Matches in SemOpenAlex for { <https://semopenalex.org/work/W2887995812> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2887995812 endingPage "299" @default.
- W2887995812 startingPage "292" @default.
- W2887995812 abstract "We describe a new multiresolution “nested encoder-decoder” convolutional network architecture and use it to annotate morphological patterns in reflectance confocal microscopy (RCM) images of human skin for aiding cancer diagnosis. Skin cancers are the most common types of cancers, melanoma being the most deadly among them. RCM is an effective, non-invasive pre-screening tool for skin cancer diagnosis, with the required cellular resolution. However, images are complex, low-contrast, and highly variable, so that it requires months to years of expert-level training for clinicians to be able to make accurate assessments. In this paper we address classifying 4 key clinically important structural/textural patterns in RCM images. The occurrence and morphology of these patterns are used by clinicians for diagnosis of melanomas. The large size of RCM images, the large variance of pattern size, the large scale range over which patterns appear, the class imbalance in collected images, and the lack of fully-labelled images all make this a challenging problem to address, even with automated machine learning tools. We designed a novel nested U-net architecture to cope with these challenges, and a selective loss function to handle partial labeling. Trained and tested on 56 melanoma-suspicious, partially labelled, 12k $$times $$ 12k pixel images, our network automatically annotated RCM images for these diagnostic patterns with high sensitivity and specificity, providing consistent labels for unlabelled sections of the test images. We believe that providing such annotation in a fast manner will aid clinicians in achieving diagnostic accuracy, and perhaps more important, dramatically facilitate clinical training, thus enabling much more rapid adoption of RCM into widespread clinical use process. In addition our adaptation of U-net architecture provides an intrinsically multiresolution deep network that may be useful in other challenging biomedical image analysis applications." @default.
- W2887995812 created "2018-08-31" @default.
- W2887995812 creator A5007171627 @default.
- W2887995812 creator A5009400514 @default.
- W2887995812 creator A5011252033 @default.
- W2887995812 creator A5042038501 @default.
- W2887995812 creator A5053808736 @default.
- W2887995812 creator A5074048076 @default.
- W2887995812 creator A5079980080 @default.
- W2887995812 date "2018-01-01" @default.
- W2887995812 modified "2023-10-13" @default.
- W2887995812 title "A Multiresolution Convolutional Neural Network with Partial Label Training for Annotating Reflectance Confocal Microscopy Images of Skin" @default.
- W2887995812 cites W1901129140 @default.
- W2887995812 cites W1903029394 @default.
- W2887995812 cites W1987869189 @default.
- W2887995812 cites W2167835377 @default.
- W2887995812 cites W2539662274 @default.
- W2887995812 cites W2563705555 @default.
- W2887995812 cites W2604785265 @default.
- W2887995812 cites W2607367829 @default.
- W2887995812 cites W2620722267 @default.
- W2887995812 cites W2963881378 @default.
- W2887995812 cites W3100175091 @default.
- W2887995812 doi "https://doi.org/10.1007/978-3-030-00934-2_33" @default.
- W2887995812 hasPublicationYear "2018" @default.
- W2887995812 type Work @default.
- W2887995812 sameAs 2887995812 @default.
- W2887995812 citedByCount "8" @default.
- W2887995812 countsByYear W28879958122019 @default.
- W2887995812 countsByYear W28879958122020 @default.
- W2887995812 countsByYear W28879958122021 @default.
- W2887995812 countsByYear W28879958122022 @default.
- W2887995812 countsByYear W28879958122023 @default.
- W2887995812 crossrefType "book-chapter" @default.
- W2887995812 hasAuthorship W2887995812A5007171627 @default.
- W2887995812 hasAuthorship W2887995812A5009400514 @default.
- W2887995812 hasAuthorship W2887995812A5011252033 @default.
- W2887995812 hasAuthorship W2887995812A5042038501 @default.
- W2887995812 hasAuthorship W2887995812A5053808736 @default.
- W2887995812 hasAuthorship W2887995812A5074048076 @default.
- W2887995812 hasAuthorship W2887995812A5079980080 @default.
- W2887995812 hasBestOaLocation W28879958122 @default.
- W2887995812 hasConcept C108583219 @default.
- W2887995812 hasConcept C153180895 @default.
- W2887995812 hasConcept C154945302 @default.
- W2887995812 hasConcept C2777522853 @default.
- W2887995812 hasConcept C31972630 @default.
- W2887995812 hasConcept C41008148 @default.
- W2887995812 hasConcept C81363708 @default.
- W2887995812 hasConceptScore W2887995812C108583219 @default.
- W2887995812 hasConceptScore W2887995812C153180895 @default.
- W2887995812 hasConceptScore W2887995812C154945302 @default.
- W2887995812 hasConceptScore W2887995812C2777522853 @default.
- W2887995812 hasConceptScore W2887995812C31972630 @default.
- W2887995812 hasConceptScore W2887995812C41008148 @default.
- W2887995812 hasConceptScore W2887995812C81363708 @default.
- W2887995812 hasLocation W28879958121 @default.
- W2887995812 hasLocation W28879958122 @default.
- W2887995812 hasOpenAccess W2887995812 @default.
- W2887995812 hasPrimaryLocation W28879958121 @default.
- W2887995812 hasRelatedWork W1975767702 @default.
- W2887995812 hasRelatedWork W3029198973 @default.
- W2887995812 hasRelatedWork W3128797991 @default.
- W2887995812 hasRelatedWork W3133861977 @default.
- W2887995812 hasRelatedWork W3167935049 @default.
- W2887995812 hasRelatedWork W3193565141 @default.
- W2887995812 hasRelatedWork W4226493464 @default.
- W2887995812 hasRelatedWork W4293226380 @default.
- W2887995812 hasRelatedWork W4312417841 @default.
- W2887995812 hasRelatedWork W4375867731 @default.
- W2887995812 isParatext "false" @default.
- W2887995812 isRetracted "false" @default.
- W2887995812 magId "2887995812" @default.
- W2887995812 workType "book-chapter" @default.