Abstract
Background Dual red imaging (DRI), a novel image-enhanced endoscopy (IEE) technology, has the potential to improve the visibility of blood vessels in deeper tissue using 600 nm and 630 nm wavelength lights in the red band.
Aim To confirm the feasibility of DRI in visualization of vessels in deeper tissue and identify pathologically the features of blood vessels visualized by DRI.
Methods Study 1: visibility of blood vessels was assessed by five observers in 137 pairs of DRI and white light imaging (WLI) images. The scores for the visibility of thick blood vessels were measured for randomized images and compared with the scoring template as a reference. The difference in visibility score between DRI and WLI was compared in each pair of images. Study 2: blood vessels detected only by DRI were examined pathologically using two pig stomachs.
Results Study 1: The mean visibility scores of DRI and WLI for each observer were 1.69 – 2.26 and 1.31 – 1.67, respectively. The mean difference in visibility score and 95 % confidence interval for the five observers was 0.59 [0.46 – 0.72], 0.54 [0.40 – 0.68], 0.34 [0.18 – 0.49], 0.51 [0.36 – 0.66], and 0.71 [0.54 – 0.88]. The visibility was statistically significantly better in DRI than in WLI for all observers (P < 0.0001). Study 2: three blood vessels were observed only by DRI. All of these blood vessels were located at a depth of 1000 – 1500 µm from the mucosal surface. The diameter of these blood vessels exceeded 80 – 200 µm.
Conclusions DRI can feasibly detect thick blood vessels in the deep mucosa or submucosa of the gastrointestinal tract.
Applying deep learning to develop endoscopic imaging technology
