Literature DB >> 33465354

High performance in risk stratification of intraductal papillary mucinous neoplasms by confocal laser endomicroscopy image analysis with convolutional neural networks (with video).

Jorge D Machicado1, Wei-Lun Chao2, David E Carlyn2, Tai-Yu Pan2, Sarah Poland3, Victoria L Alexander3, Tassiana G Maloof3, Kelly Dubay4, Olivia Ueltschi4, Dana M Middendorf3, Muhammed O Jajeh5, Aadit B Vishwanath6, Kyle Porter7, Phil A Hart8, Georgios I Papachristou8, Zobeida Cruz-Monserrate8, Darwin L Conwell8, Somashekar G Krishna8.   

Abstract

BACKGROUND AND AIMS: EUS-guided needle-based confocal laser endomicroscopy (EUS-nCLE) can differentiate high-grade dysplasia/adenocarcinoma (HGD-Ca) in intraductal papillary mucinous neoplasms (IPMNs) but requires manual interpretation. We sought to derive predictive computer-aided diagnosis (CAD) and artificial intelligence (AI) algorithms to facilitate accurate diagnosis and risk stratification of IPMNs.
METHODS: A post hoc analysis of a single-center prospective study evaluating EUS-nCLE (2015-2019; INDEX study) was conducted using 15,027 video frames from 35 consecutive patients with histopathologically proven IPMNs (18 with HGD-Ca). We designed 2 CAD-convolutional neural network (CNN) algorithms: (1) a guided segmentation-based model (SBM), where the CNN-AI system was trained to detect and measure papillary epithelial thickness and darkness (indicative of cellular and nuclear stratification), and (2) a reasonably agnostic holistic-based model (HBM) where the CNN-AI system automatically extracted nCLE features for risk stratification. For the detection of HGD-Ca in IPMNs, the diagnostic performance of the CNN-CAD algorithms was compared with that of the American Gastroenterological Association (AGA) and revised Fukuoka guidelines.
RESULTS: Compared with the guidelines, both n-CLE-guided CNN-CAD algorithms yielded higher sensitivity (HBM, 83.3%; SBM, 83.3%; AGA, 55.6%; Fukuoka, 55.6%) and accuracy (SBM, 82.9%; HBM, 85.7%; AGA, 68.6%; Fukuoka, 74.3%) for diagnosing HGD-Ca, with comparable specificity (SBM, 82.4%; HBM, 88.2%; AGA, 82.4%; Fukuoka, 94.1%). Both CNN-CAD algorithms, the guided (SBM) and agnostic (HBM) models, were comparable in risk stratifying IPMNs.
CONCLUSION: EUS-nCLE-based CNN-CAD algorithms can accurately risk stratify IPMNs. Future multicenter validation studies and AI model improvements could enhance the accuracy and fully automatize the process for real-time interpretation.
Copyright © 2021 American Society for Gastrointestinal Endoscopy. Published by Elsevier Inc. All rights reserved.

Entities:  

Mesh:

Year:  2021        PMID: 33465354     DOI: 10.1016/j.gie.2020.12.054

Source DB:  PubMed          Journal:  Gastrointest Endosc        ISSN: 0016-5107            Impact factor:   10.396


  7 in total

Review 1.  Early detection of pancreatic cancer: current state and future opportunities.

Authors:  Guru Trikudanathan; Emil Lou; Anirban Maitra; Shounak Majumder
Journal:  Curr Opin Gastroenterol       Date:  2021-09-01       Impact factor: 2.741

Review 2.  Application of Artificial Intelligence in the Management of Pancreatic Cystic Lesions.

Authors:  Shiva Rangwani; Devarshi R Ardeshna; Brandon Rodgers; Jared Melnychuk; Ronald Turner; Stacey Culp; Wei-Lun Chao; Somashekar G Krishna
Journal:  Biomimetics (Basel)       Date:  2022-06-14

Review 3.  The role of artificial intelligence in pancreatic surgery: a systematic review.

Authors:  D Schlanger; F Graur; C Popa; E Moiș; N Al Hajjar
Journal:  Updates Surg       Date:  2022-03-02

Review 4.  State-of-the-Art Update of Pancreatic Cysts.

Authors:  Andrew Canakis; Linda S Lee
Journal:  Dig Dis Sci       Date:  2021-08-12       Impact factor: 3.487

Review 5.  Recent advances in the diagnostic evaluation of pancreatic cystic lesions.

Authors:  Devarshi R Ardeshna; Troy Cao; Brandon Rodgers; Chidiebere Onongaya; Dan Jones; Wei Chen; Eugene J Koay; Somashekar G Krishna
Journal:  World J Gastroenterol       Date:  2022-02-14       Impact factor: 5.374

6.  MRI-Based Pancreatic Atrophy Is Associated With Malignancy or Invasive Carcinoma in Intraductal Papillary Mucinous Neoplasm.

Authors:  Tingting Lin; Xin Chen; Jingjing Liu; Yingying Cao; Wenjing Cui; Zhongqiu Wang; Cheng Wang; Xiao Chen
Journal:  Front Oncol       Date:  2022-06-03       Impact factor: 5.738

Review 7.  Application of artificial intelligence to pancreatic adenocarcinoma.

Authors:  Xi Chen; Ruibiao Fu; Qian Shao; Yan Chen; Qinghuang Ye; Sheng Li; Xiongxiong He; Jinhui Zhu
Journal:  Front Oncol       Date:  2022-07-22       Impact factor: 5.738

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.