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

<b>Background/Objectives</b>: 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. <b>Methods</b>: 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. <b>Results</b>: 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%). <b>Conclusions</b>: 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.

Authors

Institutions

Publication Details

Journal
Cancers
Published
2025-10-22
DOI
https://doi.org/10.3390/cancers17213398
Primary Topic
Lung Cancer Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Marcos Eduardo Lera dos Santos, Eduardo Guimarães Hourneaux de Moura, Miguel Martins, Tiago Ribeiro et al.
Cancers
Lung Cancer Diagnosis and Treatment
article

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

Marcos Eduardo Lera dos Santos, Eduardo Guimarães Hourneaux de Moura, Miguel Martins, Tiago Ribeiro, João L. Afonso, Daniel de la Iglesia, María Moris, Pedro Moutinho-Ribeiro, Miguel Mascarenhas, Belén Agudo, Mariano González-Haba, António Miguel Martins Pinto da Costa, Francisco Mendes, Ana García García de Paredes, Guilherme Macedo, G. Kim, Filipe Vilas‐Boas, Ana Pérez González, Joana Mota, Maria João Almeida, Matheus Ferreira de Carvalho, Uzma D. Siddiqui, Susana Lopes, João Canas Ferreira, Khoon-Sheng Kok, Pedro Cardoso, Jessica Widmer, Carlos Estebam Fernández-Zarza
article en

Abstract

<b>Background/Objectives</b>: 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. <b>Methods</b>: 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. <b>Results</b>: 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%). <b>Conclusions</b>: 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.

CancersVol. 17(21)
University of Liverpool (GB), Universidade do Porto (PT), Royal Liverpool University Hospital (GB), Hospital de São João (PT), University of Chicago (US), NYU Langone Health (US), Marqués de Valdecilla University Hospital (ES), Hospital Universitario Puerta de Hierro Majadahonda (ES), Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (BR), Hospital Universitario Ramón y Cajal (ES), Hospital São Paulo (BR)
Openalex Percentile: Top 57%
Lung Cancer Diagnosis and Treatment
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.