In this work, we present a machine learning method to guide an ultrasound operator towards a selected area of interest. Unlike other automatic medical imaging methods, ultrasound imaging is one of the few imaging modalities where the operator’s skill and training are critical in obtaining high quality images. Additionally, due to recent advances in affordability and portability of ultrasound technology, its utilization by non-experts has increased. Thus, there is a growing need for intelligent systems that have the ability to assist ultrasound operators in both clinical and non-clinical scenarios. We propose a system that leverages machine learning to map real time ultrasound scans to transformation vectors that can guide a user to a target organ or anatomical structure. We present a unique training system that passively collects supervised training data from an expert sonographer and uses this data to train a deep regression network. Our results show that we are able to recognize anatomical structure through the use of ultrasound imaging and give the user guidance toward obtaining an ideal image.
Net-centric warfare in todays dynamically changing military environments and the need for low-cost gigabit
intra-city communication present severe challenges for current free-space optical systems. Enabled by high-speed
electronics and advances in wavefront control, we develop an architecture that provides free-space coherent
optical links with information capacity, security, network robustness and power management performance that
exceed the current state-of-the-art, including commercially deployed systems, R&D test-beds, and alternative
theoretical architectures proposed. The deleterious effects of the turbulent atmosphere are mitigated with several
diversity transmitters and receivers. We allow the phase and the amplitude of each transmitter to be controlled
independently and assume, through coherent detection, that the phase and amplitude of the received wave
is measured. Thus we can optimally allocate transmit power into the diffraction modes with the smallest
propagation losses to increase channel capacity and mitigate turbulence-induced outages. Additionally, spatial
mode modulation and rejection provides robust communication in the presence of denial of service via interference
by adversaries with a priori knowledge of the system architecture. Some possible implementations of this system
are described. New results, including asymptotic singular value distribution, expected bit error rate, interference
performance, and performance in the presence of inhomogeneous turbulence, are given. Finally, performance of
this system is compared with the performance of optical diversity systems without wavefront control and optical
systems without diversity, both current state-of-the-art systems.
Present-day data networks are being challenged by the relentless growth of bandwidth demand. Most of this future growth, however, is not arising from more users with the same application bandwidth demands, but rather from the dramatic increase in bandwidth demand of emerging applications. The compounding of these two trends has set the stage for optical networking technology to make significant contributions in next-generation data network architecture. In this talk, we will explore key research problems of optical network architecture (such as flow switching) that, if properly exploited, will enable significant growth and cost-effective scalability of next-generation data networks.
This paper will address the application of optical free space communication to distributed network architecture. High
speed optical links in digital and/or analog forms enable new satellite and land based communication and sensing system
architectures with significantly enhanced system performance over conventional single platform architectures. These
applications include: RF communications supported by multiple spatially separated satellites or cellular-like base
stations performing beam forming and nulling and long baseline interferometry over multiple platforms for sensing. We
will examine both the physical transport design of the optical free space links and their architecture implications.
The fades and background noise that are seen by the receiver(s) in clear atmospheric optical communication can be
mitigated with diversity and coherent receivers. However, in certain applications, one may need to be concerned with
not only fades/outages, but also with an interferer that may be actively trying to interfere with our communication by
sending his own optical signal towards our receiver(s). It is important to understand how our optical system performs in
the presence of such an interferer. In this paper, we describe two potential interferer strategies when our communication
system uses Diversity Direct Detection and two potential strategies when our system uses Diversity Homodyne
Detection. We also derive and plot the performance of our systems in these scenarios, both in the absence of and in the
presence of clear atmospheric turbulence. We find that if the interferer optimizes the fraction of bits over which it
spreads its power, it degrades the performance of our Diversity Direct Detection or Diversity Homodyne Detection
significantly more than if it were simply on all the time. Moreover, we find that the performance of Homodyne
Detection with no diversity and Direct Detection with no diversity are almost the same in the presence of analogous
interferers, and that diversity improves Homodyne Detection's performance while worsening Direct Detection's
performance.
With the increasing technical maturity in fiber, wireless and satellite communication technologies, new horizons are becoming feasible for future broadband networks, providing economical data rates well in excess of Gbps for stationary and mobile users as well as novel applications these advanced network services will permit. This talk explores the future architecture possibilities of such a network using new and radical technology building blocks such as: free space laser communications, multiple access multi-beam data satellite communications, novel all-optical network transport/switching and analog transmission and processing over optical carriers that support coherent distributed platform sensing and communications. We will articulate why we have to design this new network across layers from the Physical Layer to the Network and Transport Layers (even the Application Layer). Not only can future network performance and cost undergo quantum-leap improvements; such a network can have profound transforming effects on space and terrestrial system architectures for sensing, healthcare, early warning systems, disaster relief, research collaborations and other new commercial applications.
Optical space communications is now a reality. It will be a key building block for wide-area space data networks of the future. This new technology will provide quantum-leap improvements to satellite network performance and cost and have profound transforming effects on space system architectures and applications.
Current optical networks are migrating towards WDM-based transport between traditional electronic multiplexers/demultiplexers, routers and switches. The ONRAMP Program addresses technologies, architectures and designs of future high performance data networks. This paper focuses on WDM aware IP networks with emphasis on access networks. The access network can be divided into the feeder network and the distribution network. Generally bandwidths of fiber closer to the end user is less precious. Thus in the distribution network, we propose the use of all passive optical components and remotely pumped amplifiers trading bandwidth assignment efficiencies for lower costs. We will examine the design of the distribution network from the view of services to be supported by the network and its desirable properties. Generic physical topologies will be considered and implementation optics presented.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.