Matches in SemOpenAlex for { <https://semopenalex.org/work/W2743457443> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2743457443 abstract "Machine learning has been widely used for solving various classification problems in biomedical research field due to its strength in handling massive data set systematically. In this paper, a feasible way of breast cancer localization via machine learning is presented with a preliminary result for 10 cancerous breast tissue samples (600 μm diameter and 8 μm thickness). Using a custom-built microscope-compatible microindentation system, 500 indentation points per sample were indented to a depth of 2 μm at 20 μm interval. Each indentation point is labeled as either `Normal' or `Cancerous' according to the corresponding pathological image that was annotated appropriately by a certified pathologist. We applied the support vector machine (SVM) algorithm, which is one of the supervised machine learning technique to validate the annotations by a pathologist. The tissue elasticity value which is the actual data set for machine learning is locally determined by a non-linear contact model for a spherical tip, using the contact force and the indentation depth information collected during the indentation experiment. With soft-margin SVM which is for not linearly separable data, each tissue sample is tested while the other 9 tissue samples are used for training like 10-fold cross-validation. Classification accuracy for the entire breast tissue samples was obtained as 76.20% ± 9.28%, which shows that this is a promising approach when making allowance for classification with a single parameter." @default.
- W2743457443 created "2017-08-17" @default.
- W2743457443 creator A5011203297 @default.
- W2743457443 creator A5047893446 @default.
- W2743457443 date "2017-07-01" @default.
- W2743457443 modified "2023-10-16" @default.
- W2743457443 title "Machine learning approach for breast cancer localization" @default.
- W2743457443 cites W1845365256 @default.
- W2743457443 cites W1901616594 @default.
- W2743457443 cites W1971040113 @default.
- W2743457443 cites W1976070030 @default.
- W2743457443 cites W1989095124 @default.
- W2743457443 cites W1989247998 @default.
- W2743457443 cites W2004320486 @default.
- W2743457443 cites W2010365793 @default.
- W2743457443 cites W2023667904 @default.
- W2743457443 cites W2032228491 @default.
- W2743457443 cites W2049420719 @default.
- W2743457443 cites W2056137745 @default.
- W2743457443 cites W2056554708 @default.
- W2743457443 cites W2059586561 @default.
- W2743457443 cites W2071027495 @default.
- W2743457443 cites W2088097413 @default.
- W2743457443 cites W2101728107 @default.
- W2743457443 cites W2104479723 @default.
- W2743457443 cites W2106733357 @default.
- W2743457443 cites W2116208747 @default.
- W2743457443 cites W2140494000 @default.
- W2743457443 cites W2141533839 @default.
- W2743457443 cites W2203717837 @default.
- W2743457443 cites W2220633748 @default.
- W2743457443 cites W2318102414 @default.
- W2743457443 cites W2407822856 @default.
- W2743457443 cites W2413267852 @default.
- W2743457443 cites W4296886862 @default.
- W2743457443 doi "https://doi.org/10.1109/marss.2017.8001925" @default.
- W2743457443 hasPublicationYear "2017" @default.
- W2743457443 type Work @default.
- W2743457443 sameAs 2743457443 @default.
- W2743457443 citedByCount "7" @default.
- W2743457443 countsByYear W27434574432019 @default.
- W2743457443 countsByYear W27434574432020 @default.
- W2743457443 countsByYear W27434574432021 @default.
- W2743457443 countsByYear W27434574432023 @default.
- W2743457443 crossrefType "proceedings-article" @default.
- W2743457443 hasAuthorship W2743457443A5011203297 @default.
- W2743457443 hasAuthorship W2743457443A5047893446 @default.
- W2743457443 hasConcept C119857082 @default.
- W2743457443 hasConcept C121608353 @default.
- W2743457443 hasConcept C12267149 @default.
- W2743457443 hasConcept C126322002 @default.
- W2743457443 hasConcept C136229726 @default.
- W2743457443 hasConcept C153180895 @default.
- W2743457443 hasConcept C154945302 @default.
- W2743457443 hasConcept C199360897 @default.
- W2743457443 hasConcept C2780902562 @default.
- W2743457443 hasConcept C41008148 @default.
- W2743457443 hasConcept C530470458 @default.
- W2743457443 hasConcept C71924100 @default.
- W2743457443 hasConceptScore W2743457443C119857082 @default.
- W2743457443 hasConceptScore W2743457443C121608353 @default.
- W2743457443 hasConceptScore W2743457443C12267149 @default.
- W2743457443 hasConceptScore W2743457443C126322002 @default.
- W2743457443 hasConceptScore W2743457443C136229726 @default.
- W2743457443 hasConceptScore W2743457443C153180895 @default.
- W2743457443 hasConceptScore W2743457443C154945302 @default.
- W2743457443 hasConceptScore W2743457443C199360897 @default.
- W2743457443 hasConceptScore W2743457443C2780902562 @default.
- W2743457443 hasConceptScore W2743457443C41008148 @default.
- W2743457443 hasConceptScore W2743457443C530470458 @default.
- W2743457443 hasConceptScore W2743457443C71924100 @default.
- W2743457443 hasLocation W27434574431 @default.
- W2743457443 hasOpenAccess W2743457443 @default.
- W2743457443 hasPrimaryLocation W27434574431 @default.
- W2743457443 hasRelatedWork W2041399278 @default.
- W2743457443 hasRelatedWork W2056016498 @default.
- W2743457443 hasRelatedWork W2136184105 @default.
- W2743457443 hasRelatedWork W2160451891 @default.
- W2743457443 hasRelatedWork W2336974148 @default.
- W2743457443 hasRelatedWork W2389470892 @default.
- W2743457443 hasRelatedWork W3013515612 @default.
- W2743457443 hasRelatedWork W3195168932 @default.
- W2743457443 hasRelatedWork W2187500075 @default.
- W2743457443 hasRelatedWork W2345184372 @default.
- W2743457443 isParatext "false" @default.
- W2743457443 isRetracted "false" @default.
- W2743457443 magId "2743457443" @default.
- W2743457443 workType "article" @default.