Research on Fusion Algorithm Based on Information Enhancement.

In clinical surgery, multi-spectral fluorescence imaging plays an important role in the precise localization and resection of tumors. In order to accurately label the tumor location and appropriately enhance the tumor information, this paper proposes a two-scale intraoperative navigation fusion algorithm based on saliency detection and fluorescence information enhancement. First, the fusion image of fluorescence and visible light images are used to mark the tumor. Then the tumor detail information is enhanced using saliency detection and coefficient enhancement. The proposed algorithm can effectively preserve the saliency information of the source image, and at the same time highlight the tumor detail information to achieve accurate location and detail enhancement of the tumor. The proposed algorithm is compared with seven classical fusion algorithms. The experimental results show that the proposed algorithm is superior to other seven algorithms in peak signal-to-noise ratio, mutual information, and edge retention. The fused image can provide more comfortable visual effects, the acquired tumor information is more comprehensive and provides an effective auxiliary role for clinical tumor resection.