Lumbar vertebra image classification and recognition system and device based on multi-modal image and medium

Abstract

The invention relates to a lumbar vertebra image classification and recognition system and device based on a multi-modal image and a medium. The system comprises a data acquisition module, a key information extraction module, a multi-modal image detection module and a classification and recognition module. The data acquisition module is used for acquiring a case text of a patient and multi-modal image data in the same period, and respectively sending the case text and the multi-modal image data to the key information extraction module and the multi-modal image detection module; the key information extraction module is used for carrying out key information extraction on the received case text and sending the extracted case key information to the classification identification module; the multi-modal image detection module is used for performing registration and preliminary positioning detection on the acquired multi-modal image data, and sending a preliminary positioning detection result to the classification identification module; and the classification and identification module is used for carrying out accurate segmentation and identification on a focus area in the lumbar vertebra image according to the case key information and the preliminary positioning detection result. The method can be widely applied to the field of image recognition.

Description

technical field [0001] The invention relates to a lumbar spine image classification and recognition system, equipment and medium based on multimodal images, and belongs to the technical field of image recognition. Background technique [0002] Lumbar degenerative diseases can cause nerve compression, resulting in lower extremity pain, claudication and other neurological symptoms and dysfunction. The lumbar spine is composed of 5 vertebral bodies, and nerves emanate from each vertebral body. To achieve precise treatment of lumbar degenerative diseases, it is first necessary to determine the exact location of the neuropathy, which requires extremely high nerve localization and diagnosis capabilities. The diagnosis of nerve localization in lumbar degenerative diseases is based on the comprehensive diagnosis of medical history, physical examination and imaging examination. Among them, the medical history and physical examination part need to be collected by the clinician and th...

AI Technical Summary

Problems solved by technology

Although artificial intelligence has been used in some tumor imaging, cardiovascular and cerebrovascular imaging, pathological diagnosis, outpatient data analysis, and intelligent identification of some orthopedic diseases such as fractures and children's bone age, however, due to the various manifestations of lumbar degenerative diseases, although domestic and foreign Some exploratory work has been done, but it mainly uses traditional radiomics to analyze images or machine learning methods to analyze clinical indicators for identification and prognosis prediction, and there are few reports on deep learning.

[0004] In addition, the current research is all aimed at the recognition of single modality images (X-ray, CT or MR). However, in actual clinical practice, doctors often need multi-dimensional information such as comprehensive medical history, clinical manifestations, signs and imaging data. Judgment, the recognition results based on a single modality image may have certain deviations

At the same time, even for single-modal image recognition, different imaging detection methods have different detection effects for different tissues. For lumbar degenerative diseases, not only the deformation of the lumbar spine must be considered, but also the compression of soft tissues and nerves should be observed. At present, there is still no artificial intelligence comprehensive recognition model that can integrate multi-modal image data

Images