Medical image classification device and its construction method based on multi-modal deep learning

Abstract

The invention discloses a deep learning-based medical image classification device and a construction method thereof. The device includes an input module, a rough segmentation module, a subdivision module, an integration module and a display module, wherein the rough segmentation module includes a regional convolutional neural network RCNN, and the subdivision module includes a first cyclic convolutional neural network rCNN1, which recognizes an original image, The oriented gradient histogram model that converts the image into a HOG map and the support vector machine SVM, Gaussian mixture model GMM and the second recurrent convolutional neural network rCNN2 for recognizing HOG, the integration module includes a comprehensive classifier such as GMM, which is used to subdivide The recognition confidence scores of each region output by the four classifiers of the module are input as an input vector after weighting, and the final recognition confidence scores of each region are obtained.

Description

Technical field [0001] The present invention relates to the field of depth learning and image recognition, and more particularly to a classification device of a medical image based on multi-mode depth learning and its construction method thereof. Background technique [0002] Deep learning has been successfully applied in the field of single image classification and image search, and has developed rapidly in the medical field, such as Google learning through deep learning of CT images of breast cancer, making breast cancer artificial intelligence investigation accuracy or exceeding tumor Doctor. However, deep learning due to the unknown number of unknown parameters of their own models, thus the requirements of training data are very huge. On the other hand, the cost of labeled the cost of medical images is high and quantified, in particular the data evolved by the disease requires data from different stages of the patient, often requiring data to collect data in different medical...

AI Technical Summary

Problems solved by technology

Although these schemes can carry out deep learning on the characteristics of lung diseases, they do not effectively use the gradient vector information of the diseased tissue itself and the correlation and relative changes with the surrounding healthy tissue (revealing the interconnection of biological phenomena) to improve the performance of deep learning. Specificity and robustness, so especially in the case of limited training image data, even if a trained neural network is obtained, its robustness and accuracy for disease course classification are unsatisfactory, and it is difficult to Approach or surpass doctors in practical application

[0006] Deep learning is based on big data. However, medical images are not easy to obtain massive data due to factors such as information sharing of medical institutions and patient privacy. At the same time, most of the hospital data are terminal patients who have been diagnosed, and patients often change medical institutions as the disease progresses. , so the images and data of the early and complete course of the disease are even rarer, which greatly limits the application of deep learning in the field of medical image recognition

Images