S601 Deep Learning System for Differentiation of Malignant From Benign Lymph Nodes on EUS Staging of Esophageal Cancer: A Pilot Study

EUS is largely dependent on identifying visual patterns and artificial intelligence using a deep learning model can offer an objective way of malignant LN detection. [...]we aimed to develop and validate a deep learning model to differentiate benign from malignant lymph nodes during EUS staging of e...

Full description

Saved in:
Bibliographic Details
Published inThe American journal of gastroenterology Vol. 118; no. 10S; pp. S441 - S442
Main Authors Joseph, Abel, Nadeem, Ahmed, Chen, David, Qin, Yi, Huang, Shuaiqi, Wang, Xiaofeng, Jang, Sunguk, Sanaka, Madhusudhan R., Chahal, Prabhleen, Vargo, John, Raja, Siva, Murthy, Sudish, Bhatt, Amit
Format Journal Article
LanguageEnglish
Published New York Wolters Kluwer Health Medical Research, Lippincott Williams & Wilkins 01.10.2023
Subjects
Accuracy
Artificial intelligence
Deep learning
Endoscopy
Esophageal cancer
Lymphatic system
Pathology
Surgery
Ultrasonic imaging
Online AccessGet full text

Cover

More Information
Summary:EUS is largely dependent on identifying visual patterns and artificial intelligence using a deep learning model can offer an objective way of malignant LN detection. [...]we aimed to develop and validate a deep learning model to differentiate benign from malignant lymph nodes during EUS staging of esophageal cancer. EUS is largely dependent on identifying visual patterns and artificial intelligence using a deep learning model can offer an objective way of malignant LN detection. [...]we aimed to develop and validate a deep learning model to differentiate benign from malignant lymph nodes during EUS staging of esophageal cancer (Figure 1). Baseline demographic and disease characteristics Demographic and Clinical Characteristics Total (N=272) Age, years 67.0 [61.0;72.0] Gender, Male (%) 222 (81.6%) Smoking status, active, n (%) 201 (73.9%) Body Mass Index 26.5 [23.4;31.0] Median time to surgery from Index EUS 97 days [53.75, 119.75] Median time to surgery from pCRT EUS 19 days [8, 30] EUS stage, N0 78 (28.7%) EUS stage, N1 96 (35.3%) EUS stage, N2 31 (11.4%) EUS stage, N3 2 (0.7%) Pathology, N stage, N0 158 (58.1%) Pathology, N stage, N1 47 (17.3%) Pathology, N stage, N2 38 (14.0%) Pathology, N stage, N3 16 (5.9%) pCRT, post-chemoradiation therapy, EUS, Endoscopic ultrasound.
ISSN:0002-9270
1572-0241
DOI:10.14309/01.ajg.0000952044.43959.29