FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167514989> ?p ?o ?g. }

• W3167514989 endingPage "1911" @default.
• W3167514989 startingPage "1901" @default.
• W3167514989 abstract "Detection of nodal micrometastasis (tumor size: 0.2-2.0 mm) is challenging for pathologists due to the small size of metastatic foci. Since lymph nodes with micrometastasis are counted as positive nodes, detecting micrometastasis is crucial for accurate pathologic staging of colorectal cancer. Previously, deep learning algorithms developed with manually annotated images performed well in identifying micrometastasis of breast cancer in sentinel lymph nodes. However, the process of manual annotation is labor intensive and time consuming. Multiple instance learning was later used to identify metastatic breast cancer without manual annotation, but its performance appears worse in detecting micrometastasis. Here, we developed a deep learning model using whole-slide images of regional lymph nodes of colorectal cancer with only a slide-level label (either a positive or negative slide). The training, validation, and testing sets included 1963, 219, and 1000 slides, respectively. A supercomputer TAIWANIA 2 was used to train a deep learning model to identify metastasis. At slide level, our algorithm performed well in identifying both macrometastasis (tumor size > 2.0 mm) and micrometastasis with an area under the receiver operating characteristics curve (AUC) of 0.9993 and 0.9956, respectively. Since most of our slides had more than one lymph node, we then tested the performance of our algorithm on 538 single-lymph node images randomly cropped from the testing set. At single-lymph node level, our algorithm maintained good performance in identifying macrometastasis and micrometastasis with an AUC of 0.9944 and 0.9476, respectively. Visualization using class activation mapping confirmed that our model identified nodal metastasis based on areas of tumor cells. Our results demonstrate for the first time that micrometastasis could be detected by deep learning on whole-slide images without manual annotation." @default.
• W3167514989 created "2021-06-22" @default.
• W3167514989 creator A5000223797 @default.
• W3167514989 creator A5035573488 @default.
• W3167514989 creator A5066970526 @default.
• W3167514989 creator A5067389443 @default.
• W3167514989 creator A5068514092 @default.
• W3167514989 creator A5078428149 @default.
• W3167514989 creator A5083581358 @default.
• W3167514989 creator A5087674995 @default.
• W3167514989 creator A5090005647 @default.
• W3167514989 creator A5090726034 @default.
• W3167514989 date "2021-10-01" @default.
• W3167514989 modified "2023-10-18" @default.
• W3167514989 title "Identification of nodal micrometastasis in colorectal cancer using deep learning on annotation-free whole-slide images" @default.
• W3167514989 cites W1499694722 @default.
• W3167514989 cites W2044608166 @default.
• W3167514989 cites W2194775991 @default.
• W3167514989 cites W2295107390 @default.
• W3167514989 cites W2328176404 @default.
• W3167514989 cites W2607075141 @default.
• W3167514989 cites W2772723798 @default.
• W3167514989 cites W2897434820 @default.
• W3167514989 cites W2954996726 @default.
• W3167514989 cites W2956228567 @default.
• W3167514989 cites W2966884791 @default.
• W3167514989 cites W2999091210 @default.
• W3167514989 cites W2999399991 @default.
• W3167514989 cites W3004016611 @default.
• W3167514989 cites W3007110023 @default.
• W3167514989 cites W3007464329 @default.
• W3167514989 cites W3007748798 @default.
• W3167514989 cites W3080854745 @default.
• W3167514989 cites W3132591370 @default.
• W3167514989 cites W3159164887 @default.
• W3167514989 doi "https://doi.org/10.1038/s41379-021-00838-2" @default.
• W3167514989 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8443445" @default.
• W3167514989 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34103664" @default.
• W3167514989 hasPublicationYear "2021" @default.
• W3167514989 type Work @default.
• W3167514989 sameAs 3167514989 @default.
• W3167514989 citedByCount "27" @default.
• W3167514989 countsByYear W31675149892022 @default.
• W3167514989 countsByYear W31675149892023 @default.
• W3167514989 crossrefType "journal-article" @default.
• W3167514989 hasAuthorship W3167514989A5000223797 @default.
• W3167514989 hasAuthorship W3167514989A5035573488 @default.
• W3167514989 hasAuthorship W3167514989A5066970526 @default.
• W3167514989 hasAuthorship W3167514989A5067389443 @default.
• W3167514989 hasAuthorship W3167514989A5068514092 @default.
• W3167514989 hasAuthorship W3167514989A5078428149 @default.
• W3167514989 hasAuthorship W3167514989A5083581358 @default.
• W3167514989 hasAuthorship W3167514989A5087674995 @default.
• W3167514989 hasAuthorship W3167514989A5090005647 @default.
• W3167514989 hasAuthorship W3167514989A5090726034 @default.
• W3167514989 hasBestOaLocation W31675149891 @default.
• W3167514989 hasConcept C121608353 @default.
• W3167514989 hasConcept C126322002 @default.
• W3167514989 hasConcept C126838900 @default.
• W3167514989 hasConcept C142724271 @default.
• W3167514989 hasConcept C2778123414 @default.
• W3167514989 hasConcept C2779720271 @default.
• W3167514989 hasConcept C2780849966 @default.
• W3167514989 hasConcept C526805850 @default.
• W3167514989 hasConcept C530470458 @default.
• W3167514989 hasConcept C71924100 @default.
• W3167514989 hasConceptScore W3167514989C121608353 @default.
• W3167514989 hasConceptScore W3167514989C126322002 @default.
• W3167514989 hasConceptScore W3167514989C126838900 @default.
• W3167514989 hasConceptScore W3167514989C142724271 @default.
• W3167514989 hasConceptScore W3167514989C2778123414 @default.
• W3167514989 hasConceptScore W3167514989C2779720271 @default.
• W3167514989 hasConceptScore W3167514989C2780849966 @default.
• W3167514989 hasConceptScore W3167514989C526805850 @default.
• W3167514989 hasConceptScore W3167514989C530470458 @default.
• W3167514989 hasConceptScore W3167514989C71924100 @default.
• W3167514989 hasFunder F4320322767 @default.
• W3167514989 hasIssue "10" @default.
• W3167514989 hasLocation W31675149891 @default.
• W3167514989 hasLocation W31675149892 @default.
• W3167514989 hasLocation W31675149893 @default.
• W3167514989 hasLocation W31675149894 @default.
• W3167514989 hasOpenAccess W3167514989 @default.
• W3167514989 hasPrimaryLocation W31675149891 @default.
• W3167514989 hasRelatedWork W2008553569 @default.
• W3167514989 hasRelatedWork W2028414386 @default.
• W3167514989 hasRelatedWork W2169217908 @default.
• W3167514989 hasRelatedWork W2364570576 @default.
• W3167514989 hasRelatedWork W2982319616 @default.
• W3167514989 hasRelatedWork W3030901629 @default.
• W3167514989 hasRelatedWork W3031238721 @default.
• W3167514989 hasRelatedWork W4361257721 @default.
• W3167514989 hasRelatedWork W78011566 @default.
• W3167514989 hasRelatedWork W3028931502 @default.
• W3167514989 hasVolume "34" @default.
• W3167514989 isParatext "false" @default.
• W3167514989 isRetracted "false" @default.
• W3167514989 magId "3167514989" @default.

• next