Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201638953> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3201638953 endingPage "35" @default.
- W3201638953 startingPage "25" @default.
- W3201638953 abstract "Pancreas CT segmentation offers promise at understanding the structural manifestation of metabolic conditions. To date, the medical primary record of conditions that impact the pancreas is in the electronic health record (EHR) in terms of diagnostic phenotype data (e.g., ICD-10 codes). We posit that similar structural phenotypes could be revealed by studying subjects with similar medical outcomes. Segmentation is mainly driven by imaging data, but this direct approach may not consider differing canonical appearances with different underlying conditions (e.g., pancreatic atrophy versus pancreatic cysts). To this end, we exploit clinical features from EHR data to complement image features for enhancing the pancreas segmentation, especially in high-risk outcomes. Specifically, we propose, to the best of our knowledge, the first phenotype embedding model for pancreas segmentation by predicting representatives that share similar comorbidities. Such an embedding strategy can adaptively refine the segmentation outcome based on the discriminative contexts distilled from clinical features. Experiments with 2000 patients’ EHR data and 300 CT images with the healthy pancreas, type II diabetes, and pancreatitis subjects show that segmentation by predictive phenotyping significantly improves performance over state-of-the-arts (Dice score 0.775 to 0.791, (p < 0.05), Wilcoxon signed-rank test). The proposed method additionally achieves superior performance on two public testing datasets, BTCV MICCAI Challenge 2015 and TCIA pancreas CT. Our approach provides a promising direction of advancing segmentation with phenotype features while without requiring EHR data as input during testing." @default.
- W3201638953 created "2021-09-27" @default.
- W3201638953 creator A5003076238 @default.
- W3201638953 creator A5004320806 @default.
- W3201638953 creator A5037478865 @default.
- W3201638953 creator A5048972725 @default.
- W3201638953 creator A5051208155 @default.
- W3201638953 creator A5059275651 @default.
- W3201638953 creator A5060337434 @default.
- W3201638953 creator A5063409605 @default.
- W3201638953 creator A5067191302 @default.
- W3201638953 creator A5067640436 @default.
- W3201638953 creator A5075735203 @default.
- W3201638953 creator A5078051038 @default.
- W3201638953 date "2021-01-01" @default.
- W3201638953 modified "2023-09-28" @default.
- W3201638953 title "Pancreas CT Segmentation by Predictive Phenotyping" @default.
- W3201638953 cites W2017573704 @default.
- W3201638953 cites W2061326496 @default.
- W3201638953 cites W2067794541 @default.
- W3201638953 cites W2110952210 @default.
- W3201638953 cites W2460902346 @default.
- W3201638953 cites W2464708700 @default.
- W3201638953 cites W2618237340 @default.
- W3201638953 cites W2705158815 @default.
- W3201638953 cites W2742491462 @default.
- W3201638953 cites W2792014895 @default.
- W3201638953 cites W2886667086 @default.
- W3201638953 cites W2950722229 @default.
- W3201638953 cites W3034781633 @default.
- W3201638953 cites W3090426973 @default.
- W3201638953 cites W3112256294 @default.
- W3201638953 cites W3128566160 @default.
- W3201638953 cites W855272188 @default.
- W3201638953 doi "https://doi.org/10.1007/978-3-030-87193-2_3" @default.
- W3201638953 hasPublicationYear "2021" @default.
- W3201638953 type Work @default.
- W3201638953 sameAs 3201638953 @default.
- W3201638953 citedByCount "2" @default.
- W3201638953 countsByYear W32016389532022 @default.
- W3201638953 crossrefType "book-chapter" @default.
- W3201638953 hasAuthorship W3201638953A5003076238 @default.
- W3201638953 hasAuthorship W3201638953A5004320806 @default.
- W3201638953 hasAuthorship W3201638953A5037478865 @default.
- W3201638953 hasAuthorship W3201638953A5048972725 @default.
- W3201638953 hasAuthorship W3201638953A5051208155 @default.
- W3201638953 hasAuthorship W3201638953A5059275651 @default.
- W3201638953 hasAuthorship W3201638953A5060337434 @default.
- W3201638953 hasAuthorship W3201638953A5063409605 @default.
- W3201638953 hasAuthorship W3201638953A5067191302 @default.
- W3201638953 hasAuthorship W3201638953A5067640436 @default.
- W3201638953 hasAuthorship W3201638953A5075735203 @default.
- W3201638953 hasAuthorship W3201638953A5078051038 @default.
- W3201638953 hasConcept C154945302 @default.
- W3201638953 hasConcept C41008148 @default.
- W3201638953 hasConcept C89600930 @default.
- W3201638953 hasConceptScore W3201638953C154945302 @default.
- W3201638953 hasConceptScore W3201638953C41008148 @default.
- W3201638953 hasConceptScore W3201638953C89600930 @default.
- W3201638953 hasLocation W32016389531 @default.
- W3201638953 hasOpenAccess W3201638953 @default.
- W3201638953 hasPrimaryLocation W32016389531 @default.
- W3201638953 hasRelatedWork W2134924024 @default.
- W3201638953 hasRelatedWork W2138214894 @default.
- W3201638953 hasRelatedWork W2358941527 @default.
- W3201638953 hasRelatedWork W2361006516 @default.
- W3201638953 hasRelatedWork W2387675639 @default.
- W3201638953 hasRelatedWork W2394327295 @default.
- W3201638953 hasRelatedWork W2895616727 @default.
- W3201638953 hasRelatedWork W2954384599 @default.
- W3201638953 hasRelatedWork W3107474891 @default.
- W3201638953 hasRelatedWork W3170495089 @default.
- W3201638953 isParatext "false" @default.
- W3201638953 isRetracted "false" @default.
- W3201638953 magId "3201638953" @default.
- W3201638953 workType "book-chapter" @default.