Multimodal collaborative image segmentation system for esophageal cancer lesions based on self-sampling similarity

Abstract

The invention belongs to the technical field of medical image intelligent processing, and specifically relates to a self-sampling similarity-based multimodal collaborative esophageal cancer lesion image segmentation system. For the diagnosis of early esophageal cancer, first construct a paired white light image and NBI data set; the segmentation system includes a feature extraction encoder, a self-sampling similar feature separation module, and a feature fusion decoder; with white light images and NBI as multimodal input, The features of the two modalities are extracted by two encoders; for each modality, the self-sampling similar feature separation module effectively distinguishes the features of the lesion area from the normal area; the decoder completes multi-modal feature fusion in the feature domain, Finally, the lesion segmentation results of the two modality images are output. Experimental results show that the present invention can reasonably integrate features of different modalities, significantly distinguish diseased areas from normal areas, realize precise segmentation of diseased areas, and improve the efficiency of clinical diagnosis.

Description

technical field [0001] The invention belongs to the technical field of medical image intelligent processing, in particular to an esophageal cancer lesion image segmentation system, more specifically, to a self-sampling similarity-based multi-modal cooperative esophageal cancer lesion image segmentation system. Background technique [0002] Esophageal cancer is a common upper gastrointestinal cancer in China and developing countries, ranking sixth in cancer deaths in the world [1] . Studies have shown that the 5-year survival rate of patients with advanced esophageal cancer is less than 20%, but it can exceed 85% in the early stage. Advanced unresectable tumors are the main cause of poor prognosis in most patients with esophageal cancer. Therefore, accurate diagnosis of early esophageal cancer plays an important role in reducing mortality. [0003] Endoscopic screening significantly reduces mortality from esophageal cancer. White-light endoscopic imaging (WH) is the most ...

AI Technical Summary

Problems solved by technology

[0006] Although the above methods have achieved certain results, the researchers only considered the use of white light images

Images