Optical dynamic imaging system
    51.
    发明授权

    公开(公告)号:US10321826B2

    公开(公告)日:2019-06-18

    申请号:US15261032

    申请日:2016-09-09

    Inventor: Chang-Hee Won

    Abstract: The dynamic positioning of sensors, which exploit the mechanical and physiological changes in tissues, can significantly increase the performance in characterization of tumors. Here, we disclose the Optical Dynamic Imaging (ODI) System for tumor characterization. ODI System estimates size, depth, elastic modulus and optical properties of embedded objects. The ODI System consists of a tactile imaging sensor (TIS), and a near infrared diffuse spectral imaging. To obtain mechanical properties of the target, we compress the region of interest with the probe, then the light from the probe is scattered and captured by the camera as a tactile image. On the other hand, using a light source and the camera as a detector, we obtain the diffuse spectral images. From these images, we compute the absorption coefficient of the embedded tumor phantom. We move the source-detector simultaneously and collect optical information. We termed this maneuver as dynamic positioning. Optical Dynamic Imaging System also provides position and orientation of the light source and the detectors. The combination of the absorption coefficient and tactile data along with location information improves the size, depth, and elastic modulus estimation.

    System and Method for Automatic Interpretation of EEG Signals Using a Deep Learning Statistical Model

    公开(公告)号:US20190142291A1

    公开(公告)日:2019-05-16

    申请号:US15560658

    申请日:2016-03-23

    Abstract: A system and method for automatically interpreting EEG signals is described. In certain aspects, the system and method use a statistical model trained to automatically interpret EEGs using a three-level decision-making process in which event labels are converted into epoch labels. In the first level, the signal is converted to EEG events using a hidden Markov model based system that models the temporal evolution of the signal. In the second level, three stacked denoising autoencoders (SDAs) are implemented with different window sizes to map event labels onto a single composite epoch label vector. In the third level, a probabilistic grammar is applied that combines left and right context with the current label vector to produce a final decision for an epoch. A physician's report with diagnoses, event markers and confidence levels can be generated based on output from the statistical model. Systems and methods for dealing with channel variation or a missing EEG electrode valve are also disclosed. A feature-space boosted maximum mutual information training of discriminative features or an iVectors technique to determine invariant feature components can be implemented for generating a plurality of EEG event labels. An optional GUI allows scrolling by EEG events.

    Detection of HIV-1-associated neurocognitive disorders

    公开(公告)号:US10161925B2

    公开(公告)日:2018-12-25

    申请号:US15129353

    申请日:2015-03-24

    Abstract: Provided is a method of detecting mild neurocognitive disturbance (MNCD) or HIV associated dementia (HAD) in a patient comprising detecting the level of acetyl spermine and/or acetyl spermidine from a cerebrospinal fluid test sample of the patient; and comparing the level of acetyl spermine and/or acetyl spermidine in the test sample to the level of the acetyl spermine and/or acetyl spermidine in a cerebrospinal fluid control sample or to a control value for lack of neurocognitive impairment, MNCD or HAD; wherein an elevated level of acetyl spermine and/or acetyl spermidine in the test sample as compared to the level in the control sample or a control value for lack of neurocognitive impairment, or a level of acetyl spermine and/or acetyl spermidine that is similar to that of a control value for MNCD or HAD, indicates that the patient suffers from MNCD or HAD. Also provided are methods for measuring the progression of an HIV-1-associated neurocognitive disorder, as well as methods for staging such a disorder.

Patent Agency Ranking