Skin cancer classification method based on optical intensity and gradient of OCT imaging image

A classification method, skin cancer technology, applied in the field of biomedical image processing
CN112116027APending Publication Date: 2020-12-22NINGBO UNIVERSITY OF TECHNOLOGY
0 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
NINGBO UNIVERSITY OF TECHNOLOGY
Publication Date
2020-12-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a skin cancer classification method based on the optical intensity and gradient of an OCT imaging image, and the method comprises the steps: (1) collecting a skin cancer imagethrough an OCT device, and normalizing the intensity in the OCT image into [0, 1]; (2) performing noise reduction on the OCT image through noise reduction processing; (3) extracting optical intensitycharacteristic parameters; (4) calculating to obtain the discrete value of each parameter of the marked sample, and then obtaining the difference and ROC analysis of each characteristic parameter in the marked control group through a mathematical statistics method to obtain a boundary value; and (5) calculating to obtain the discrete value of each parameter of the unknown sample, comparing the discrete value with the boundary value in the step (4), and classifying the unknown sample according to the comparison result. According to the invention, normal skin tissues, melanoma and melanin nevuscan be quickly and accurately judged; discomfort and trauma brought to a patient by an invasive method of skin biopsy are avoided.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a skin cancer classification method based on the optical intensity and gradient of an optical coherence tomography (OCT) imaging image, belonging to the field of biomedical image processing. Background technique

[0002] Skin cancer is one of the most common cancers worldwide. According to the World Health Organization, more than 2 million cases of skin cancer are diagnosed each year. In clinical practice, skin biopsy is the gold standard for diagnosing skin cancer. However, skin biopsy is an invasive procedure that can cause patient discomfort. Therefore, non-invasive methods have been adopted to eliminate the shortcomings of biopsy in skin cancer diagnosis, including dermoscopy, confocal microscopy, Raman spectroscopy and optical coherence tomography (OCT). These patterns are able to generate images to help dermatologists diagnose different types of skin disorders. Dermoscopy not only allows a visual inspection of the ski...

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