Medical image recognition method, system, equipment and medium

Abstract

The invention provides a medical image recognition method, system and device and a medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring a to-be-identified medical image, age information and gender information transmitted by a target user; performing human body part prediction identification and skin prediction identification on the to-be-identified medical image; if the abnormal skin exists in the to-be-identified medical image, continuing abnormal category prediction, and outputting a plurality of predicted abnormal categories; and according to the human body part prediction identification result, the age information and the gender information, rechecking the plurality of prediction abnormity categories, and feeding back the rechecked prediction identification result to the target user; and if the skin does not exist in the medical image to be recognized or the normal skin exists in the medical image to be recognized, directly feeding back an image prediction recognition result to the target user. According to the method, firstly, the to-be-identified medical image is subjected to multi-stage prediction identification, and then the image prediction identification result is rechecked, so that the accuracy of performing abnormal category prediction on the to-be-identified medical image can be improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a medical image recognition method, system, device and medium. Background technique [0002] Skin disease is one of the most common diseases. According to statistics, less than 15% of people in China actually have healthy skin. To deal with skin problems, more than 60% of people prefer self-medication or endure the troubles caused by skin diseases. Coupled with the shortage and imbalance of offline medical resources, most people cannot receive timely and effective treatment, which greatly increases the risk of exacerbation of corresponding diseases. [0003] With the development of artificial intelligence (AI) technology, more and more AI technologies have been practically applied in various fields. In recent years, some institutions have developed artificial intelligence systems that can predict and identify some common skin diseases. However, when the ...

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned shortcomings of the prior art, the object of the present invention is to provide a medical image recognition method, system, device and medium, which are used to solve the problem of inaccurate accuracy of the artificial intelligence system in the prior art when predicting and identifying medical images. Unable to give any prompt information or help information for the predicted recognition results

Images