Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897013810> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2897013810 abstract "Fine-grained classification of cervical cells into different abnormality levels is of great clinical importance but remains very challenging. Contrary to traditional classification methods that rely on hand-crafted or engineered features, convolution neural network (CNN) can classify cervical cells based on automatically learned deep features. However, CNN in previous studies do not involve cell morphological information, and it is unknown whether morphological features can be directly modeled by CNN to classify cervical cells. This paper presents a CNN-based method that combines cell image appearance with cell morphology for classification of cervical cells in Pap smear. The training cervical cell dataset consists of adaptively re-sampled image patches coarsely centered on the nuclei. Several CNN models (AlexNet, GoogleNet, ResNet and DenseNet) pre-trained on ImageNet dataset were fine-tuned on the cervical dataset for comparison. The proposed method is evaluated on the Herlev cervical dataset by five-fold cross-validation at patient level splitting. Results show that by adding cytoplasm and nucleus masks as raw morphological information into appearance-based CNN learning, higher classification accuracies can be achieved in general. Among the four CNN models, GoogleNet fed with both morphological and appearance information obtains the highest classification accuracies of 94.5% for 2-class classification task and 64.5% for 7-class classification task. Our method demonstrates that combining cervical cell morphology with appearance information can provide improved classification performance, which is clinically important for early diagnosis of cervical dysplastic changes." @default.
- W2897013810 created "2018-10-26" @default.
- W2897013810 creator A5038765418 @default.
- W2897013810 creator A5046695536 @default.
- W2897013810 creator A5053298653 @default.
- W2897013810 creator A5059780651 @default.
- W2897013810 creator A5071171819 @default.
- W2897013810 date "2018-10-14" @default.
- W2897013810 modified "2023-09-23" @default.
- W2897013810 title "Fine-Grained Classification of Cervical Cells Using Morphological and Appearance Based Convolutional Neural Networks" @default.
- W2897013810 cites W1829380873 @default.
- W2897013810 cites W1901129140 @default.
- W2897013810 cites W2003298534 @default.
- W2897013810 cites W2003927787 @default.
- W2897013810 cites W2022274350 @default.
- W2897013810 cites W2034633442 @default.
- W2897013810 cites W2035902235 @default.
- W2897013810 cites W2057836452 @default.
- W2897013810 cites W2059272842 @default.
- W2897013810 cites W2076242843 @default.
- W2897013810 cites W2081719476 @default.
- W2897013810 cites W2089575713 @default.
- W2897013810 cites W2097117768 @default.
- W2897013810 cites W2147800946 @default.
- W2897013810 cites W2156065311 @default.
- W2897013810 cites W2174023915 @default.
- W2897013810 cites W2194775991 @default.
- W2897013810 cites W2253429366 @default.
- W2897013810 cites W2628702118 @default.
- W2897013810 cites W2886281300 @default.
- W2897013810 cites W2949667497 @default.
- W2897013810 cites W2950094539 @default.
- W2897013810 cites W2963446712 @default.
- W2897013810 cites W2963663752 @default.
- W2897013810 cites W3101156210 @default.
- W2897013810 doi "https://doi.org/10.48550/arxiv.1810.06058" @default.
- W2897013810 hasPublicationYear "2018" @default.
- W2897013810 type Work @default.
- W2897013810 sameAs 2897013810 @default.
- W2897013810 citedByCount "1" @default.
- W2897013810 countsByYear W28970138102023 @default.
- W2897013810 crossrefType "posted-content" @default.
- W2897013810 hasAuthorship W2897013810A5038765418 @default.
- W2897013810 hasAuthorship W2897013810A5046695536 @default.
- W2897013810 hasAuthorship W2897013810A5053298653 @default.
- W2897013810 hasAuthorship W2897013810A5059780651 @default.
- W2897013810 hasAuthorship W2897013810A5071171819 @default.
- W2897013810 hasBestOaLocation W28970138101 @default.
- W2897013810 hasConcept C108583219 @default.
- W2897013810 hasConcept C115961682 @default.
- W2897013810 hasConcept C118552586 @default.
- W2897013810 hasConcept C153180895 @default.
- W2897013810 hasConcept C154945302 @default.
- W2897013810 hasConcept C162324750 @default.
- W2897013810 hasConcept C187736073 @default.
- W2897013810 hasConcept C2780451532 @default.
- W2897013810 hasConcept C41008148 @default.
- W2897013810 hasConcept C50965678 @default.
- W2897013810 hasConcept C71924100 @default.
- W2897013810 hasConcept C75294576 @default.
- W2897013810 hasConcept C81363708 @default.
- W2897013810 hasConceptScore W2897013810C108583219 @default.
- W2897013810 hasConceptScore W2897013810C115961682 @default.
- W2897013810 hasConceptScore W2897013810C118552586 @default.
- W2897013810 hasConceptScore W2897013810C153180895 @default.
- W2897013810 hasConceptScore W2897013810C154945302 @default.
- W2897013810 hasConceptScore W2897013810C162324750 @default.
- W2897013810 hasConceptScore W2897013810C187736073 @default.
- W2897013810 hasConceptScore W2897013810C2780451532 @default.
- W2897013810 hasConceptScore W2897013810C41008148 @default.
- W2897013810 hasConceptScore W2897013810C50965678 @default.
- W2897013810 hasConceptScore W2897013810C71924100 @default.
- W2897013810 hasConceptScore W2897013810C75294576 @default.
- W2897013810 hasConceptScore W2897013810C81363708 @default.
- W2897013810 hasLocation W28970138101 @default.
- W2897013810 hasOpenAccess W2897013810 @default.
- W2897013810 hasPrimaryLocation W28970138101 @default.
- W2897013810 hasRelatedWork W2084220915 @default.
- W2897013810 hasRelatedWork W2738221750 @default.
- W2897013810 hasRelatedWork W2766604260 @default.
- W2897013810 hasRelatedWork W2986507176 @default.
- W2897013810 hasRelatedWork W3018756076 @default.
- W2897013810 hasRelatedWork W3156786002 @default.
- W2897013810 hasRelatedWork W3160711233 @default.
- W2897013810 hasRelatedWork W3189091156 @default.
- W2897013810 hasRelatedWork W4309224979 @default.
- W2897013810 hasRelatedWork W564581980 @default.
- W2897013810 isParatext "false" @default.
- W2897013810 isRetracted "false" @default.
- W2897013810 magId "2897013810" @default.
- W2897013810 workType "article" @default.