animal tissue. This framework can be applied to other trauma relevant imaging applications such as internal bleeding to further simplify trauma medicine when resources and image interpretation are scarce.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2010

Interference-free ultrasound imaging during HIFU therapy, using software tools

Disclosed herein is a method for obtaining a composite interference-free ultrasound image when non-imaging ultrasound waves would otherwise interfere with ultrasound imaging. A conventional ultrasound imaging system is used to collect frames of ultrasound image data in the presence of non-imaging ultrasound waves, such as high-intensity focused ultrasound (HIFU). The frames are directed to a processor that analyzes the frames to identify portions of the frame that are interference-free. Interference-free portions of a plurality of different ultrasound image frames are combined to generate a single composite interference-free ultrasound image that is displayed to a user. In this approach, a frequency of the non-imaging ultrasound waves is offset relative to a frequency of the ultrasound imaging waves, such that the interference introduced by the non-imaging ultrasound waves appears in a different portion of the frames.

Vaezy, Shahram↗
NASA NTRS1999

Three-dimensional segmentation of luminal and adventitial borders in serial intravascular ultrasound images

Intravascular ultrasound (IVUS) provides exact anatomy of arteries, allowing accurate quantitative analysis. Automated segmentation of IVUS images is a prerequisite for routine quantitative analyses. We present a new three-dimensional (3D) segmentation technique, called active surface segmentation, which detects luminal and adventitial borders in IVUS pullback examinations of coronary arteries. The technique was validated against expert tracings by computing correlation coefficients (range 0.83-0.97) and William's index values (range 0.37-0.66). The technique was statistically accurate, robust to image artifacts, and capable of segmenting a large number of images rapidly. Active surface segmentation enabled geometrically accurate 3D reconstruction and visualization of coronary arteries and volumetric measurements.

NASA Discipline Cardiopulmonary↗
NASA NTRS2011

Split-screen display system and standardized methods for ultrasound image acquisition and multi-frame data processing

A standardized acquisition methodology assists operators to accurately replicate high resolution B-mode ultrasound images obtained over several spaced-apart examinations utilizing a split-screen display in which the arterial ultrasound image from an earlier examination is displayed on one side of the screen while a real-time "live" ultrasound image from a current examination is displayed next to the earlier image on the opposite side of the screen. By viewing both images, whether simultaneously or alternately, while manually adjusting the ultrasound transducer, an operator is able to bring into view the real-time image that best matches a selected image from the earlier ultrasound examination. Utilizing this methodology, dynamic material properties of arterial structures, such as IMT and diameter, are measured in a standard region over successive image frames. Each frame of the sequence has its echo edge boundaries automatically determined by using the immediately prior frame's true echo edge coordinates as initial boundary conditions. Computerized echo edge recognition and tracking over multiple successive image frames enhances measurement of arterial diameter and IMT and allows for improved vascular dimension measurements, including vascular stiffness and IMT determinations.

Selzer, Robert H.↗
NASA NTRS2006

System and method for improving ultrasound image acquisition and replication for repeatable measurements of vascular structures

High resolution B-mode ultrasound images of the common carotid artery are obtained with an ultrasound transducer using a standardized methodology. Subjects are supine with the head counter-rotated 45 degrees using a head pillow. The jugular vein and carotid artery are located and positioned in a vertical stacked orientation. The transducer is rotated 90 degrees around the centerline of the transverse image of the stacked structure to obtain a longitudinal image while maintaining the vessels in a stacked position. A computerized methodology assists operators to accurately replicate images obtained over several spaced-apart examinations. The methodology utilizes a split-screen display in which the arterial ultrasound image from an earlier examination is displayed on one side of the screen while a real-time live ultrasound image from a current examination is displayed next to the earlier image on the opposite side of the screen. By viewing both images, whether simultaneously or alternately, while manually adjusting the ultrasound transducer, an operator is able to bring into view the real-time image that best matches a selected image from the earlier ultrasound examination. Utilizing this methodology, measurement of vascular dimensions such as carotid arterial IMT and diameter, the coefficient of variation is substantially reduced to values approximating from about 1.0% to about 1.25%. All images contain anatomical landmarks for reproducing probe angulation, including visualization of the carotid bulb, stacking of the jugular vein above the carotid artery, and initial instrumentation settings, used at a baseline measurement are maintained during all follow-up examinations.

Selzer, Robert H.↗
DOE OSTI2024

Using AI Segmentation Models to Improve Foreign Body Detection and Triage from Ultrasound Images

Medical imaging can be a critical tool for triaging casualties in trauma situations. In remote or military medicine scenarios, triage is essential for identifying how to use limited resources or prioritize evacuation for the most serious cases. Ultrasound imaging, while portable and often available near the point of injury, can only be used for triage if images are properly acquired, interpreted, and objectively triage scored. Here, we detail how AI segmentation models can be used for improving image interpretation and objective triage evaluation for a medical application focused on foreign bodies embedded in tissues at variable distances from critical neurovascular features. Ultrasound images previously collected in a tissue phantom with or without neurovascular features were labeled with ground truth masks. These image sets were used to train two different segmentation AI frameworks: YOLOv7 and U-Net segmentation models. Overall, both approaches were successful in identifying shrapnel in the image set, with U-Net outperforming YOLOv7 for single-class segmentation. Both segmentation models were also evaluated with a more complex image set containing shrapnel, artery, vein, and nerve features. YOLOv7 obtained higher precision scores across multiple classes whereas U-Net achieved higher recall scores. Using each AI model, a triage distance metric was adapted to measure the proximity of shrapnel to the nearest neurovascular feature, with U-Net more closely mirroring the triage distances measured from ground truth labels. Overall, the segmentation AI models were successful in detecting shrapnel in ultrasound images and could allow for improved injury triage in emergency medicine scenarios.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Using Ultrasound Image Augmentation and Ensemble Predictions to Prevent Machine-Learning Model Overfitting

Deep learning predictive models have the potential to simplify and automate medical imaging diagnostics by lowering the skill threshold for image interpretation. However, this requires predictive models that are generalized to handle subject variability as seen clinically. Here, we highlight methods to improve test accuracy of an image classifier model for shrapnel identification using tissue phantom image sets. Using a previously developed image classifier neural network—termed ShrapML—blind test accuracy was less than 70% and was variable depending on the training/test data setup, as determined by a leave one subject out (LOSO) holdout methodology. Introduction of affine transformations for image augmentation or MixUp methodologies to generate additional training sets improved model performance and overall accuracy improved to 75%. Further improvements were made by aggregating predictions across five LOSO holdouts. This was done by bagging confidences or predictions from all LOSOs or the top-3 LOSO confidence models for each image prediction. Top-3 LOSO confidence bagging performed best, with test accuracy improved to greater than 85% accuracy for two different blind tissue phantoms. This was confirmed by gradient-weighted class activation mapping to highlight that the image classifier was tracking shrapnel in the image sets. Overall, data augmentation and ensemble prediction approaches were suitable for creating more generalized predictive models for ultrasound image analysis, a critical step for real-time diagnostic deployment.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2006

Validation of Ultrasound Imaging to Rule-out Thoracic Trauma on the International Space Station

Introduction: Aboard the International Space Station (ISS) an intra-thoracic injury may be disastrous to the crew member if the diagnosis is missed or even delayed. Pneumothorax and hemothorax commonly seen in trauma patients; the diagnosis is usually confirmed by chest X-ray or computed tomography. In this study, the ability of ultrasound to rule out pneumothorax by the presence "lung sliding" and hemothorax by the absence of pleural fluid was validated. Methods: The research activities were approved by the NASA Johnson Space Center Committee for the Protection of Human Subjects, and the participating crewmembers signed informed consent prior to the activity. ISS crewmembers received 2-hours of "hands on" ultrasound training 8 months prior to the on-orbit ultrasound exam. Baseline ultrasound images of the thorax were acquired on the crewmebers of Increment 8 and 9 prior to launch from Bakonur, Russia. Ultrasound examination of the thorax were performed on crewmembers at 30 day intervals (n=??) throughout their flight. Post flight images were acquired on or about landing day 10. Ultrasound images were acquired using the ISS Health Research Facility ultrasound system and examined by experts on the ground to rule out the presence of pneumothorax and hemothorax. Results: The presence of "lung sliding" which excludes pneumothorax, was seen in all subjects. The absence of pleural fluid, which excludes hemothorax was seen in all subjects. The optimal position between sonographer and patient under microgravity conditions and the amount and type of training for a non-physician crew medical officer for these procedures was also established for this procedure. Conclusion: Ultrasound can be performed on orbit under microgravity condition to rule thoracic trauma, such as pneumothorax and hemothorax.

Hamilton, Douglas R.↗
NASA NTRS2010

Ultrasound Imaging of Spine: State of the Art and Utility for Space Flight

Introduction: Ultrasound imaging (sonography) has been increasingly used for both primary diagnosis and monitoring of musculoskeletal injury, including fractures. In certain injuries, sonography has been shown to equal or surpass Magnetic Resonance Imaging in accuracy. Long-term exposure to reduced gravity may be expected to cause physiological and anatomical changes of the musculoskeletal system, which are not fully described or understood. In a limited-resource environment like space flight, sonography will likely remain the only imaging modality; therefore, further attention to its potential is warranted, including its ability to image anatomical deviations as well as irregularities of vertebrae and the spinal column. Methods: A thorough review of literature was conducted on the subject. A multipurpose ultrasound system was used to identify specific vertebrae, intervertebral disks, and other structures of the cervical spine in healthy volunteers, selected to represent various age, gender, and Body Mass Index (BMI) groups. Sonographic views were sought that would parallel radiographic views and signs used in the diagnosis of cervical spine injuries. Results: While using widely accepted radiographic signs of cervical spine injury, this sonographic protocol development effort resulted in successful identification of scanning planes and imaging protocols that could serve as alternatives for radiography. Some of these views are also applicable to diagnosing degenerative disk and bone disease, and other non-traumatic spine pathology. Strong, preliminary correlation has been demonstrated in a number of clinical cases between sonography and other imaging modalities. Conclusion: In the absence of radiography, sonography can be used to diagnose or rule out certain common types of cervical spine conditions including injury. Clinical validation of the findings appears to be realistic and would facilitate establishment of new sonographic protocols for special environments with lacking radiographic capability, such as human space flight.

Sargsyan, Ashot E.↗
DOE OSTI2022

Training Ultrasound Image Classification Deep-Learning Algorithms for Pneumothorax Detection Using a Synthetic Tissue Phantom Apparatus

Ultrasound (US) imaging is a critical tool in emergency and military medicine because of its portability and immediate nature. However, proper image interpretation requires skill, limiting its utility in remote applications for conditions such as pneumothorax (PTX) which requires rapid intervention. Artificial intelligence has the potential to automate ultrasound image analysis for various pathophysiological conditions. Training models require large data sets and a means of troubleshooting in real-time for ultrasound integration deployment, and they also require large animal models or clinical testing. Here, we detail the development of a dynamic synthetic tissue phantom model for PTX and its use in training image classification algorithms. The model comprises a synthetic gelatin phantom cast in a custom 3D-printed rib mold and a lung mimicking phantom. When compared to PTX images acquired in swine, images from the phantom were similar in both PTX negative and positive mimicking scenarios. We then used a deep learning image classification algorithm, which we previously developed for shrapnel detection, to accurately predict the presence of PTX in swine images by only training on phantom image sets, highlighting the utility for a tissue phantom for AI applications.

Boice, Emily N. (ORCID:0000000171802842)↗
NASA NTRS1989

Computer-generated 3D ultrasound images of the carotid artery

A method is under development to measure carotid artery lesions from a computer-generated three-dimensional ultrasound image. For each image, the position of the transducer in six coordinates (x, y, z, azimuth, elevation, and roll) is recorded and used to position each B-mode picture element in its proper spatial position in a three-dimensional memory array. After all B-mode images have been assembled in the memory, the three-dimensional image is filtered and resampled to produce a new series of parallel-plane two-dimensional images from which arterial boundaries are determined using edge tracking methods.

Selzer, Robert H.↗
NASA NTRS1999

Observations from the Microgravity Smoldering Combustion (MSC) Ultrasound Imaging System (UIS)

The Microgravity Smoldering Combustion (MSC) experiment is a study of the smolder characteristics of porous combustible materials in a microgravity environment. The objective of the study is to provide a better understanding of the controlling mechanisms of smolder, both in microgravity and normal earth gravity. Experiments have been conducted aboard the NASA Space Shuttle in the GAS-CAN, an apparatus requiring completely remote operation. Future GAS-CAN experiments will utilize an ultrasound imaging system (UIS). Thermocouples are currently used to measure temperature and reaction front velocities, but a less intrusive method is desirable, as smolder is affected by heat transfer along the thermocouple. It is expected that the UIS will eventually replace the existing array of thermocouples as a non-intrusive technique without compromising data acquisition. Smoldering is defined as a non-flaming, self-sustaining, propagating, exothermic, surface reaction, deriving its principal heat from heterogeneous oxidation of the fuel. Smolder of cable insulation is of particular concern in the space program; to date there have been a few minor incidents of overheated and charred cables and electrical components reported on Space Shuttle flights. Recently, the establishment of the International Space Station and other space facilities has increased interest in the study of smoldering in microgravity because of the need to preempt the possibility, and/or to minimize the effect of a smolder initiated fire during the operation of these facilities. The ignition and propagation of smolder are examined using both thermocouples and the UIS. The UIS has been implemented into the MSC flight hardware. The system provides information about local permeability variations within a smoldering sample, which can, in turn, be interpreted to track the propagation of the smolder reaction. The method utilizes the observation that transmission of an ultrasonic signal through a porous material increases with increasing permeability. Since a propagating smolder reaction leaves behind a char that is higher in permeability than the original (unburnt) material, ultrasonic transmission can be employed to monitor the progress of the primary reaction front, char evolution (i.e. material left by the smolder reaction), pyrolysis, and condensation fronts.

Walther, D.C.↗
NASA NTRS1999

Ultrasound Imaging System Implementation and Ignition Protocol for the Microgravity Smoldering Combustion (MSC) Experiments

The Microgravity Smoldering Combustion (MSC) experiment is a study of the smolder characteristics of porous combustible materials in a microgravity environment. The objective of the study is to provide a better understanding of the controlling mechanisms of smolder, both in microgravity and normal earth gravity. Experiments have been conducted aboard the NASA Space Shuttle in the Get Away Special Canister (GAS-CAN), an apparatus requiring completely remote operation. Future GAS-CAN experiments will utilize an ultrasound imaging system (UIS) which has been incorporated into the MSC experimental apparatus. Thermocouples are currently used to measure temperature and reaction front velocities. A less intrusive method is desirable, however, as smolder is a very weak reaction and it has been found that heat transfer along the thermocouple is sufficient to affect the smolder reaction. It is expected that the UIS system will eventually replace the existing array of thermocouples as a non-intrusive technique without compromising data acquisition. The UIS measures line of sight permeability, providing information about the reaction front position and extent. Additionally, the ignition sequence of the MSC experiments has been optimized from previous experiments to provide longer periods of self-supported smolder. An ignition protocol of a fixed power to the igniter for a fixed time is now implemented. This, rather than a controlled temperature profile ignition protocol at the igniter surface, along with the UIS system, will allow for better study of the effect of gravity on a smolder reaction.

Walther, David C.↗
NASA NTRS2004

Balanced Expertise Distribution in Remote Ultrasound Imaging Aboard The International Space Station (ISS)

Astronaut training for ISS operations usually ensures independent performance. With small crew size same crews also conduct all science work onboard. With diverse backgrounds, a good "match" between the existing and required skills can only be anecdotal. Furthermore, full proficiency in most of the complex tasks can be attained only through long training and practice, which may not be justified and may be impossible given the scarcity of training time. To enable a number of operational and science advancements, authors have developed a new approach to expertise distribution in time and among the space and ground personnel. Methods: As part of NASA Operational Ultrasound Project (1998-2003) and the NASA-solicited experiment "Advanced Diagnostic Ultrasound in Microgravity-ADUM" (P.I. -S.D., ongoing), the authors have created a "Balanced Expertise Distribution" approach to perform complex ultrasound imaging tasks on ISS for both operational and science use. The four components of expertise are a) any pre-existing pertinent expertise; b) limited preflight training c) adaptive onboard proficiency enhancement tools; d) real-time ' guidance from the ground. Throughout the pre-flight training and flight time preceding the experiments, the four components are shaped in a dynamic fashion to meet in an optimum combination during the experiment sessions. Results: Procedure validation sessions and feasibility studies have given encouraging results. While several successful real-time remote guidance sessions have been conducted on ISS, Expedition 8 is the first to use an "on-orbit proficiency enhancement" tool. Conclusions: In spite of severely limited training time, daring peer-reviewed research and operational enhancements are feasible through a balanced distribution of expertise in time, as well as among the crewmembers and ground personnel. This approach shows great promise for biomedical research, but may be applicable for other areas of micro gravity-based science

Sargsyan, Ashot↗