14 20

Cited 0 times in

A Lesion-Based Convolutional Neural Network Improves Endoscopic Detection and Depth Prediction of Early Gastric Cancer

Authors
 Hong Jin Yoon  ;  Seunghyup Kim  ;  Jie-Hyun Kim  ;  Ji-Soo Keum  ;  Sang-Il Oh 2  ;  Junik Jo 2  ;  Jaeyoung Chun 1  ;  Young Hoon Youn 1  ;  Hyojin Park 1  ;  In Gyu Kwon 3  ;  Seung Ho Choi 3 and Sung Hoon Noh 3 
Citation
 Journal of Clinical Medicine, Vol.8(9) : E1310, 2019 
Journal Title
 Journal of Clinical Medicine 
Issue Date
2019
Keywords
artificial intelligence ; convolutional neural networks ; early gastric cancer ; endoscopy
Abstract
In early gastric cancer (EGC), tumor invasion depth is an important factor for determining the treatment method. However, as endoscopic ultrasonography has limitations when measuring the exact depth in a clinical setting as endoscopists often depend on gross findings and personal experience. The present study aimed to develop a model optimized for EGC detection and depth prediction, and we investigated factors affecting artificial intelligence (AI) diagnosis. We employed a visual geometry group(VGG)-16 model for the classification of endoscopic images as EGC (T1a or T1b) or non-EGC. To induce the model to activate EGC regions during training, we proposed a novel loss function that simultaneously measured classification and localization errors. We experimented with 11,539 endoscopic images (896 T1a-EGC, 809 T1b-EGC, and 9834 non-EGC). The areas under the curves of receiver operating characteristic curves for EGC detection and depth prediction were 0.981 and 0.851, respectively. Among the factors affecting AI prediction of tumor depth, only histologic differentiation was significantly associated, where undifferentiated-type histology exhibited a lower AI accuracy. Thus, the lesion-based model is an appropriate training method for AI in EGC. However, further improvements and validation are required, especially for undifferentiated-type histology.
Files in This Item:
T201903125.pdf Download
DOI
10.3390/jcm8091310
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Surgery (외과학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
Yonsei Authors
Kwon, In Gyu(권인규) ORCID logo https://orcid.org/0000-0002-1489-467X
Kim, Seung Up(김승업) ORCID logo https://orcid.org/0000-0002-9658-8050
Kim, Jie-Hyun(김지현) ORCID logo https://orcid.org/0000-0002-9198-3326
Noh, Sung Hoon(노성훈) ORCID logo https://orcid.org/0000-0003-4386-6886
Park, Hyo Jin(박효진) ORCID logo https://orcid.org/0000-0003-4814-8330
Youn, Young Hoon(윤영훈) ORCID logo https://orcid.org/0000-0002-0071-229X
Yoon, Hong Jin(윤홍진) ORCID logo https://orcid.org/0000-0002-4880-3262
Chun, Jaeyoung(천재영) ORCID logo https://orcid.org/0000-0002-4212-0380
Choi, Seung Ho(최승호) ORCID logo https://orcid.org/0000-0002-9872-3594
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/171236
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse