Matches in SemOpenAlex for { <https://semopenalex.org/work/W3109007209> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3109007209 endingPage "47" @default.
- W3109007209 startingPage "36" @default.
- W3109007209 abstract "The performance of a computer-aided automated diagnosis system of lung cancer from Computed Tomography (CT) volumetric images greatly depends on the accurate detection and segmentation of tumor regions. In this paper, we present Recurrent 3D-DenseUNet, a novel deep learning based architecture for volumetric lung tumor segmentation from CT scans. The proposed architecture consists of a 3D encoder block that learns to extract fine-grained spatial and coarse-grained temporal features, a recurrent block of multiple Convolutional Long Short-Term Memory (ConvLSTM) layers to extract fine-grained spatio-temporal information, and finally a 3D decoder block to reconstruct the desired volume segmentation masks from the latent feature space. The encoder and decoder blocks consist of several 3D-convolutional layers that are densely connected among themselves so that necessary feature aggregation can occur throughout the network. During prediction, we apply selective thresholding followed by morphological operation, on top of the network prediction, to better differentiate between tumorous and non-tumorous image-slices, which shows more promise than only thresholding-based approaches. We train and test our network on the NSCLC-Radiomics dataset of 300 patients, provided by The Cancer Imaging Archive (TCIA) for the 2018 IEEE VIP Cup. Moreover, we perform an extensive ablation study of different loss functions in practice for this task. The proposed network outperforms other state-of-the-art 3D segmentation architectures with an average dice score of 0.7228." @default.
- W3109007209 created "2020-12-07" @default.
- W3109007209 creator A5000538706 @default.
- W3109007209 creator A5028231939 @default.
- W3109007209 creator A5030447120 @default.
- W3109007209 creator A5031853573 @default.
- W3109007209 creator A5064666806 @default.
- W3109007209 date "2020-01-01" @default.
- W3109007209 modified "2023-10-17" @default.
- W3109007209 title "Lung Cancer Tumor Region Segmentation Using Recurrent 3D-DenseUNet" @default.
- W3109007209 cites W1901129140 @default.
- W3109007209 cites W1988160404 @default.
- W3109007209 cites W2061757011 @default.
- W3109007209 cites W2064675550 @default.
- W3109007209 cites W2083927153 @default.
- W3109007209 cites W2128739912 @default.
- W3109007209 cites W2211483859 @default.
- W3109007209 cites W2343144365 @default.
- W3109007209 cites W2464708700 @default.
- W3109007209 cites W2587787457 @default.
- W3109007209 cites W2774479194 @default.
- W3109007209 cites W2793444752 @default.
- W3109007209 cites W2907772920 @default.
- W3109007209 cites W2936495845 @default.
- W3109007209 cites W2954996726 @default.
- W3109007209 cites W2962914239 @default.
- W3109007209 cites W2963351448 @default.
- W3109007209 cites W2963446712 @default.
- W3109007209 cites W2964227007 @default.
- W3109007209 cites W2980848734 @default.
- W3109007209 cites W3013349709 @default.
- W3109007209 doi "https://doi.org/10.1007/978-3-030-62469-9_4" @default.
- W3109007209 hasPublicationYear "2020" @default.
- W3109007209 type Work @default.
- W3109007209 sameAs 3109007209 @default.
- W3109007209 citedByCount "10" @default.
- W3109007209 countsByYear W31090072092022 @default.
- W3109007209 countsByYear W31090072092023 @default.
- W3109007209 crossrefType "book-chapter" @default.
- W3109007209 hasAuthorship W3109007209A5000538706 @default.
- W3109007209 hasAuthorship W3109007209A5028231939 @default.
- W3109007209 hasAuthorship W3109007209A5030447120 @default.
- W3109007209 hasAuthorship W3109007209A5031853573 @default.
- W3109007209 hasAuthorship W3109007209A5064666806 @default.
- W3109007209 hasBestOaLocation W31090072092 @default.
- W3109007209 hasConcept C108583219 @default.
- W3109007209 hasConcept C111919701 @default.
- W3109007209 hasConcept C115961682 @default.
- W3109007209 hasConcept C118505674 @default.
- W3109007209 hasConcept C138885662 @default.
- W3109007209 hasConcept C153180895 @default.
- W3109007209 hasConcept C154945302 @default.
- W3109007209 hasConcept C191178318 @default.
- W3109007209 hasConcept C2524010 @default.
- W3109007209 hasConcept C2776401178 @default.
- W3109007209 hasConcept C2777210771 @default.
- W3109007209 hasConcept C31972630 @default.
- W3109007209 hasConcept C33923547 @default.
- W3109007209 hasConcept C41008148 @default.
- W3109007209 hasConcept C41895202 @default.
- W3109007209 hasConcept C81363708 @default.
- W3109007209 hasConcept C89600930 @default.
- W3109007209 hasConceptScore W3109007209C108583219 @default.
- W3109007209 hasConceptScore W3109007209C111919701 @default.
- W3109007209 hasConceptScore W3109007209C115961682 @default.
- W3109007209 hasConceptScore W3109007209C118505674 @default.
- W3109007209 hasConceptScore W3109007209C138885662 @default.
- W3109007209 hasConceptScore W3109007209C153180895 @default.
- W3109007209 hasConceptScore W3109007209C154945302 @default.
- W3109007209 hasConceptScore W3109007209C191178318 @default.
- W3109007209 hasConceptScore W3109007209C2524010 @default.
- W3109007209 hasConceptScore W3109007209C2776401178 @default.
- W3109007209 hasConceptScore W3109007209C2777210771 @default.
- W3109007209 hasConceptScore W3109007209C31972630 @default.
- W3109007209 hasConceptScore W3109007209C33923547 @default.
- W3109007209 hasConceptScore W3109007209C41008148 @default.
- W3109007209 hasConceptScore W3109007209C41895202 @default.
- W3109007209 hasConceptScore W3109007209C81363708 @default.
- W3109007209 hasConceptScore W3109007209C89600930 @default.
- W3109007209 hasLocation W31090072091 @default.
- W3109007209 hasLocation W31090072092 @default.
- W3109007209 hasOpenAccess W3109007209 @default.
- W3109007209 hasPrimaryLocation W31090072091 @default.
- W3109007209 hasRelatedWork W1542224353 @default.
- W3109007209 hasRelatedWork W1661087619 @default.
- W3109007209 hasRelatedWork W2014501910 @default.
- W3109007209 hasRelatedWork W2953058328 @default.
- W3109007209 hasRelatedWork W3029198973 @default.
- W3109007209 hasRelatedWork W3133861977 @default.
- W3109007209 hasRelatedWork W3167935049 @default.
- W3109007209 hasRelatedWork W3193565141 @default.
- W3109007209 hasRelatedWork W4226493464 @default.
- W3109007209 hasRelatedWork W4312417841 @default.
- W3109007209 isParatext "false" @default.
- W3109007209 isRetracted "false" @default.
- W3109007209 magId "3109007209" @default.
- W3109007209 workType "book-chapter" @default.