Matches in SemOpenAlex for { <https://semopenalex.org/work/W2941712557> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2941712557 endingPage "267" @default.
- W2941712557 startingPage "253" @default.
- W2941712557 abstract "Gastric cancer(GC) is the fourth leading cause of cancer death worldwide. To prevent the occurrence of advanced GCs, there is a need for immediate detection and treatment of gastric precancerous and early cancerous lesions. Magnification endoscopy with narrow-band imaging (M-NBI) system as an advanced diagnostic imaging technology is widely used in evaluating gastric lesion types, which can interpret gastric lesion characteristics by enhancing contrasts between vessels and mucosal surfaces. Based on microvascular morphologies presented on M-NBI images, physicians can manually diagnose gastric lesions; but this is a tough work for unexperienced doctors and it is lacking of objectivity. In this study, we propose a transfer learning framework by fine-tuning pre-trained convolutional neural networks (CNNs) to classify gastric M-NBI images into three classes: chronic gastritis (CGT), low grade neoplasia (LGN) and early gastric cancer (EGC). The method we choose is used to compare with three kinds of traditional handcraft texture feature extraction methods and CNN models trained directly by our dataset. Results show that the performance of fine-tuned CNNs outperforms traditional handcraft features and trained CNNs. Experiments also illustrate that ResNet50 can achieve 0.96 accuracy, 0.92, 0.91 and 0.99 f1-scores for classifying M-NBI images into CGT, LGN and EGC. In conclusion, the proposed framework is suit for multi-classification tasks of gastric M-NBI images." @default.
- W2941712557 created "2019-05-03" @default.
- W2941712557 creator A5014633229 @default.
- W2941712557 creator A5033196998 @default.
- W2941712557 creator A5035651264 @default.
- W2941712557 creator A5069121438 @default.
- W2941712557 date "2020-06-01" @default.
- W2941712557 modified "2023-10-06" @default.
- W2941712557 title "Fine-tuning Pre-trained Convolutional Neural Networks for Gastric Precancerous Disease Classification on Magnification Narrow-band Imaging Images" @default.
- W2941712557 cites W2012602905 @default.
- W2941712557 cites W2029927832 @default.
- W2941712557 cites W2039533874 @default.
- W2941712557 cites W2117539524 @default.
- W2941712557 cites W2214724293 @default.
- W2941712557 cites W2272984102 @default.
- W2941712557 cites W2511760322 @default.
- W2941712557 cites W2726189936 @default.
- W2941712557 cites W2746410086 @default.
- W2941712557 cites W2757457388 @default.
- W2941712557 cites W2762363380 @default.
- W2941712557 cites W2783231089 @default.
- W2941712557 cites W2963493912 @default.
- W2941712557 cites W4211019965 @default.
- W2941712557 doi "https://doi.org/10.1016/j.neucom.2018.10.100" @default.
- W2941712557 hasPublicationYear "2020" @default.
- W2941712557 type Work @default.
- W2941712557 sameAs 2941712557 @default.
- W2941712557 citedByCount "39" @default.
- W2941712557 countsByYear W29417125572019 @default.
- W2941712557 countsByYear W29417125572020 @default.
- W2941712557 countsByYear W29417125572021 @default.
- W2941712557 countsByYear W29417125572022 @default.
- W2941712557 countsByYear W29417125572023 @default.
- W2941712557 crossrefType "journal-article" @default.
- W2941712557 hasAuthorship W2941712557A5014633229 @default.
- W2941712557 hasAuthorship W2941712557A5033196998 @default.
- W2941712557 hasAuthorship W2941712557A5035651264 @default.
- W2941712557 hasAuthorship W2941712557A5069121438 @default.
- W2941712557 hasConcept C108583219 @default.
- W2941712557 hasConcept C121608353 @default.
- W2941712557 hasConcept C126322002 @default.
- W2941712557 hasConcept C126838900 @default.
- W2941712557 hasConcept C153180895 @default.
- W2941712557 hasConcept C154945302 @default.
- W2941712557 hasConcept C2778451229 @default.
- W2941712557 hasConcept C2781399487 @default.
- W2941712557 hasConcept C3020576462 @default.
- W2941712557 hasConcept C41008148 @default.
- W2941712557 hasConcept C4144372 @default.
- W2941712557 hasConcept C52622490 @default.
- W2941712557 hasConcept C71924100 @default.
- W2941712557 hasConcept C81363708 @default.
- W2941712557 hasConceptScore W2941712557C108583219 @default.
- W2941712557 hasConceptScore W2941712557C121608353 @default.
- W2941712557 hasConceptScore W2941712557C126322002 @default.
- W2941712557 hasConceptScore W2941712557C126838900 @default.
- W2941712557 hasConceptScore W2941712557C153180895 @default.
- W2941712557 hasConceptScore W2941712557C154945302 @default.
- W2941712557 hasConceptScore W2941712557C2778451229 @default.
- W2941712557 hasConceptScore W2941712557C2781399487 @default.
- W2941712557 hasConceptScore W2941712557C3020576462 @default.
- W2941712557 hasConceptScore W2941712557C41008148 @default.
- W2941712557 hasConceptScore W2941712557C4144372 @default.
- W2941712557 hasConceptScore W2941712557C52622490 @default.
- W2941712557 hasConceptScore W2941712557C71924100 @default.
- W2941712557 hasConceptScore W2941712557C81363708 @default.
- W2941712557 hasFunder F4320321001 @default.
- W2941712557 hasLocation W29417125571 @default.
- W2941712557 hasOpenAccess W2941712557 @default.
- W2941712557 hasPrimaryLocation W29417125571 @default.
- W2941712557 hasRelatedWork W2279398222 @default.
- W2941712557 hasRelatedWork W2731899572 @default.
- W2941712557 hasRelatedWork W2890724796 @default.
- W2941712557 hasRelatedWork W3133861977 @default.
- W2941712557 hasRelatedWork W3156786002 @default.
- W2941712557 hasRelatedWork W4200173597 @default.
- W2941712557 hasRelatedWork W4299822940 @default.
- W2941712557 hasRelatedWork W4312417841 @default.
- W2941712557 hasRelatedWork W4321369474 @default.
- W2941712557 hasRelatedWork W4366492315 @default.
- W2941712557 hasVolume "392" @default.
- W2941712557 isParatext "false" @default.
- W2941712557 isRetracted "false" @default.
- W2941712557 magId "2941712557" @default.
- W2941712557 workType "article" @default.