A multi-modal medical image retrieval method based on multi-image regularization deep hashing

Abstract

The invention requests to protect a multi-image regularization depth hash multi-modal medical image retrieval method. The method specifically comprises the following steps of: simultaneously extracting features of a multi-modal medical image group through a multi-channel depth model; Correspondingly constructing a plurality of graph regularization matrixes according to the characteristics of the multi-modal medical image group; fusing Multiple graph regularization matrixes, and obtaining Hash codes of the multi-mode medical image set through modal self-adaptive restricted Boltzmann machine learning; solving The distance between a single modal data hash code and a multi-modal medical image group hash code through Hamming distance measurement, carrying out sorting according to an ascending order, and selecting and returning n groups of multi-modal medical images with the minimum distance to a user, so that multi-modal medical image retrieval is realized. According to the method, a doctorcan be helped to quickly find data of other multiple modes through data of a certain mode in multi-mode medical images such as ultrasonic images, dispute end texts and nuclear magnetic resonance images, medical diagnosis of the doctor is facilitated, the workload of the doctor is reduced, and the working efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and in particular relates to a multi-image regularized deep hash method to realize multi-modal medical image retrieval. Background technique [0002] Multimodal medical image retrieval technology refers to retrieving matching medical images of the same modality and different modalities from the multimodal medical image database according to the input data of a certain modality. The existing multimodal retrieval technology mainly has three modules: text-based image retrieval technology, text-based video retrieval technology, and image-based text retrieval technology. Existing multimodal retrieval technologies mostly retrieve each other between two modalities. However, the increasing number of multimodal medical images makes the existing technology unable to meet the user's needs for mutual retrieval between any modality data. [0003] Cross-modal hash retrieval algorithm has beco...

AI Technical Summary

Problems solved by technology

However, there are still some technical defects: (1) Most of the existing methods learn the hash code by extracting the manual features of the data. Hash codes have a great impact on retrieval accuracy; (2) most existing cross-modal hash algorithms based on deep learning only realize mutual retrieval between two modal data; (3) existing methods When implementing the mapping from data to hash codes, the inherent manifold structure of the data is not considered, so that the learned hash codes also fail to maintain the local manifold structure of the data, thus affecting the retrieval accuracy.

[0005] The problem to be solved by the present invention is that manual features cannot meet high-precision retrieval requirements, cross-modal hash algorithms are mostly dual-modal mutual retrieval, and the mapping between data and hash codes cannot maintain the local manifold structure of data, etc. insufficient

Images