# Artificial intelligence-based endoscopic ultrasonography model for detecting the origin layer of gastric subepithelial lesions

## TL;DR

This paper introduces an AI system using MedMamba architecture to accurately identify the origin layer of gastric subepithelial lesions during endoscopic ultrasonography.

## Contribution

A novel AI system based on MedMamba architecture for improved diagnosis of gastric subepithelial lesions.

## Key findings

- The MedMamba model achieved 92.04% accuracy in classifying the origin layer of gastric SELs.
- It outperformed other AI models with 94.83% specificity and 81.11% sensitivity.
- The model shows potential to reduce diagnostic variability in endoscopic ultrasonography.

## Abstract

Gastric subepithelial lesions (SELs) are typically covered by intact mucosa, which challenges the determination of their layer of origin under conventional endoscopy. Endoscopic ultrasonography (EUS) is indispensable for diagnosing SELs. However, EUS operation and interpretation are more challenging than standard endoscopy and are subject to inter-observer variability. This study aimed to develop a novel AI system based on the MedMamba architecture to assist clinicians in identifying the layer of origin of gastric SELs.

We retrospectively collected data from patients who underwent EUS at the First Affiliated Hospital of Nanjing Medical University between May 1, 2016 and May 1, 2023. The dataset comprised 1,855 images from 320 patients. Images were split into training, validation, and test sets at an 8:1:1 ratio at the patient level to prevent data leakage. A structured State space sequence model (MedMamba) was trained and the performance was compared against endoscopists.

The proposed MedMamba model achieved an overall accuracy of 92.04% (95%CI: 90.33–93.75%), with 94.83% (95%CI: 93.22–96.44%) specificity and 81.11% (95%CI: 75.19–87.03%) sensitivity in the five-category classification. It achieved high sensitivity and accuracy, outperforming other AI models.

The MedMamba-based AI system demonstrated superior performance in discriminating the layer of origin of SELs compared with other AI models, indicating its potential utility in reducing diagnostic variability and enhancing clinical diagnostic workflows.