# Artificial Intelligence for Lymph Node Detection and Malignancy Prediction in Endoscopic Ultrasound: A Multicenter Study

## TL;DR

This study introduces an AI system using EUS imaging to accurately detect and predict lymph node malignancy, offering a new tool for better cancer staging and treatment.

## Contribution

The first worldwide deep learning model for lymph node assessment using EUS imaging, with high accuracy and clinical applicability.

## Key findings

- The AI model achieved 98.8% sensitivity and 99.0% specificity in predicting lymph node malignancy.
- The model processed images with 98.3% overall diagnostic accuracy, showing strong potential for clinical use.
- This multicenter study used 59,992 images from 82 EUS procedures to train and validate the model.

## Abstract

Endoscopic ultrasound is fundamental for lymph node assessment, being pivotal in oncological staging and treatment guidance. However, significant limitations are observed when considering EUS criteria for prediction of lymph node malignancy. The authors aimed to develop a YOLO convolutional neural network for artificial intelligence-based prediction of lymph node malignancy during EUS. The model had an overall accuracy over 98% for prediction of lymph node malignancy, with an image processing time that favors its clinical applicability. This is the first study worldwide study evaluating deep learning models for lymph node assessment using EUS imaging, enabling artificial intelligence-assisted EUS has a novel tool for achieving a more accurate and tailored patient management.

Background/Objectives: Endoscopic ultrasound (EUS) is crucial for lymph node (LN) characterization, playing a key role in oncological staging and treatment guidance. EUS criteria for predicting malignancy are imprecise, and histologic diagnosis may have limitations. This multicenter study aimed to evaluate the effectiveness of a novel artificial intelligence (AI)–based system in predicting LN malignancy from EUS images. Methods: This multicenter study included EUS images from nine centers. Lesions were labeled (“malignant” or “benign”) and delimited with bounding boxes. Definitive diagnoses were based on cytology/biopsy or surgical specimens and, if negative, a minimum six-month clinical follow-up. A convolutional neural network (CNN) was developed using the YOLO (You Only Look Once) architecture, incorporating both detection and classification modules. Results: A total of 59,992 images from 82 EUS procedures were analyzed. The CNN distinguished malignant from benign lymph nodes with a sensitivity of 98.8% (95% CI: 98.5–99.2%), specificity of 99.0% (95% CI: 98.3–99.7%), and precision of 99.0% (95% CI: 98.4–99.7%). The negative and positive predictive values for malignancy were 98.8% and 99.0%, respectively. Overall diagnostic accuracy was 98.3% (95% CI: 97.6–99.1%). Conclusions: This is the first study evaluating the performance of deep learning systems for LN assessment using EUS imaging. Our AI-powered imaging model shows excellent detection and classification capabilities, emphasizing its potential to provide a valuable tool to refine LN evaluation with EUS, ultimately supporting more tailored, efficient patient care.