Diagnostic Ability of High-definition Imaging Using Ultraslim Endoscopes in Early Gastric Cancer

Diagnostic performance of deep-learning-based virtual chromoendoscopy in gastric neoplasms

BACKGROUNDS

Cycle-consistent generative adversarial network (CycleGAN) is a deep neural network model that performs image-to-image translations. We generated virtual indigo carmine (IC) chromoendoscopy images of gastric neoplasms using CycleGAN and compared their diagnostic performance with that of white light endoscopy (WLE).

METHODS

WLE and IC images of 176 patients with gastric neoplasms who underwent endoscopic resection were obtained. We used 1,633 images (911 WLE and 722 IC) of 146 cases in the training dataset to develop virtual IC images using CycleGAN. The remaining 30 WLE images were translated into 30 virtual IC images using the trained CycleGAN and used for validation. The lesion borders were evaluated by 118 endoscopists from 22 institutions using the 60 paired virtual IC and WLE images. The lesion area concordance rate and successful whole-lesion diagnosis were compared.

RESULTS

The lesion area concordance rate based on the pathological diagnosis in virtual IC was lower than in WLE (44.1% vs. 48.5%, p < 0.01). The successful whole-lesion diagnosis was higher in the virtual IC than in WLE images; however, the difference was insignificant (28.2% vs. 26.4%, p = 0.11). Conversely, subgroup analyses revealed a significantly higher diagnosis in virtual IC than in WLE for depressed morphology (41.9% vs. 36.9%, p = 0.02), differentiated histology (27.6% vs. 24.8%, p = 0.02), smaller lesion size (42.3% vs. 38.3%, p = 0.01), and assessed by expert endoscopists (27.3% vs. 23.6%, p = 0.03).

CONCLUSIONS

The diagnostic ability of virtual IC was higher for some lesions, but not completely superior to that of WLE. Adjustments are required to improve the imaging system's performance.

Visibility of early gastric cancers by texture and color enhancement imaging using a high-definition ultrathin transnasal endoscope

We evaluated whether texture and color enhancement imaging (TXI) using a high-definition ultrathin transnasal endoscope (UTE) improves the visibility of early gastric cancer (EGC) compared with white-light imaging (WLI). This study included 31 EGCs observed by TXI mode 2 using a high-definition UTE prior to endoscopic submucosal dissection. The first outcome was to compare the color differences based on Commission Internationale de l'Eclairage L*a*b* color space between EGCs and the surrounding mucosa by WLI and TXI using the UTE (objective appearance of EGC). The second outcome was to assess the visibility of EGCs by WLI and TXI using the UTE in an image evaluation test performed on 10 endoscopists (subjective appearance of EGC). Color differences between EGCs and non-neoplastic mucosa were significantly higher in TXI than in WLI in all EGCs (TXI: 16.0 ± 10.1 vs. WLI: 10.2 ± 5.5 [mean ± standard deviation], P < 0.001). Median visibility scores evaluated by 10 endoscopists using TXI were significantly higher than those evaluated using WLI (TXI: 4 [interquartile range, 4-4] vs. WLI: 4 [interquartile range, 3-4], P < 0.001). TXI using high-definition UTE improved both objective and subjective visibility of EGCs compared with WLI.