Dataset Information

Characteristics of superficial esophageal squamous cell carcinomas undetectable with narrow-band imaging endoscopy

ABSTRACT: Abstract

Background

The detection rate of narrow-band imaging (NBI) for superficial esophageal squamous cell carcinoma (SESCC), including high-grade intraepithelial neoplasia, is significantly higher than that of white-light endoscopy. However, there are SESCCs that are undetectable by NBI but detectable by Lugol chromoendoscopy (LCE) and the characteristics of these SESCCs are still unknown. Thus, this study aimed to clarify the characteristics of SESCC that are undetectable using NBI.

Methods

Patients with current SCC or a history of SCC in the head and neck or in the esophagus were enrolled. The inspection of the esophagus was initiated by NBI, followed by LCE. Biopsies were taken of all suspected SESCC lesions during NBI observation and Lugol-voiding lesions (LVLs) that were irregularly shaped and >5 mm and/or pink in color during LCE observation. The characteristics of SESCC that were undetectable with NBI were statistically analysed.

Results

Overall, 147 lesions in 105 cases were histologically diagnosed as SESCC. Twenty in 15 cases were NBI-undetectable lesions, all of which were macroscopic flat type (0-IIb). The median sizes of the NBI-undetectable lesions and NBI-detectable lesions were both 15 mm (P = 0.47). Multivariate analysis revealed independent factors for NBI-undetectable lesions such as numerous irregularly shaped LVLs (odds ratio [OR]: 4.94, 95% confidence interval [CI]: 1.39–17.5, P < 0.05) and anterior wall position (OR: 4.99, 95% CI: 1.58–15.8, P < 0.05).

Conclusions

The detection of SESCCs with NBI is challenging when lesions are morphologically completely flat, in cases with numerous irregularly shaped LVLs, and if located at the anterior wall.

SUBMITTER: Ono S

PROVIDER: S-EPMC8560036 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Esophageal carcinoma (EC) is a prominent contributor to cancer-related mortality since it lacks discernible features in its first phases. Multiple studies have shown that narrow-band imaging (NBI) has superior accuracy, sensitivity, and specificity in detecting EC compared to white light imaging (WLI). Thus, this study innovatively employs a color space linked to décor to transform WLIs into NBIs, offering a novel approach to enhance the detection capabilities of EC in its early stages. In this study a total of 3415 WLI along with the corresponding 3415 simulated NBI images were used for analysis combined with the YOLOv5 algorithm to train the WLI images and the NBI images individually showcasing the adaptability of advanced object detection techniques in the context of medical image analysis. The evaluation of the model's performance was based on the produced confusion matrix and five key metrics: precision, recall, specificity, accuracy, and F1-score of the trained model. The model underwent training to accurately identify three specific manifestations of EC, namely dysplasia, squamous cell carcinoma (SCC), and polyps demonstrates a nuanced and targeted analysis, addressing diverse aspects of EC pathology for a more comprehensive understanding. The NBI model effectively enhanced both its recall and accuracy rates in detecting dysplasia cancer, a pre-cancerous stage that might improve the overall five-year survival rate. Conversely, the SCC category decreased its accuracy and recall rate, although the NBI and WLI models performed similarly in recognizing the polyp. The NBI model demonstrated an accuracy of 0.60, 0.81, and 0.66 in the dysplasia, SCC, and polyp categories, respectively. Additionally, it attained a recall rate of 0.40, 0.73, and 0.76 in the same categories. The WLI model demonstrated an accuracy of 0.56, 0.99, and 0.65 in the dysplasia, SCC, and polyp categories, respectively. Additionally, it obtained a recall rate of 0.39, 0.86, and 0.78 in the same categories, respectively. The limited number of training photos is the reason for the suboptimal performance of the NBI model which can be improved by increasing the dataset.