Assessment of early gastric cancer visibility in deep-learning-based virtual indigo carmine chromoendoscopy (with video).

ABSTRACT:

Background and study aims

Indigo carmine chromoendoscopy (IC) enhances diagnosis of early gastric cancer (EGC), but its clinical application is limited by procedure complexity and time. We developed a deep-learning system using a cycle-consistent generative adversarial network (CycleGAN) to generate virtual IC images from white-light endoscopy (WLE) and evaluated visibility of EGC in video-based virtual IC in a pilot study.

Patients and methods

We collected 4,096 endoscopic still images (2,089 WLE, 2,007 real IC) from 262 patients with gastric neoplasms. A CycleGAN model was trained to convert WLE into virtual IC images, and videos with 512 × 512 pixels at 30 frames per second were generated for five EGC cases. For each case, WLE, real IC, and virtual IC videos were prepared

SUBMITTER: Takasu A 

PROVIDER: S-EPMC12817183 | biostudies-literature | 2026

REPOSITORIES: biostudies-literature