Convolutional Neural Networks for Organ Segmentation

Accurate automated organ and disease feature segmentation is a challenge for medical imaging analysis. The pancreas, for example, is a small, soft, organ with low uniformity of shape and volume between patients. Because of the lack of uniform image patterns, there are few features that can be used to aid in automated identification of anatomy and boundaries. Segmentation of high variability features is uniquely difficult for a computer to perform.

High-Resolution and Artifact-Free Measurement and Visualization of Tissue Strain by Processing MRI Using a Deep Learning Approach

This technology includes a system for automatic artifact-free measurement and visualization of tissue strain by MRI at native resolution. The investigation of regional soft tissue mechanical strain can serve as a unique indicator for different related disorders. For example, measurement of myocardial tissue during contraction can help calculate, track, and assess cardiac stress. Currently, methods such as tagging MRI (tMRI) are used for imaging soft tissue deformation. Despite being well validated, methods such as tMRI suffer from low spatial and temporal resolution.

Non-Contact Total Emission Detection Methods for Multiphoton Microscopy: Improved Image Fidelity and Biological Sample Analysis

The technology offered for licensing and for further development is in the field of multiphoton microscopy (MPM). More specifically, the invention pertains to optical designs that can enhance and extend the capabilities of MPM in spectral imaging of biological samples. The unique design of the light collection and the detection optics maximizes the collection of emitted light, thus increasing the signal and hence the signal-to-noise ratio (SNR).

Method for Finding Usable Portion of Sigmoid Curve (the Taylor Method), Improved Assay Readouts, and Enhanced Quality Control/Assurance

CDC researchers have developed algorithmic methods for determining sigmoid curve optimums and calculating component concentrations. Sigmoid curves are commonly generated in bioassays and used to calculate results. Various techniques have been used to define the curve, analyze the observations, and calculate a concentration. This technology is an algorithmic approach to identifying the usable portion of a sigmoid curve.

Real Time Medical Image Processing Using Cloud Computing

The invention pertains to a system for reconstructing images acquired from MR and CT scanners in a robust Gadgetron based cloud computing system. A hardware interface connects clinical imaging instruments (e.g., MR or CT scanners) with a cloud computing environment that includes image data reconstruction and processing software not limited by the computational constraints typical of static hardware with finite processor power.

Non-invasive Pan-Cancer Detection Method

One of four deaths in the United States is due to cancer despite an emphasis on prevention, early detection, and treatment that has lowered cancer death rates by 20% in the past two decades. Further improvements in survival rates are likely to come from improving the limits of detection sensitivity at earlier stages of cancer. New approaches that rely heavily on genomic information, however, may change future testing strategies.

Hybrid Computer Tomography Scanning System

The invention relates to a combination hybrid computer tomography (CT) system that is particularly suited for elucidating stages in pulmonary diseases, notably cystic fibrosis and lung cancer. Improved visualization of lung parenchyma and the margins of lung cysts (non-invasive “virtual biopsy”) may provide sufficient detail to distinguish the types of cystic lesions such that the typical lung tissue pathologic biopsy would not be needed to make a diagnosis.

Single Scan Bright-blood and Dark-blood Phase Sensitive Inversion Recovery (PSIR) Late Gadolinium Enhancement (LGE) for Cardiovascular Magnetic Resonance (CMR) Imaging

This technology includes a technique to improves detection of myocardial scar compared with conventional bright-blood late gadolinium enhancement (LGE) techniques. Dark-blood late gadolinium enhancement (DB-LGE) improves tissue delineation with signal suppression of the blood pool based on T2-preparation pulse that is relatively independent from the blood flow velocities and improves scar detection in patients with known or suspected coronary artery disease.

Isotopes of Alpha Ketoglutarate and Related Compounds for Hyperpolarized MRI Imaging

This technology includes 1-13C-ketoglutarate which can be used for imaging the conversion to hydroxyglutarate (HG) or Gln in cancer cells with an IDH1 mutations by hyperpolarized MRI. The ability to detect the status of IDH1 mutations is clinically prognostic for multiple cancers. These exciting observations are limited by two factors, the major one being that the natural abundance of 13C at position C5 overlaps with 1-13C-2-hydroxyglutarate peak, which limits the sensitivity of analysis and prevents simultaneous observations of HG and Gln formation.

DeePlexing – Extending Imaging Multiplexity Using Machine Learning

Spatial proteomics and transcriptomics are fast-emerging fields with the potential to revolutionize various branches of biology. In the last five years, various multiplex immunofluorescence and immunohistochemistry imaging methods have been developed to stain 5-60 different protein markers in a given tissue. Nonetheless, most of these techniques are iterative and can image a maximum of 3-8 markers in a single cycle, resulting in processing time of several hours to days.

Subscribe to Software / Apps