Multimodal Image Classification System Based on Correlation Learning
A classification system and correlation technology, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as ignoring relevant information and limiting performance
Active Publication Date: 2022-04-08
SHANDONG UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, most of the existing methods independently generate classification results for a single modality, ignoring the correlation information between the two modalities, thus limiting the performance improvement.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0025] It should be pointed out that the following detailed description is exemplary and is intended to provide further explanation to the present application. Unless defined otherwise, all technical and scientific terms used in this disclosure have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0026] It should be noted that the terminology used here is only for describing specific implementations, and is not intended to limit the exemplary implementations according to the present application. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and / or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and / or combinations thereof.
[0027] The present disclosure provides a multimodal image classification system based on correlat...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present disclosure discloses a multimodal image classification system based on correlation learning, including: an acquisition module configured to: acquire mammogram X-ray images to be classified and breast ultrasound images to be classified collected by different types of instruments and equipment from the same patient The image segmentation module is configured to: perform image segmentation on the mammogram image to be classified, and obtain the first ROI; perform image segmentation on the breast ultrasound image to be classified, and obtain the second ROI; The feature extraction module is configured to: extract the first image feature from the first region of interest ROI; extract the second image feature from the second region of interest ROI; the classification output module is configured to: the first image The features and the second image features are simultaneously input into the modality correlation embedding model obtained by pre-training, and the classification result of the breast image of the current patient is output.
Description
technical field [0001] The present disclosure relates to the technical field of image classification, in particular to a correlation learning-based multimodal image classification system. Background technique [0002] The statements in this section merely mention background art related to the present disclosure and do not necessarily constitute prior art. [0003] Today, cancer is a serious public health problem worldwide. Among cancer categories, breast cancer is the second most common form of cancer in women worldwide, with an extremely high mortality rate. Early detection and diagnosis help to increase the cure rate of patients, improve the quality of life of patients, and improve the survival ability of patients. In the clinical diagnosis of breast cancer, medical images play a vital role. Of these existing detection modalities, mammography and ultrasound are the two most commonly used. [0004] Mammography is a more effective way of diagnosing breast cancer than oth...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06V10/764G06V10/25G06V10/26G06V10/40G06T7/00
CPCG06T7/0012G06T2207/10132G06T2207/10116G06T2207/20081G06T2207/20104G06T2207/30068G06T2207/30096G06V10/25G06V10/267G06V10/40G06F18/241
Inventor 尹义龙李冰冰袭肖明孟宪静聂秀山张光
Owner SHANDONG UNIV