Matches in SemOpenAlex for { <https://semopenalex.org/work/W3170253974> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3170253974 abstract "3D complete renal structures(CRS) segmentation targets on segmenting the kidneys, tumors, renal arteries and veins in one inference. Once successful, it will provide preoperative plans and intraoperative guidance for laparoscopic partial nephrectomy(LPN), playing a key role in the renal cancer treatment. However, no success has been reported in 3D CRS segmentation due to the complex shapes of renal structures, low contrast and large anatomical variation. In this study, we utilize the adversarial ensemble learning and propose Ensemble Multi-condition GAN(EnMcGAN) for 3D CRS segmentation for the first time. Its contribution is three-fold. 1)Inspired by windowing, we propose the multi-windowing committee which divides CTA image into multiple narrow windows with different window centers and widths enhancing the contrast for salient boundaries and soft tissues. And then, it builds an ensemble segmentation model on these narrow windows to fuse the segmentation superiorities and improve whole segmentation quality. 2)We propose the multi-condition GAN which equips the segmentation model with multiple discriminators to encourage the segmented structures meeting their real shape conditions, thus improving the shape feature extraction ability. 3)We propose the adversarial weighted ensemble module which uses the trained discriminators to evaluate the quality of segmented structures, and normalizes these evaluation scores for the ensemble weights directed at the input image, thus enhancing the ensemble results. 122 patients are enrolled in this study and the mean Dice coefficient of the renal structures achieves 84.6%. Extensive experiments with promising results on renal structures reveal powerful segmentation accuracy and great clinical significance in renal cancer treatment." @default.
- W3170253974 created "2021-06-22" @default.
- W3170253974 creator A5000166507 @default.
- W3170253974 creator A5001522611 @default.
- W3170253974 creator A5008751186 @default.
- W3170253974 creator A5011631723 @default.
- W3170253974 creator A5042978732 @default.
- W3170253974 creator A5049077061 @default.
- W3170253974 creator A5052775662 @default.
- W3170253974 creator A5064571884 @default.
- W3170253974 creator A5085738793 @default.
- W3170253974 date "2021-06-08" @default.
- W3170253974 modified "2023-09-27" @default.
- W3170253974 title "EnMcGAN: Adversarial Ensemble Learning for 3D Complete Renal Structures Segmentation" @default.
- W3170253974 cites W1997372885 @default.
- W3170253974 cites W2077251622 @default.
- W3170253974 cites W2095488888 @default.
- W3170253974 cites W2099471712 @default.
- W3170253974 cites W2114079675 @default.
- W3170253974 cites W2125389028 @default.
- W3170253974 cites W2134158406 @default.
- W3170253974 cites W2169808652 @default.
- W3170253974 cites W2464708700 @default.
- W3170253974 cites W2554423077 @default.
- W3170253974 cites W2620296437 @default.
- W3170253974 cites W2781889927 @default.
- W3170253974 cites W2891048235 @default.
- W3170253974 cites W2907125610 @default.
- W3170253974 cites W2912934387 @default.
- W3170253974 cites W2962835968 @default.
- W3170253974 cites W2962914239 @default.
- W3170253974 cites W2963270775 @default.
- W3170253974 cites W2963429638 @default.
- W3170253974 cites W2963683318 @default.
- W3170253974 cites W2964121744 @default.
- W3170253974 cites W2979402407 @default.
- W3170253974 cites W3025299467 @default.
- W3170253974 doi "https://doi.org/10.48550/arxiv.2106.04130" @default.
- W3170253974 hasPublicationYear "2021" @default.
- W3170253974 type Work @default.
- W3170253974 sameAs 3170253974 @default.
- W3170253974 citedByCount "0" @default.
- W3170253974 crossrefType "posted-content" @default.
- W3170253974 hasAuthorship W3170253974A5000166507 @default.
- W3170253974 hasAuthorship W3170253974A5001522611 @default.
- W3170253974 hasAuthorship W3170253974A5008751186 @default.
- W3170253974 hasAuthorship W3170253974A5011631723 @default.
- W3170253974 hasAuthorship W3170253974A5042978732 @default.
- W3170253974 hasAuthorship W3170253974A5049077061 @default.
- W3170253974 hasAuthorship W3170253974A5052775662 @default.
- W3170253974 hasAuthorship W3170253974A5064571884 @default.
- W3170253974 hasAuthorship W3170253974A5085738793 @default.
- W3170253974 hasBestOaLocation W31702539741 @default.
- W3170253974 hasConcept C138885662 @default.
- W3170253974 hasConcept C153180895 @default.
- W3170253974 hasConcept C154945302 @default.
- W3170253974 hasConcept C2776214188 @default.
- W3170253974 hasConcept C2776401178 @default.
- W3170253974 hasConcept C31972630 @default.
- W3170253974 hasConcept C41008148 @default.
- W3170253974 hasConcept C41895202 @default.
- W3170253974 hasConcept C89600930 @default.
- W3170253974 hasConceptScore W3170253974C138885662 @default.
- W3170253974 hasConceptScore W3170253974C153180895 @default.
- W3170253974 hasConceptScore W3170253974C154945302 @default.
- W3170253974 hasConceptScore W3170253974C2776214188 @default.
- W3170253974 hasConceptScore W3170253974C2776401178 @default.
- W3170253974 hasConceptScore W3170253974C31972630 @default.
- W3170253974 hasConceptScore W3170253974C41008148 @default.
- W3170253974 hasConceptScore W3170253974C41895202 @default.
- W3170253974 hasConceptScore W3170253974C89600930 @default.
- W3170253974 hasLocation W31702539741 @default.
- W3170253974 hasOpenAccess W3170253974 @default.
- W3170253974 hasPrimaryLocation W31702539741 @default.
- W3170253974 hasRelatedWork W1669643531 @default.
- W3170253974 hasRelatedWork W1988199133 @default.
- W3170253974 hasRelatedWork W2005437358 @default.
- W3170253974 hasRelatedWork W2023558673 @default.
- W3170253974 hasRelatedWork W2039154422 @default.
- W3170253974 hasRelatedWork W2122581818 @default.
- W3170253974 hasRelatedWork W2134924024 @default.
- W3170253974 hasRelatedWork W2517104666 @default.
- W3170253974 hasRelatedWork W2895616727 @default.
- W3170253974 hasRelatedWork W2182382398 @default.
- W3170253974 isParatext "false" @default.
- W3170253974 isRetracted "false" @default.
- W3170253974 magId "3170253974" @default.
- W3170253974 workType "article" @default.