Matches in SemOpenAlex for { <https://semopenalex.org/work/W3123409890> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W3123409890 endingPage "124" @default.
- W3123409890 startingPage "118" @default.
- W3123409890 abstract "Background Patients with hereditary diffuse gastric cancer often undergo prophylactic gastrectomy to minimize cancer risk. Because intramucosal poorly cohesive carcinomas in this setting are typically not grossly visible, many pathologists assess the entire gastrectomy specimen microscopically. With 150 or more slides per case, this is a major time burden for pathologists. This study utilizes deep learning methods to analyze digitized slides and detect regions of carcinoma. Materials and methods Prophylactic gastrectomy specimens from seven patients with germline CDH1 mutations were analyzed (five for training/validation and two for testing, with a total of 133 tumor foci). All hematoxylin and eosin slides containing cancer foci were digitally scanned, and patches of size 256×256 pixels were randomly extracted from regions of cancer as well as from regions of normal background tissue, resulting in 15,851 images for training/validation and 970 images for testing. A model with DenseNet-169 architecture was trained for 150 epochs, then evaluated on images from the test set. External validation was conducted on 814 images scanned at an outside institution. Results On individual patches, the trained model achieved a receiver operating characteristic (ROC) area under the curve (AUC) of 0.9986. This enabled it to maintain a sensitivity of 90% with a false-positive rate of less than 0.1%. On the external validation dataset, the model achieved a similar ROC AUC of 0.9984. On whole slide images, the network detected 100% of tumor foci and correctly eliminated an average of 99.9% of the non-cancer slide area from consideration. Conclusion Overall, our model shows encouraging progress towards computer-assisted diagnosis of hereditary diffuse gastric cancer." @default.
- W3123409890 created "2021-02-01" @default.
- W3123409890 creator A5013567823 @default.
- W3123409890 creator A5053845155 @default.
- W3123409890 creator A5071627343 @default.
- W3123409890 date "2021-03-15" @default.
- W3123409890 modified "2023-10-12" @default.
- W3123409890 title "Deep learning for computer-assisted diagnosis of hereditary diffuse gastric cancer" @default.
- W3123409890 cites W2557738935 @default.
- W3123409890 cites W2789755511 @default.
- W3123409890 cites W2804905867 @default.
- W3123409890 cites W2893813411 @default.
- W3123409890 cites W2897434820 @default.
- W3123409890 cites W2952481429 @default.
- W3123409890 cites W2952800276 @default.
- W3123409890 cites W2956228567 @default.
- W3123409890 cites W2963446712 @default.
- W3123409890 doi "https://doi.org/10.4132/jptm.2020.12.22" @default.
- W3123409890 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7987520" @default.
- W3123409890 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33472333" @default.
- W3123409890 hasPublicationYear "2021" @default.
- W3123409890 type Work @default.
- W3123409890 sameAs 3123409890 @default.
- W3123409890 citedByCount "7" @default.
- W3123409890 countsByYear W31234098902021 @default.
- W3123409890 countsByYear W31234098902022 @default.
- W3123409890 countsByYear W31234098902023 @default.
- W3123409890 crossrefType "journal-article" @default.
- W3123409890 hasAuthorship W3123409890A5013567823 @default.
- W3123409890 hasAuthorship W3123409890A5053845155 @default.
- W3123409890 hasAuthorship W3123409890A5071627343 @default.
- W3123409890 hasBestOaLocation W31234098901 @default.
- W3123409890 hasConcept C121608353 @default.
- W3123409890 hasConcept C126322002 @default.
- W3123409890 hasConcept C142724271 @default.
- W3123409890 hasConcept C143998085 @default.
- W3123409890 hasConcept C71924100 @default.
- W3123409890 hasConceptScore W3123409890C121608353 @default.
- W3123409890 hasConceptScore W3123409890C126322002 @default.
- W3123409890 hasConceptScore W3123409890C142724271 @default.
- W3123409890 hasConceptScore W3123409890C143998085 @default.
- W3123409890 hasConceptScore W3123409890C71924100 @default.
- W3123409890 hasIssue "2" @default.
- W3123409890 hasLocation W31234098901 @default.
- W3123409890 hasLocation W31234098902 @default.
- W3123409890 hasOpenAccess W3123409890 @default.
- W3123409890 hasPrimaryLocation W31234098901 @default.
- W3123409890 hasRelatedWork W2016512228 @default.
- W3123409890 hasRelatedWork W2084898420 @default.
- W3123409890 hasRelatedWork W2313296927 @default.
- W3123409890 hasRelatedWork W2365364931 @default.
- W3123409890 hasRelatedWork W2418638721 @default.
- W3123409890 hasRelatedWork W2526763385 @default.
- W3123409890 hasRelatedWork W2766518664 @default.
- W3123409890 hasRelatedWork W2950054659 @default.
- W3123409890 hasRelatedWork W2989971117 @default.
- W3123409890 hasRelatedWork W4324259137 @default.
- W3123409890 hasVolume "55" @default.
- W3123409890 isParatext "false" @default.
- W3123409890 isRetracted "false" @default.
- W3123409890 magId "3123409890" @default.
- W3123409890 workType "article" @default.