Surgical tumor operation real-time navigation method based on indocyanogen-green fluorescence development

Abstract

The invention discloses a surgical tumor operation real-time navigation method based on indocyanogen-green (Indocyanine-green for English abbreviation (ICG)) fluorescence development. The surgical tumor operation real-time navigation method comprises the following steps: 1, obtaining each frame of image in a real-time ICG fluorescence operation video and storing the image as an ICG fluorescence image; 2, segmenting a tumor boundary in the ICG fluorescence image by using a tumor boundary segmentation model based on deep learning, and adding the tumor boundary to the original ICG fluorescence image in a color line manner for display; 3, evaluating the segmentation boundary of the ICG fluorescence image by adopting an edge evaluation function to obtain a corresponding boundary clearness coefficient; and 4, finding out the image with the maximum boundary clearness coefficient, superposing the corresponding segmentation boundary on the tumor image under the conventional illumination, displaying a superposing result on a screen, and guiding a doctor to carry out a tumor excision operation.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a real-time navigation method for tumor surgery based on indocyanine green fluorescence imaging. Background technique [0002] China is the largest country with liver cancer, and a large number of patients die of liver cancer every year. Surgical removal of liver cancer cells completely is the most effective way to treat liver cancer. During the operation, surgeons usually use preoperative CT, MRI and other imaging data, and use visual diagnosis, palpation, and intraoperative ultrasound to judge the tumor margin and determine the extent of resection. Due to the problems of huge equipment, ray radiation, and long examination time in CT and MRI, intraoperative real-time imaging evaluation is limited to ultrasonography. However, ultrasonography requires high professional skills in image interpretation and is difficult to popularize in liver surgery. [0003] Indoc...

AI Technical Summary

Problems solved by technology

At present, ICG has been widely used in endoscopic surgery, but the existing surgical navigation system guided by ICG only simply displays the fluorescence image, and then the doctor observes the image and draws the boundary based on his own clinical experience, which lacks scientific quantification standard

ICG staining is a sequential process, that is, with the absorption and metabolism of cells, the fluorescence is a process that gradually increases from dark to peak and then gradually decays. At the same time, the edges of ICG fluorescence images are blurred, and traditional image processing methods cannot effectively acquire Boundary, but the clearest boundary cannot be obtained only with the naked eye of a doctor

Images