Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281657029> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4281657029 endingPage "106924" @default.
- W4281657029 startingPage "106924" @default.
- W4281657029 abstract "Gastric cancer has high morbidity and mortality compared to other cancers. Accurate histopathological diagnosis has great significance for the treatment of gastric cancer. With the development of artificial intelligence, many researchers have applied deep learning for the classification of gastric cancer pathological images. However, most studies have used binary classification on pathological images of gastric cancer, which is insufficient with respect to the clinical requirements. Therefore, we proposed a multi-classification method based on deep learning with more practical clinical value.In this study, we developed a novel multi-scale model called StoHisNet based on Transformer and the convolutional neural network (CNN) for the multi-classification task. StoHisNet adopts Transformer to learn global features to alleviate the inherent limitations of the convolution operation. The proposed StoHisNet can classify the publicly available pathological images of a gastric dataset into four categories -normal tissue, tubular adenocarcinoma, mucinous adenocarcinoma, and papillary adenocarcinoma.The accuracy, F1-score, recall, and precision of the proposed model in the public gastric pathological image dataset were 94.69%, 94.96%, 94.95%, and 94.97%, respectively. We conducted additional experiments using two other public datasets to verify the generalization ability of the model. On the BreakHis dataset, our model performed better compared with other classification models, and the accuracy was 91.64%. Similarly, on the four-classification task on the Endometrium dataset, our model showed better classification ability than others with accuracy of 81.74%. These experiments showed that the proposed model has excellent ability of classification and generalization.The StoHisNet model had high performance in the multi-classification on gastric histopathological images and showed strong generalization ability on other pathological datasets. This model may be a potential tool to assist pathologists in the analysis of gastric histopathological images." @default.
- W4281657029 created "2022-06-13" @default.
- W4281657029 creator A5001141933 @default.
- W4281657029 creator A5004739483 @default.
- W4281657029 creator A5028167410 @default.
- W4281657029 creator A5039508181 @default.
- W4281657029 creator A5062306821 @default.
- W4281657029 creator A5072381481 @default.
- W4281657029 date "2022-06-01" @default.
- W4281657029 modified "2023-10-04" @default.
- W4281657029 title "StoHisNet: A hybrid multi-classification model with CNN and Transformer for gastric pathology images" @default.
- W4281657029 cites W2022459634 @default.
- W4281657029 cites W2056568601 @default.
- W4281657029 cites W2077688544 @default.
- W4281657029 cites W2088814549 @default.
- W4281657029 cites W2091882615 @default.
- W4281657029 cites W2099029452 @default.
- W4281657029 cites W2102563634 @default.
- W4281657029 cites W2175791037 @default.
- W4281657029 cites W2344480160 @default.
- W4281657029 cites W2624699030 @default.
- W4281657029 cites W2789525724 @default.
- W4281657029 cites W2809376948 @default.
- W4281657029 cites W2884561390 @default.
- W4281657029 cites W2957792382 @default.
- W4281657029 cites W2998472909 @default.
- W4281657029 cites W3027869849 @default.
- W4281657029 cites W3046091280 @default.
- W4281657029 cites W3081006013 @default.
- W4281657029 cites W3100398151 @default.
- W4281657029 cites W3138516171 @default.
- W4281657029 cites W3138973186 @default.
- W4281657029 cites W4214636423 @default.
- W4281657029 cites W4240198818 @default.
- W4281657029 cites W4281853941 @default.
- W4281657029 doi "https://doi.org/10.1016/j.cmpb.2022.106924" @default.
- W4281657029 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35671603" @default.
- W4281657029 hasPublicationYear "2022" @default.
- W4281657029 type Work @default.
- W4281657029 citedByCount "17" @default.
- W4281657029 countsByYear W42816570292022 @default.
- W4281657029 countsByYear W42816570292023 @default.
- W4281657029 crossrefType "journal-article" @default.
- W4281657029 hasAuthorship W4281657029A5001141933 @default.
- W4281657029 hasAuthorship W4281657029A5004739483 @default.
- W4281657029 hasAuthorship W4281657029A5028167410 @default.
- W4281657029 hasAuthorship W4281657029A5039508181 @default.
- W4281657029 hasAuthorship W4281657029A5062306821 @default.
- W4281657029 hasAuthorship W4281657029A5072381481 @default.
- W4281657029 hasConcept C108583219 @default.
- W4281657029 hasConcept C12267149 @default.
- W4281657029 hasConcept C153180895 @default.
- W4281657029 hasConcept C154945302 @default.
- W4281657029 hasConcept C41008148 @default.
- W4281657029 hasConcept C50644808 @default.
- W4281657029 hasConcept C66905080 @default.
- W4281657029 hasConcept C81363708 @default.
- W4281657029 hasConceptScore W4281657029C108583219 @default.
- W4281657029 hasConceptScore W4281657029C12267149 @default.
- W4281657029 hasConceptScore W4281657029C153180895 @default.
- W4281657029 hasConceptScore W4281657029C154945302 @default.
- W4281657029 hasConceptScore W4281657029C41008148 @default.
- W4281657029 hasConceptScore W4281657029C50644808 @default.
- W4281657029 hasConceptScore W4281657029C66905080 @default.
- W4281657029 hasConceptScore W4281657029C81363708 @default.
- W4281657029 hasFunder F4320321001 @default.
- W4281657029 hasFunder F4320322272 @default.
- W4281657029 hasLocation W42816570291 @default.
- W4281657029 hasLocation W42816570292 @default.
- W4281657029 hasOpenAccess W4281657029 @default.
- W4281657029 hasPrimaryLocation W42816570291 @default.
- W4281657029 hasRelatedWork W2731899572 @default.
- W4281657029 hasRelatedWork W2738221750 @default.
- W4281657029 hasRelatedWork W3133861977 @default.
- W4281657029 hasRelatedWork W3156786002 @default.
- W4281657029 hasRelatedWork W4200173597 @default.
- W4281657029 hasRelatedWork W4307635210 @default.
- W4281657029 hasRelatedWork W4312417841 @default.
- W4281657029 hasRelatedWork W4315694979 @default.
- W4281657029 hasRelatedWork W4321369474 @default.
- W4281657029 hasRelatedWork W564581980 @default.
- W4281657029 hasVolume "221" @default.
- W4281657029 isParatext "false" @default.
- W4281657029 isRetracted "false" @default.
- W4281657029 workType "article" @default.