scholarly journals Detecting early gastric cancer: Comparison between the diagnostic ability of convolutional neural networks and endoscopists

2020 ◽  
Vol 33 (1) ◽  
pp. 141-150 ◽  
Author(s):  
Yohei Ikenoyama ◽  
Toshiaki Hirasawa ◽  
Mitsuaki Ishioka ◽  
Ken Namikawa ◽  
Shoichi Yoshimizu ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Neural Networks ◽  
Early Gastric Cancer ◽  
Convolutional Neural Networks ◽  
Diagnostic Ability

scholarly journals Applying Convolutional Neural Networks for Automatic Detection of Early Gastric Cancer with Limited Endoscopic Images

2019 ◽  
Vol 85 (9) ◽  
pp. 761-764
Author(s):  
Satoko TAKEMOTO ◽  
Keisuke HORI ◽  
Yoshimasa SAKAI ◽  
Masaomi NISHIMURA ◽  
Hiroaki IKEMATSU ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Neural Networks ◽  
Early Gastric Cancer ◽  
Convolutional Neural Networks ◽  
Automatic Detection ◽  
Endoscopic Images

scholarly journals Diagnostic ability of magnifying endoscopy with blue laser imaging for early gastric cancer: a prospective study

2016 ◽  
Vol 20 (2) ◽  
pp. 297-303 ◽  
Author(s):  
Osamu Dohi ◽  
Nobuaki Yagi ◽  
Atsushi Majima ◽  
Yusuke Horii ◽  
Tomoko Kitaichi ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Early Gastric Cancer ◽  
Prospective Study ◽  
Magnifying Endoscopy ◽  
Blue Laser ◽  
Laser Imaging ◽  
Diagnostic Ability ◽  
Blue Laser Imaging ◽  
A Prospective Study

scholarly journals End-to-end learning to predict survival in patients with gastric cancer using convolutional neural networks

2018 ◽  
Vol 29 ◽  
pp. viii23 ◽  
Author(s):  
A. Meier ◽  
K. Nekolla ◽  
S. Earle ◽  
L. Hewitt ◽  
T. Aoyama ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
End To End

scholarly journals Diagnostic Ability of High-definition Imaging Using Ultraslim Endoscopes in Early Gastric Cancer

2021 ◽  
Vol 21 ◽  
Author(s):  
Tomomi Sugita ◽  
Sho Suzuki ◽  
Ryoji Ichijima ◽  
Kanako Ogura ◽  
Chika Kusano ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Early Gastric Cancer ◽  
High Definition ◽  
Diagnostic Ability

scholarly journals Discovering Biomarkers in Gastric Cancer by Urine Metabolomics

2021 ◽  
Author(s):  
Yuan Kong ◽  
Hongya Zhang ◽  
Shuang Li ◽  
Jian Suo ◽  
Shaopeng Zhang ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Cluster Analysis ◽  
Early Gastric Cancer ◽  
Partial Least Square ◽  
Least Square ◽  
Urine Samples ◽  
Diagnostic Ability ◽  
Healthy Group ◽  
Cancer Group ◽  
Gastric Cancer Group

Abstract IntroductionGastric cancer is one of the most common gastrointestinal tumors, ranking forth in incidence and second in mortality worldwide. Discovering molecular biomarkers for early gastric cancer diagnosis is of great importance. MethodsUrine and related clinical data of 40 patients with gastric cancer (20 in advanced stage and 20 in early stage) and 20 healthy volunteers from Jilin University First Hospital were collected. Liquid chromatography-mass spectrometry (LC-MS) was used to detect urine samples and the metabolic differences between the three groups of urine samples were analyzed. The principal component analysis was performed after data processing, and different metabolites were found using analysis of variance. Partial least square discriminant analysis was performed to further narrow the range of different metabolites. The precise mass to charge ratios of different metabolites were imported into the Human Metabolomics Database (HMDB). Finally, the identified different metabolites were further screened by cluster analysis and ROC curve. ResultsUrine samples of the healthy group (NOR), the early gastric cancer group (EGC), and the advanced gastric cancer group (AGC) were different metabolites. 324 statistically significant metabolites are screened out. The cluster analysis showed 7-Methylguanine, vinylacetylglycine, butyric acid, 4-Vinylphenol sulf,
5`-biotinyl-AMP, and 3-Amino-2-piperido in EGC, AGC and NGO were similar. 7-Methylguanine, vinylacetylglycine and 4-Vinylphenolsulfate had good diagnostic ability in EGC and NOR (p<0.05), and gastric cancer and NOR (p<0.05). ConclusionDifferences in the metabolites in urine between the early gastric cancer group and the healthy group were found. 7-Methylguanine, Vinylacetylglycine, and 4-Vinylphenolsulfate have good diagnostic ability and may be potential biomarkers of early gastric cancer.

scholarly journals Detecting gastric cancer from video images using convolutional neural networks

2018 ◽  
Vol 31 (2) ◽  
Author(s):  
Mitsuaki Ishioka ◽  
Toshiaki Hirasawa ◽  
Tomohiro Tada
Keyword(s):  
Gastric Cancer ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Video Images

scholarly journals Evaluation of the Diagnostic Ability of Optical Enhancement System in Early Gastric Cancer Demarcation

2016 ◽  
Vol 2016 ◽  
pp. 1-6 ◽  
Author(s):  
Misato Nagao ◽  
Jun Nishikawa ◽  
Ryo Ogawa ◽  
Sho Sasaki ◽  
Munetaka Nakamura ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Early Gastric Cancer ◽  
False Negative ◽  
Three Dimensional ◽  
Diagnostic Ability ◽  
Mahalanobis Distances ◽  
Color Differences ◽  
Light Mode ◽  
Mean Vectors ◽  
The Mean

This study aimed to evaluate the utility of optical enhancement (OE) in early gastric cancer demarcation. Twenty lesions of early gastric cancer were examined by PENTAX endoscopy system with OE-1 and OE-2 functions. The areas of tumor demarcation identified by 12 evaluators (6 novice and 6 experienced) were compared to the corresponding correct areas determined by postoperative histopathology findings. The misdiagnosed scores that were the sums of false-positive and false-negative areas were compared. Color of one hundred pixels from the inside of the cancerous area and the outside of the cancerous area was expressed as three-dimensional RGB component vectors. The mean vectors and covariance matrixes were calculated and the Mahalanobis distance, indicative of color differences between two areas, was tested. Comparisons of the misdiagnosed score revealed that OE-1 was preferred over WL-1 for gastric cancer demarcation for all 12 evaluators (p=0.008) and in novice evaluators (p=0.026). OE-2 was not significantly different from WL-2 in all cases. OE-1 images gave significantly larger Mahalanobis distances, indicative of color differences, than WL-1 images (p=0.002). It was demonstrated that the OE Mode 1 has a significant advantage over the white light mode in demarcation of early gastric cancer.

Sign in / Sign up

Export Citation Format

Share Document