Cargando…
A Lesion-Based Convolutional Neural Network Improves Endoscopic Detection and Depth Prediction of Early Gastric Cancer
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 pre...
Autores principales: | , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6781189/ https://www.ncbi.nlm.nih.gov/pubmed/31454949 http://dx.doi.org/10.3390/jcm8091310 |
_version_ | 1783457312024821760 |
---|---|
author | Yoon, Hong Jin Kim, Seunghyup Kim, Jie-Hyun Keum, Ji-Soo Oh, Sang-Il Jo, Junik Chun, Jaeyoung Youn, Young Hoon Park, Hyojin Kwon, In Gyu Choi, Seung Ho Noh, Sung Hoon |
author_facet | Yoon, Hong Jin Kim, Seunghyup Kim, Jie-Hyun Keum, Ji-Soo Oh, Sang-Il Jo, Junik Chun, Jaeyoung Youn, Young Hoon Park, Hyojin Kwon, In Gyu Choi, Seung Ho Noh, Sung Hoon |
author_sort | Yoon, Hong Jin |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-6781189 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-67811892019-10-30 A Lesion-Based Convolutional Neural Network Improves Endoscopic Detection and Depth Prediction of Early Gastric Cancer Yoon, Hong Jin Kim, Seunghyup Kim, Jie-Hyun Keum, Ji-Soo Oh, Sang-Il Jo, Junik Chun, Jaeyoung Youn, Young Hoon Park, Hyojin Kwon, In Gyu Choi, Seung Ho Noh, Sung Hoon J Clin Med Article 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. MDPI 2019-08-26 /pmc/articles/PMC6781189/ /pubmed/31454949 http://dx.doi.org/10.3390/jcm8091310 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Yoon, Hong Jin Kim, Seunghyup Kim, Jie-Hyun Keum, Ji-Soo Oh, Sang-Il Jo, Junik Chun, Jaeyoung Youn, Young Hoon Park, Hyojin Kwon, In Gyu Choi, Seung Ho Noh, Sung Hoon A Lesion-Based Convolutional Neural Network Improves Endoscopic Detection and Depth Prediction of Early Gastric Cancer |
title | A Lesion-Based Convolutional Neural Network Improves Endoscopic Detection and Depth Prediction of Early Gastric Cancer |
title_full | A Lesion-Based Convolutional Neural Network Improves Endoscopic Detection and Depth Prediction of Early Gastric Cancer |
title_fullStr | A Lesion-Based Convolutional Neural Network Improves Endoscopic Detection and Depth Prediction of Early Gastric Cancer |
title_full_unstemmed | A Lesion-Based Convolutional Neural Network Improves Endoscopic Detection and Depth Prediction of Early Gastric Cancer |
title_short | A Lesion-Based Convolutional Neural Network Improves Endoscopic Detection and Depth Prediction of Early Gastric Cancer |
title_sort | lesion-based convolutional neural network improves endoscopic detection and depth prediction of early gastric cancer |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6781189/ https://www.ncbi.nlm.nih.gov/pubmed/31454949 http://dx.doi.org/10.3390/jcm8091310 |
work_keys_str_mv | AT yoonhongjin alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT kimseunghyup alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT kimjiehyun alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT keumjisoo alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT ohsangil alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT jojunik alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT chunjaeyoung alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT younyounghoon alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT parkhyojin alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT kwoningyu alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT choiseungho alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT nohsunghoon alesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT yoonhongjin lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT kimseunghyup lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT kimjiehyun lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT keumjisoo lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT ohsangil lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT jojunik lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT chunjaeyoung lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT younyounghoon lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT parkhyojin lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT kwoningyu lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT choiseungho lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer AT nohsunghoon lesionbasedconvolutionalneuralnetworkimprovesendoscopicdetectionanddepthpredictionofearlygastriccancer |