2026 Volume 15 Issue 2 Pages 266-272
The progression of a malignant tumor in the gastrointestinal tract is usually determined by an endoscopist based on endoscopic images. In such cases, the diameter of the tumor is the most important factor in determining the degree of progression. In this paper, we introduce a new image processing technique to model tumors on the gastric surface in three dimensions from endoscopic images and to measure the diameter of the tumor from the data. Further, a new reflection model based on the two-point light source model is used. Finally, we demonstrate the effectiveness of the proposed method through experiments using endoscopic images of actual cancer patients.