Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197245280> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3197245280 endingPage "6483" @default.
- W3197245280 startingPage "6473" @default.
- W3197245280 abstract "To quickly locate cancer lesions, especially suspected metastatic lesions after gastrectomy, AI algorithms of object detection and semantic segmentation were established. A total of 509 macroscopic images from 381 patients were collected. The RFB-SSD object detection algorithm and ResNet50-PSPNet semantic segmentation algorithm were used. Another 57 macroscopic images from 48 patients were collected for prospective verification. We used mAP as the metrics of object detection. The best mAP was 95.90% with an average of 89.89% in the test set. The mAP reached 92.60% in validation set. We used mIoU for evaluation of semantic segmentation. The best mIoU was 80.97% with an average of 79.26% in the test set. In addition, 81 out of 92 (88.04%) gastric specimens were accurately predicted for the cancer lesion located at the serosa by ResNet50-PSPNet semantic segmentation model. The positive rate and accuracy of AI prediction were different based on cancer invasive depth. The metastatic lymph nodes were predicted in 24 cases by semantic segmentation model. Among them, 18 cases were confirmed by pathology. The predictive accuracy was 75.00%. Our well-trained AI algorithms effectively identified the subtle features of gastric cancer in resected specimens that may be missed by naked eyes. Taken together, AI algorithms could assist clinical doctors quickly locating cancer lesions and improve their work efficiency." @default.
- W3197245280 created "2021-09-13" @default.
- W3197245280 creator A5000114353 @default.
- W3197245280 creator A5013395896 @default.
- W3197245280 creator A5018737741 @default.
- W3197245280 creator A5035729876 @default.
- W3197245280 creator A5037688225 @default.
- W3197245280 creator A5048070937 @default.
- W3197245280 creator A5051133445 @default.
- W3197245280 creator A5062740680 @default.
- W3197245280 creator A5078129260 @default.
- W3197245280 date "2021-01-01" @default.
- W3197245280 modified "2023-10-03" @default.
- W3197245280 title "Tracking cancer lesions on surgical samples of gastric cancer by artificial intelligent algorithms" @default.
- W3197245280 doi "https://doi.org/10.7150/jca.63879" @default.
- W3197245280 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8489126" @default.
- W3197245280 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34659538" @default.
- W3197245280 hasPublicationYear "2021" @default.
- W3197245280 type Work @default.
- W3197245280 sameAs 3197245280 @default.
- W3197245280 citedByCount "3" @default.
- W3197245280 countsByYear W31972452802022 @default.
- W3197245280 countsByYear W31972452802023 @default.
- W3197245280 crossrefType "journal-article" @default.
- W3197245280 hasAuthorship W3197245280A5000114353 @default.
- W3197245280 hasAuthorship W3197245280A5013395896 @default.
- W3197245280 hasAuthorship W3197245280A5018737741 @default.
- W3197245280 hasAuthorship W3197245280A5035729876 @default.
- W3197245280 hasAuthorship W3197245280A5037688225 @default.
- W3197245280 hasAuthorship W3197245280A5048070937 @default.
- W3197245280 hasAuthorship W3197245280A5051133445 @default.
- W3197245280 hasAuthorship W3197245280A5062740680 @default.
- W3197245280 hasAuthorship W3197245280A5078129260 @default.
- W3197245280 hasBestOaLocation W31972452801 @default.
- W3197245280 hasConcept C11413529 @default.
- W3197245280 hasConcept C121608353 @default.
- W3197245280 hasConcept C124504099 @default.
- W3197245280 hasConcept C126322002 @default.
- W3197245280 hasConcept C153180895 @default.
- W3197245280 hasConcept C154945302 @default.
- W3197245280 hasConcept C169903167 @default.
- W3197245280 hasConcept C177264268 @default.
- W3197245280 hasConcept C199360897 @default.
- W3197245280 hasConcept C2776151529 @default.
- W3197245280 hasConcept C2780470880 @default.
- W3197245280 hasConcept C31972630 @default.
- W3197245280 hasConcept C41008148 @default.
- W3197245280 hasConcept C71924100 @default.
- W3197245280 hasConcept C89600930 @default.
- W3197245280 hasConceptScore W3197245280C11413529 @default.
- W3197245280 hasConceptScore W3197245280C121608353 @default.
- W3197245280 hasConceptScore W3197245280C124504099 @default.
- W3197245280 hasConceptScore W3197245280C126322002 @default.
- W3197245280 hasConceptScore W3197245280C153180895 @default.
- W3197245280 hasConceptScore W3197245280C154945302 @default.
- W3197245280 hasConceptScore W3197245280C169903167 @default.
- W3197245280 hasConceptScore W3197245280C177264268 @default.
- W3197245280 hasConceptScore W3197245280C199360897 @default.
- W3197245280 hasConceptScore W3197245280C2776151529 @default.
- W3197245280 hasConceptScore W3197245280C2780470880 @default.
- W3197245280 hasConceptScore W3197245280C31972630 @default.
- W3197245280 hasConceptScore W3197245280C41008148 @default.
- W3197245280 hasConceptScore W3197245280C71924100 @default.
- W3197245280 hasConceptScore W3197245280C89600930 @default.
- W3197245280 hasIssue "21" @default.
- W3197245280 hasLocation W31972452801 @default.
- W3197245280 hasLocation W31972452802 @default.
- W3197245280 hasLocation W31972452803 @default.
- W3197245280 hasOpenAccess W3197245280 @default.
- W3197245280 hasPrimaryLocation W31972452801 @default.
- W3197245280 hasRelatedWork W1485614034 @default.
- W3197245280 hasRelatedWork W2005437358 @default.
- W3197245280 hasRelatedWork W2112454231 @default.
- W3197245280 hasRelatedWork W2517104666 @default.
- W3197245280 hasRelatedWork W2536634271 @default.
- W3197245280 hasRelatedWork W2613186388 @default.
- W3197245280 hasRelatedWork W2734888972 @default.
- W3197245280 hasRelatedWork W2739874619 @default.
- W3197245280 hasRelatedWork W3112953119 @default.
- W3197245280 hasRelatedWork W2187221949 @default.
- W3197245280 hasVolume "12" @default.
- W3197245280 isParatext "false" @default.
- W3197245280 isRetracted "false" @default.
- W3197245280 magId "3197245280" @default.
- W3197245280 workType "article" @default.