Visible light image and fluorescence image fusion method and system

Abstract

The invention discloses a visible light image and fluorescence image fusion method and system, and relates to the technical field of medical image processing. Comprising the following steps: carrying out image registration on a visible light camera and a near-infrared camera to obtain registration parameters; a visible light image and a fluorescence image are synchronously collected, the received fluorescence image is preprocessed, and pixels of the visible light image and the preprocessed fluorescence image are aligned according to the registration parameters; performing pixel fusion on the visible light image and the fluorescence image after registration and alignment to generate a multispectral image; and sequentially merging the fused multispectral images to generate a corresponding video sequence. According to the method, offline camera registration is adopted, the visible light image and the fluorescence image can be efficiently and accurately aligned through registration parameters, the high-quality fluorescence image can be generated through enhancement preprocessing, and the fusion weight is calculated according to the edge intensity value and the fluorescence intensity value; the multi-spectral image after weight fusion can keep edge and fluorescence intensity information at the same time, and the method is suitable for medical equipment such as a fluorescence microscope / endoscope and the like.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, and more specifically relates to a fusion method and system for visible light images and fluorescence images. Background technique [0002] At present, the camera module of most medical imaging systems is a color visible light sensor with a CMOS / CCD structure. With the rapid iterative update of the photosensitive element manufacturing process and imaging technology, the imaging resolution and imaging quality of the current visible light image can meet the requirements of the medical community for high-quality imaging. Universal request. However, color visible light cameras can only produce visible light images, and cannot present image information outside the visible spectrum; in contrast, near-infrared cameras can collect and image signals other than visible light wavelengths. Combined with dyeing reagents that generate invisible light by laser excitation, such as the fluoresce...

AI Technical Summary

Problems solved by technology

However, the current visible light and fluorescence image fusion technology is facing several difficulties: (1) The medical field has strict requirements on the authenticity and accuracy of imaging results, so image fusion must be based on strict alignment of pixels, while visible light images and fluorescence images are usually Collected from different cameras, if the images are not accurately registered before fusion, it may cause imaging errors and stroboscopic and other bad situations; (2) The fluorescence signal collected by the near-infrared camera is very weak, and there are interference signals, which cannot be directly compared with the visible light image. Fusion requires proper enhanced preprocessing; (3) In the process of image weighted fusion, the weight setting is very critical to the image quality. Improper weight setting may lead to problems such as low brightness, blurred edges, and difficulty in distinguishing the intensity of fluorescent signals.

Images