Detection of Precancerous Cervical Cancer Using Dual-Source Image Fusion Network

White light medical images are often used to detect early symptoms of cervical cancer, but they have limitations in the diagnosis and grading of early symptoms of cervical cancer. White light images can only provide limited information and it is difficult to fully capture the complex characteristics of cervical cancer,such as metabolic changes and microenvironmental differences. Therefore, it is difficult to judge the severity of symptoms and it is easy to lead to misdiagnosis. This paper proposes a dual-source medical image fusion network PFM (PConvFusionModel) based on attention mechanism for the diagnosis and classification of early cervical cancer symptoms. The network processes two image sources, white light images and fluorescence images, and extracts the morphological features of white light images and the tissue and metabolic features of fluorescence images respectively. PFM is designed based on PConv architecture and includes four core components: feature extraction module, attention enhancement module, dual-source feature fusion module and multi-head self-attention decision module. The network first obtains the original features of the two images through the PConv feature extraction module, then uses the channel attention and spatial attention modules to enhance the features of the two types of images respectively, then splices the enhanced features, and further integrates the relationship between the features through the multi-head self-attention mechanism. Finally, the classification module completes the diagnosis and classification of the disease. The experimental results show that compared with the single-source image neural network method, the accuracy of this method on the experimental data set is improved by 7 percentage points, and the recall rate is improved by 6 percentage points. The experiment verifies that this method improves the accuracy of detecting early symptoms of cervical cancer.