Image retrieval method, device, readable storage medium and electronic equipment

Abstract

The invention provides an image retrieval method and device, a readable storage medium and electronic equipment. The method comprises the steps of obtaining a to-be-retrieved image and edge segmentation information of a focus in the to-be-retrieved image; according to the edge segmentation information of the lesion, extracting machine learning features of the lesion from the to-be-retrieved image,and obtaining a machine learning vector; according to the edge segmentation information of the lesion, extracting an imaging omics feature of the lesion from the to-be-retrieved image to obtain an imaging omics vector; combining the machine learning vector and the image omics vector to obtain a feature vector corresponding to the focus; and outputting a retrieval result of a similar focus similarto the focus according to the feature vector corresponding to the focus. According to the image retrieval method, the similar lesions can be quickly retrieved, by combining the machine learning vector and the image omics vector, feature extraction of the lesions is more comprehensive, the retrieved similar lesions are more accurate, the retrieval accuracy is improved, and then doctors can be helped to make more reasonable diagnosis and treatment suggestions.

Description

technical field [0001] The invention relates to the technical field of image retrieval, in particular to an image retrieval method, device, readable storage medium and electronic equipment. Background technique [0002] Pathologically similar lesions often have similar properties. Therefore, finding the pathological results, diagnosis and treatment methods, etc. of lesions with similar shapes, and making horizontal comparisons usually help doctors to have a clearer and more comprehensive judgment on the current lesions, thereby Diagnosis and treatment opinions can be given more accurately. [0003] For the search of similar lesions, the traditional solution is to search for keywords in the database to find matching results with the same keywords, but the doctor’s cognition of the characteristics of the lesions may be biased, resulting in inaccurate keywords and inaccurate search results. Accurate, resulting in diagnostic bias. Moreover, using a large number of keywords for...

AI Technical Summary

Problems solved by technology

[0003] For the search of similar lesions, the traditional solution is to search for keywords in the database to find matching results with the same keywords, but the doctor’s cognition of the characteristics of the lesions may be biased, resulting in inaccurate keywords and inaccurate search results. Accurate, causing diagnostic bias

Moreover, using a large number of keywords for description is time-consuming and labor-intensive, which affects work efficiency

Images