Cervical lesion prediction system based on multi-modal feature level fusion

Abstract

The invention discloses a cervical lesion prediction system based on multi-modal feature level fusion. The system comprises a computer memory, a computer processor and a computer program which is stored in the computer memory and can be executed on the computer processor, a cervical lesion prediction model is stored in the computer memory and comprises an acetic acid image feature extraction network, an iodine image feature extraction network and an auxiliary module used for fusing extracted features. When the computer processor executes a computer program, the following steps are realized: receiving an acetic acid image and an iodine image in colposcopy, and cutting out an area containing cervix uteri; respectively inputting the acetic acid image and the iodine image into an acetic acid image feature extraction network and an iodine image feature extraction network in the cervical lesion prediction model, respectively inputting the acetic acid image and the iodine image into respective auxiliary modules after feature extraction, carrying out feature fusion, and outputting a prediction result through calculation. According to the system, the prediction result can be more accurate so as to assist a doctor in making correct diagnosis and judgment.

Description

technical field [0001] The invention belongs to the field of medical image processing, in particular to a cervical lesion prediction system based on multimodal feature-level fusion. Background technique [0002] Cervical cancer is the second most common type of cancer in the female reproductive system, seriously affecting the life and quality of life of patients. Cervical disease screening can help prevent cervical cancer by detecting squamous intraepithelial lesions, which generally fall into two categories: low-grade squamous intraepithelial lesions (LSIL) and high-grade squamous intraepithelial lesions (HSIL). In clinical practice, an important goal of screening is to distinguish cervical high-grade squamous intraepithelial lesion (HSIL) from normal / low-grade squamous intraepithelial lesion (LSIL) for early detection of cervical cancer, because most (60%) low-grade squamous intraepithelial lesions will spontaneously resolve, while high-grade squamous intraepithelial lesi...

AI Technical Summary

Problems solved by technology

[0006] However, the above-mentioned methods for identifying cervical lesions only use one kind of image (only acetic acid image or iodine image) during use, which cannot fully capture the characteristics of cervical lesions.

Images