Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

124 results about "Retinal Disorder" patented technology

An abnormal structure or function of the retina and its associated tissues.

Multi-phasic microphotodetector retinal implant with variable voltage and current capability and apparatus for insertion

A visible and infrared light powered retinal implant is disclosed that is implanted into the subretinal space for electrically inducing formed vision in the eye. The retinal implant includes a stacked microphotodetector arrangement having an image sensing pixel layer and a voltage and current gain adjustment layer for providing variable voltage and current gain to the implant so as to obtain better low light implant performance than the prior art, and to compensate for high retinal stimulation thresholds present in some retinal diseases. A first light filter is positioned on one of the microphotodetectors in each of the image sensing pixels of the implant, and a second light filter is positioned on the other of the microphotodetectors in the image sensing pixel of the implant, each of the microphotodetectors of the pixel to respond to a different wavelength of light to produce a sensation of darkness utilizing the first wavelength, and a sensation of light using the second wavelength, and a third light filter is positioned on a portion of the voltage and current gain adjustment layer that is exposed to light, to allow adjustment of the implant voltage and current gain of the device by use of a third wavelength of light.
Owner:OPTOBIONICS

Compositions of very long chain polyunsaturated fatty acids and methods of use

The present invention relates to processes for production of Very Long Chain Polyunsaturated Fatty Acids (VLC-PUFAs). The present invention also relates to compositions (e.g., nutritional supplements, food products, and pharmaceutic compositions) containing such VLC-PUFAs. In one embodiment, the present invention is directed to methods for biosynthesis and production of the VLC-PUFAs described herein (particularly C28-C40 PUFAs, also referred to herein as supraenes or supraenoics) by the expression, in a production host cell, of the full or partial sequence(s) of Elovl4 DNA / mRNA nucleic acids or ELOVL4 protein sequences encoded thereby, from any species (prokaryotic or eukaryotic) for use in the biosynthesis, production, purification and utilization of VLC-PUFAs in particular by the elongation of C18-C26 saturated fatty acids and PUFAs. The composition of the invention comprises, in various embodiments, a dietary supplement, a food product, a nutritional formulation, a pharmaceutical formulation, a humanized animal milk, an infant formula, and a cosmetic item and for example. A pharmaceutical formulation can include, but is not limited to: a composition for enhancing neural development and function, a drug for treatment of neurodegenerative disease, an ocular disorder, a retinal disorder, age related maculopathy, a fertility disorder, particularly regarding sperm or testes, or a skin disorder.
Owner:THE BOARD OF RGT UNIV OF OKLAHOMA

Convolutional neural network weight optimization method for retinal lesion classification

The invention relates to the field of medical information intelligent processing, in particular to a convolutional neural network weight optimization method for retinal lesion classification. The method comprises the following steps: firstly, acquiring a fundus image training set and a corresponding multi-lesion label; searching an optimal initial weight value through a single-population leapfrogalgorithm, then constructing a convolution layer, a pooling layer and a full connection layer in the convolutional neural network, and taking the optimal initial weight value as a parameter of first forward propagation calculation; performing cross entropy loss calculation and summation on the four predicted values of the four lesions in the retina and the true value to obtain a loss value, judging whether the loss value is abnormal or not, if the loss value is abnormal, generating a frog group around the weight of the previous forward propagation, and searching an optimal frog updating network weight; otherwise, updating the network weight by adopting a gradient descent algorithm; and finally, optimizing the final weight. According to the method, the accuracy of fundus image multi-lesiondetection can be effectively improved, and the method has high application value for retinal diseases and adjuvant therapy.
Owner:NANTONG UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products