Matches in SemOpenAlex for { <https://semopenalex.org/work/W2959557291> ?p ?o ?g. }
- W2959557291 endingPage "100205" @default.
- W2959557291 startingPage "100205" @default.
- W2959557291 abstract "Abstract Background Lung cancer is a leading cause of death worldwide, and its early detection is usually performed with low-dose computed tomography. For lesions suspected of abnormality by CT examination, a cytological diagnosis of lung cells collected by biopsy is first performed. However, atypical cells are the major challenge in malignant lung cell classification for cytotechnologists and cytopathologists. In this study, we aimed to automatize the classification of malignant lung cells from microscopic images using a deep convolutional neural network (DCNN). Method Cytological specimens were prepared with a liquid-based cytology system and stained using the Papanicolaou technique. Images were acquired with a digital still camera attached to a microscope with a 40× objective lens. The original microscopic images were first cropped to obtain image patches with resolution of 224 × 224 pixels. We obtained 306 benign and 315 malignant image patches. To avoid overfitting, 60,000 patch images were generated using data augmentation by applying rotation, flipping, filtering, and color adjustment. DCNN classification was conducted based on a fine-tuned VGG-16 model. We performed patch-based segmentation of malignant regions in the images and evaluated classification performance using threefold cross-validation. Results The classification sensitivity and specificity were 89.3 and 83.3%, respectively, reaching a performance comparable to that of a cytopathologist. Using the gradient-weighted class activation mapping, we visualized the DCNN identification performance while the network searched for typical benign and malignant cells in images for classification. Conclusions: The proposed method can be useful for accurate and automatic classification of lung cells from pulmonary cytological images." @default.
- W2959557291 created "2019-07-23" @default.
- W2959557291 creator A5006717260 @default.
- W2959557291 creator A5009725511 @default.
- W2959557291 creator A5014764863 @default.
- W2959557291 creator A5027406783 @default.
- W2959557291 creator A5032404324 @default.
- W2959557291 creator A5033914337 @default.
- W2959557291 creator A5049262522 @default.
- W2959557291 creator A5058885400 @default.
- W2959557291 creator A5083081446 @default.
- W2959557291 date "2019-01-01" @default.
- W2959557291 modified "2023-10-18" @default.
- W2959557291 title "Automated classification of benign and malignant cells from lung cytological images using deep convolutional neural network" @default.
- W2959557291 cites W130099911 @default.
- W2959557291 cites W15765066 @default.
- W2959557291 cites W2037451751 @default.
- W2959557291 cites W2068059460 @default.
- W2959557291 cites W2080457512 @default.
- W2959557291 cites W2090667737 @default.
- W2959557291 cites W2127074647 @default.
- W2959557291 cites W2127710322 @default.
- W2959557291 cites W2143701388 @default.
- W2959557291 cites W2200290088 @default.
- W2959557291 cites W2307535535 @default.
- W2959557291 cites W2383601426 @default.
- W2959557291 cites W2401520370 @default.
- W2959557291 cites W2761290139 @default.
- W2959557291 cites W2883683269 @default.
- W2959557291 cites W2919115771 @default.
- W2959557291 cites W3102737931 @default.
- W2959557291 cites W4242036753 @default.
- W2959557291 doi "https://doi.org/10.1016/j.imu.2019.100205" @default.
- W2959557291 hasPublicationYear "2019" @default.
- W2959557291 type Work @default.
- W2959557291 sameAs 2959557291 @default.
- W2959557291 citedByCount "50" @default.
- W2959557291 countsByYear W29595572912019 @default.
- W2959557291 countsByYear W29595572912020 @default.
- W2959557291 countsByYear W29595572912021 @default.
- W2959557291 countsByYear W29595572912022 @default.
- W2959557291 countsByYear W29595572912023 @default.
- W2959557291 crossrefType "journal-article" @default.
- W2959557291 hasAuthorship W2959557291A5006717260 @default.
- W2959557291 hasAuthorship W2959557291A5009725511 @default.
- W2959557291 hasAuthorship W2959557291A5014764863 @default.
- W2959557291 hasAuthorship W2959557291A5027406783 @default.
- W2959557291 hasAuthorship W2959557291A5032404324 @default.
- W2959557291 hasAuthorship W2959557291A5033914337 @default.
- W2959557291 hasAuthorship W2959557291A5049262522 @default.
- W2959557291 hasAuthorship W2959557291A5058885400 @default.
- W2959557291 hasAuthorship W2959557291A5083081446 @default.
- W2959557291 hasBestOaLocation W29595572911 @default.
- W2959557291 hasConcept C108583219 @default.
- W2959557291 hasConcept C115961682 @default.
- W2959557291 hasConcept C121608353 @default.
- W2959557291 hasConcept C126322002 @default.
- W2959557291 hasConcept C126838900 @default.
- W2959557291 hasConcept C142724271 @default.
- W2959557291 hasConcept C153180895 @default.
- W2959557291 hasConcept C154945302 @default.
- W2959557291 hasConcept C2777714996 @default.
- W2959557291 hasConcept C3019684167 @default.
- W2959557291 hasConcept C41008148 @default.
- W2959557291 hasConcept C50644808 @default.
- W2959557291 hasConcept C71924100 @default.
- W2959557291 hasConcept C75294576 @default.
- W2959557291 hasConcept C81363708 @default.
- W2959557291 hasConceptScore W2959557291C108583219 @default.
- W2959557291 hasConceptScore W2959557291C115961682 @default.
- W2959557291 hasConceptScore W2959557291C121608353 @default.
- W2959557291 hasConceptScore W2959557291C126322002 @default.
- W2959557291 hasConceptScore W2959557291C126838900 @default.
- W2959557291 hasConceptScore W2959557291C142724271 @default.
- W2959557291 hasConceptScore W2959557291C153180895 @default.
- W2959557291 hasConceptScore W2959557291C154945302 @default.
- W2959557291 hasConceptScore W2959557291C2777714996 @default.
- W2959557291 hasConceptScore W2959557291C3019684167 @default.
- W2959557291 hasConceptScore W2959557291C41008148 @default.
- W2959557291 hasConceptScore W2959557291C50644808 @default.
- W2959557291 hasConceptScore W2959557291C71924100 @default.
- W2959557291 hasConceptScore W2959557291C75294576 @default.
- W2959557291 hasConceptScore W2959557291C81363708 @default.
- W2959557291 hasFunder F4320320912 @default.
- W2959557291 hasLocation W29595572911 @default.
- W2959557291 hasOpenAccess W2959557291 @default.
- W2959557291 hasPrimaryLocation W29595572911 @default.
- W2959557291 hasRelatedWork W2084220915 @default.
- W2959557291 hasRelatedWork W2732542196 @default.
- W2959557291 hasRelatedWork W2738221750 @default.
- W2959557291 hasRelatedWork W2766604260 @default.
- W2959557291 hasRelatedWork W3018756076 @default.
- W2959557291 hasRelatedWork W3156786002 @default.
- W2959557291 hasRelatedWork W3189091156 @default.
- W2959557291 hasRelatedWork W4285815555 @default.
- W2959557291 hasRelatedWork W4309224979 @default.
- W2959557291 hasRelatedWork W564581980 @default.
- W2959557291 hasVolume "16" @default.