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

667 results about "Skin lesion" patented technology

A skin lesion is a part of the skin that has an abnormal growth or appearance compared to the skin around it. Two categories of skin lesions exist: primary and secondary. Primary skin lesions are abnormal skin conditions present at birth or acquired over a person’s lifetime.

Digital skin lesion imaging system and method

InactiveUS7162063B1Easy to useReadily accurately identifyImage enhancementImage analysisDisplay deviceImage scale
New or significantly changed skin lesions are detected by providing digital baseline image data of an area of a subject's skin by placing a calibration piece on the area and then positioning a digital camera to frame the area within a field of view of the camera and digitally photographing the area to produce a digital baseline image of the area. The digital baseline image is downloaded from the camera to a computer, which digitally filters the baseline image to produce a partially transparent baseline image scaled to fit over a viewfinder display of the camera. The filtered baseline image is printed on a transparent sheet to produce template. Substantially later, a calibration piece is placed on the area, and the template is placed over the viewfinder display of the camera. The camera is positioned to frame that area within the field of view so as to align a live image of the area with the baseline image on the template. The area is photographed to produce a digital current image thereof. The current image is downloaded to the computer, which is operated to alternately display the aligned current image data and the baseline image data to allow visual identification of lesions which changed enough in the “alternating image comparison display” to identify a new or significantly growing lesion.
Owner:WESTERN RES

Three-dimensional thermal imaging for the detection of skin lesions and other natural and abnormal conditions

A thermal imaging system includes a data processing system and a geometrical scanning system constructed to communicate with the data processing system. The geometrical scanning system is adapted to scan at least a section of a surface of a subject under observation. The thermal imaging system also includes an infrared imaging system constructed to communicate with the data processing system. The infrared imaging system is adapted to image at least a portion of the section of the surface of the subject under observation. The data processing system is configured to receive data from the geometrical scanning system and to construct a surface map of the section of the surface of the subject under observation and to identify geometrical markers on the surface map based on the data from the geometrical scanning system. The data processing system is also configured to receive data from the infrared imaging system and to construct a thermal map of the portion of the section of the surface, to identify thermal markers on the thermal map based on the data from the infrared imaging system, and to register the thermal map to the surface map based on a correspondence between at least some of the geometrical and thermal markers. The data processor is configured to correct temperatures of the thermal map based on the surface map subsequent to the registering.
Owner:THE JOHN HOPKINS UNIV SCHOOL OF MEDICINE

Deep-learning-based image identification method of melanoma of skin cancer

The invention discloses a deep-learning-based image identification method of the melanoma of a skin cancer. The method comprises: establishing a skin lesion dermatoscope image database; carrying out data preprocessing and quality assessment and screening; carrying out cascaded connection of deep convolution neural networks, and introducing transfer learning and a classifier. At a training stage, enhancement or screening is carried out on original data; and after inputting of positive and negative samples, sample expansion and overfitting prevention are carried out. At the preprocessing stage,data enhancement is added, cascaded connection of two deep convolution neural networks is carried out; transfer learning of existing pre-trained features at a natural image to an identification network is carried out; and then classification prediction is carried out by using the classifier and fine adjustment of network parameters is carried out based on network convergence and prediction situations. Therefore, the accuracy of skin lesion classification is improved; the restriction of manual feature selection is avoided; the adaptability is improved; and thus the deep-learning-based image identification method has the certain significance in a medical skin disease image analysis.
Owner:HANGZHOU DIANZI UNIV +1

Short peptides useful for treatment of ischemia/reperfusion injury and other tissue damage conditions associated with nitric oxide and its reactive species

This invention discloses isolated short peptides comprising the amino acid sequence Cys-Glu-Phe-His (CEFH) and analogs thereof as well as compositions comprising CEFH peptides and analogs thereof. The CEFH peptides disclosed herein are effective in mediating the denitration of 3-nitrotyrosines (3-NT) in cellular proteins thereby preventing tissue damage associated with excess nitric oxide (NO) and its reactive species. The CEFH peptides disclosed herein are useful in the treatment of ischemia/reperfusion (I/R) injury of various tissues (e.g., I/R injury of heart muscle associated with heart attack or cardiac surgery, I/R injury of brain tissue associated with stroke, I/R injury of liver tissue, skeletal muscles, etc.), septic shock, anaphylactic shock, neurodegenerative diseases (e.g., Alzheimer's and Parkinson's diseases), neuronal injury, atherosclerosis, diabetes, multiple sclerosis, autoimmune uveitis, pulmonary fibrosis, oobliterative bronchiolitis, bronchopulmonary dysplasia (BPD), amyotrophic lateral sclerosis (ALS), sepsis, inflammatory bowel disease, arthritis, allograft rejection, autoimmune myocarditis, myocardial inflammation, pulmonary granulomatous inflammation, influenza- or HSV-induced pneumonia, chronic cerebral vasospasm, allergic encephalomyelitis, central nervous system (CNS) inflammation, Heliobacterium pylori gastritis, necrotizing entrerocolitis, celliac disease, peritonitis, early prosthesis failure, inclusion body myositis, preeclamptic pregnancies, skin lesions with anaphylactoid purpura, nephrosclerosis, ileitis, leishmaniasis, cancer, and related disorders.
Owner:NEW YORK UNIVERSITY

A dermatoscope image segmentation method based on a multi-branch convolutional neural network

The invention discloses a dermatoscope image segmentation method based on a multi-branch convolutional neural network. The method comprises the following steps of 1, collecting training samples; 2, expanding the image; 3, designing a multi-branch convolutional neural network model; 4, training the multi-branch convolutional network; 5, generating a skin damage distribution probability graph; 6, obtaining a segmentation result. The method has the advantages that the training data set is effectively expanded by using the corresponding image transformation according to the data characteristics ofthe dermatoscope image, so that the network training is effective, and the generalization performance is high; the convolutional neural network comprises a plurality of branches, rich semantic information and detail information are fused, compared with a common network, the skin lesion edge can be better recovered, and a more accurate skin lesion segmentation result is obtained; the method is a full-automatic segmentation scheme, only the dermatoscope image to be segmented needs to be input, the segmentation result of the image can be automatically given through the scheme, the additional processing is not needed, and the method is efficient, simple and convenient.
Owner:BEIHANG UNIV
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