Intelligent decision-making system for evaluating severity of psoriasis based on skin image
A skin image and severity technology, applied in the field of intelligent decision-making systems, can solve the problems of psoriasis without considering the subjective feelings of patients, and the inability to objectively and comprehensively evaluate the severity of psoriasis
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0038] Such as figure 1 As shown, this implementation discloses an intelligent decision-making system for assessing the severity of psoriasis based on skin images, including: an image acquisition component, an identification and segmentation component, a PASI score calculation component, a DLQI score acquisition component and an evaluation component, and an image acquisition component : Used to collect skin images of various parts of the body of the subject to be evaluated;
[0039] Identification and segmentation component: used to input the skin images of various parts of the body of the subject to be evaluated into the pre-built tissue region segmentation model, and identify and segment the psoriatic lesions in the skin images of various parts of the body;
[0040] PASI score calculation component: used to calculate the skin lesion area in each part of the body according to the psoriasis skin lesion area segmented in the skin image of each part of the body; and calculate th...
Embodiment 2
[0045] Embodiment 2 is a preferred embodiment of Embodiment 1. It differs from Embodiment 1 in that it introduces the construction and application of an intelligent decision-making system for assessing the severity of psoriasis based on skin images, specifically including:
[0046] Step 1: Data Collection and Preprocessing
[0047] 300,000 clinical images of psoriasis were collected for the realization of the psoriasis intelligent evaluation system. Each image was labeled with labelImg software, and the skin type and lesion location in the image data were marked for feature recognition by the machine. 1000 cases of psoriasis images were scored manually by 3 clinicians, respectively.
[0048] Step 2 Model building and training
[0049] Generate tissue region segmentation model: According to the skin disease image samples and tissue region division labels, apply the self-optimized InceptionResNetV2 model for deep learning training of skin disease image samples, iteratively opti...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
