Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081015625> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3081015625 abstract "Accurate and automated tumor segmentation is highly desired since it has the great potential to increase the efficiency and reproducibility of computing more complete tumor measurements and imaging biomarkers, comparing to (often partial) human measurements. This is probably the only viable means to enable the large-scale clinical oncology patient studies that utilize medical imaging. Deep learning approaches have shown robust segmentation performances for certain types of tumors, e.g., brain tumors in MRI imaging, when a training dataset with plenty of pixel-level fully-annotated tumor images is available. However, more than often, we are facing the challenge that only (very) limited annotations are feasible to acquire, especially for hard tumors. Pancreatic ductal adenocarcinoma (PDAC) segmentation is one of the most challenging tumor segmentation tasks, yet critically important for clinical needs. Previous work on PDAC segmentation is limited to the moderate amounts of annotated patient images (n<300) from venous or venous+arterial phase CT scans. Based on a new self-learning framework, we propose to train the PDAC segmentation model using a much larger quantity of patients (n~=1,000), with a mix of annotated and un-annotated venous or multi-phase CT images. Pseudo annotations are generated by combining two teacher models with different PDAC segmentation specialties on unannotated images, and can be further refined by a teaching assistant model that identifies associated vessels around the pancreas. A student model is trained on both manual and pseudo annotated multi-phase images. Experiment results show that our proposed method provides an absolute improvement of 6.3% Dice score over the strong baseline of nnUNet trained on annotated images, achieving the performance (Dice = 0.71) similar to the inter-observer variability between radiologists." @default.
- W3081015625 created "2020-09-01" @default.
- W3081015625 creator A5002039083 @default.
- W3081015625 creator A5016038454 @default.
- W3081015625 creator A5027768127 @default.
- W3081015625 creator A5031808825 @default.
- W3081015625 creator A5045227579 @default.
- W3081015625 creator A5050613338 @default.
- W3081015625 creator A5075245264 @default.
- W3081015625 creator A5083228843 @default.
- W3081015625 date "2020-08-24" @default.
- W3081015625 modified "2023-09-23" @default.
- W3081015625 title "Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scans" @default.
- W3081015625 cites W1901129140 @default.
- W3081015625 cites W2166737644 @default.
- W3081015625 cites W2413073178 @default.
- W3081015625 cites W2791585271 @default.
- W3081015625 cites W2791680898 @default.
- W3081015625 cites W2893299523 @default.
- W3081015625 cites W2911605224 @default.
- W3081015625 cites W2915126261 @default.
- W3081015625 cites W2928374940 @default.
- W3081015625 cites W2954262888 @default.
- W3081015625 cites W2965994994 @default.
- W3081015625 cites W2966826235 @default.
- W3081015625 cites W2970546341 @default.
- W3081015625 cites W2979458288 @default.
- W3081015625 cites W2979744002 @default.
- W3081015625 cites W2990682087 @default.
- W3081015625 cites W3005060603 @default.
- W3081015625 cites W3035160371 @default.
- W3081015625 doi "https://doi.org/10.48550/arxiv.2008.10652" @default.
- W3081015625 hasPublicationYear "2020" @default.
- W3081015625 type Work @default.
- W3081015625 sameAs 3081015625 @default.
- W3081015625 citedByCount "0" @default.
- W3081015625 crossrefType "posted-content" @default.
- W3081015625 hasAuthorship W3081015625A5002039083 @default.
- W3081015625 hasAuthorship W3081015625A5016038454 @default.
- W3081015625 hasAuthorship W3081015625A5027768127 @default.
- W3081015625 hasAuthorship W3081015625A5031808825 @default.
- W3081015625 hasAuthorship W3081015625A5045227579 @default.
- W3081015625 hasAuthorship W3081015625A5050613338 @default.
- W3081015625 hasAuthorship W3081015625A5075245264 @default.
- W3081015625 hasAuthorship W3081015625A5083228843 @default.
- W3081015625 hasBestOaLocation W30810156251 @default.
- W3081015625 hasConcept C121608353 @default.
- W3081015625 hasConcept C124504099 @default.
- W3081015625 hasConcept C126322002 @default.
- W3081015625 hasConcept C126838900 @default.
- W3081015625 hasConcept C153180895 @default.
- W3081015625 hasConcept C154945302 @default.
- W3081015625 hasConcept C2780210213 @default.
- W3081015625 hasConcept C2781182431 @default.
- W3081015625 hasConcept C2992026798 @default.
- W3081015625 hasConcept C31972630 @default.
- W3081015625 hasConcept C41008148 @default.
- W3081015625 hasConcept C71924100 @default.
- W3081015625 hasConcept C89600930 @default.
- W3081015625 hasConceptScore W3081015625C121608353 @default.
- W3081015625 hasConceptScore W3081015625C124504099 @default.
- W3081015625 hasConceptScore W3081015625C126322002 @default.
- W3081015625 hasConceptScore W3081015625C126838900 @default.
- W3081015625 hasConceptScore W3081015625C153180895 @default.
- W3081015625 hasConceptScore W3081015625C154945302 @default.
- W3081015625 hasConceptScore W3081015625C2780210213 @default.
- W3081015625 hasConceptScore W3081015625C2781182431 @default.
- W3081015625 hasConceptScore W3081015625C2992026798 @default.
- W3081015625 hasConceptScore W3081015625C31972630 @default.
- W3081015625 hasConceptScore W3081015625C41008148 @default.
- W3081015625 hasConceptScore W3081015625C71924100 @default.
- W3081015625 hasConceptScore W3081015625C89600930 @default.
- W3081015625 hasLocation W30810156251 @default.
- W3081015625 hasOpenAccess W3081015625 @default.
- W3081015625 hasPrimaryLocation W30810156251 @default.
- W3081015625 hasRelatedWork W1507266234 @default.
- W3081015625 hasRelatedWork W1669643531 @default.
- W3081015625 hasRelatedWork W1721780360 @default.
- W3081015625 hasRelatedWork W2110230079 @default.
- W3081015625 hasRelatedWork W2117664411 @default.
- W3081015625 hasRelatedWork W2117933325 @default.
- W3081015625 hasRelatedWork W2122581818 @default.
- W3081015625 hasRelatedWork W2159066190 @default.
- W3081015625 hasRelatedWork W2739874619 @default.
- W3081015625 hasRelatedWork W1967061043 @default.
- W3081015625 isParatext "false" @default.
- W3081015625 isRetracted "false" @default.
- W3081015625 magId "3081015625" @default.
- W3081015625 workType "article" @default.