Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Seven-type skin tumor detection method applied to web

A technology for skin tumors and detection methods, which is applied in applications, diagnostic records/measurements, sensors, etc., can solve problems such as insufficient medical resources, and achieve the effects of simplifying the process, expanding the data range, and running quickly

Active Publication Date: 2019-08-16
HANGZHOU DIANZI UNIV
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the serious shortage of medical resources at present, the present invention proposes a detection method for seven types of skin tumors applied to mobile phones

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Seven-type skin tumor detection method applied to web
  • Seven-type skin tumor detection method applied to web
  • Seven-type skin tumor detection method applied to web

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0026] The hardware environment used for implementation is: CPU Intel(R) Xeon(R) CPU E5-2630v4@2.20GHz, GPU is NVIDIA K80, and the operating environment is python2.7 and TensorFlow.

[0027] The deep convolutional neural network Inception-ResNetV2 is adopted, the global average pooling layer is used to replace the fully connected layer, and the space is decomposed into asymmetric convolution, which greatly reduces the amount of parameters and speeds up the calculation.

[0028] The excellent performance of this network is mainly due to the extensive use of dimensionality reduction processing. The convolution of large-size filters (such as 5*5, 7*7) introduces a large amount of calculations. Using two 3*3 convolutions in series instead of a 5*5 convolution can reduce the amount of calculations, and the 3 The *3 convolution kernel is decomposed ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a seven-class skin tumor detection method applied to Web, which combines the weight of a model with a Web end based on a model migration technology taking Tensorflow as an intermediary agent, so that the model can normally and quickly run in a browser environment familiar to a user, and meanwhile, a model result is visualized. The model uses an optimized Inception-ResNetV2classification network to propose a skin tumor classification method for skin tumor images. Seven types of skin tumors can be detected through the method so that the ideal effect is achieved, and doctors can be effectively assisted in diagnosis. According to the Web end development method for detecting the seven types of skin tumors, the process of detecting the skin tumors is simplified, the obtained probability result is responded to the client browser, rendering visualization is conducted through the browser, and therefore a doctor and a patient can obtain the detection result in real timeonly by simply operating the Web end.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and relates to a method for detecting seven types of skin tumors applied to a web terminal. Background technique [0002] Skin cancer is a malignant tumor that occurs on the surface of the skin. It is also one of the most common cancers. There are about 2 to 3 million new cases of cancer worldwide every year, resulting in more than 50,000 deaths. However, as long as the malignant skin tumor can be diagnosed at an early stage, regardless of surgery, radiotherapy or other treatment methods, it has a good curative effect on malignant skin tumors, and the cure rate can be over 90%. [0003] The deep learning algorithm has attracted people's attention since its success in 2006. Compared with non-deep learning algorithms in many fields, the overall effect is 20%-30% higher. In recent years, breakthroughs in algorithms have emerged one after another, making the deep learning model more and more p...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62A61B5/00
CPCA61B5/444A61B5/7267G06V2201/03G06F18/214
Inventor 端阳王飞孙玲玲吕岱霖李智星
Owner HANGZHOU DIANZI 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
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com