Matches in SemOpenAlex for { <https://semopenalex.org/work/W2965839964> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2965839964 abstract "U-Net has achieved huge success in various medical image segmentation challenges. Kinds of new architectures with bells and whistles might succeed in certain dataset when employed with optimal hyper-parameter, but their generalization always can't be guaranteed. Here, we focused on the basic U-Net architecture and proposed a multi scale supervised 3D U-Net for the segmentation task in KiTS19 challenge. To enhance the performance, our work can be summarized as three folds: first, we used multi scale supervision in the decoder pathway, which could encourage the network to predict right results from the deep layers; second, with the aim to alleviate the bad effect from the sample imbalance of kidney and tumor, we adopted exponential logarithmic loss; third, a connected-component based post processing method was designed to remove the obviously wrong voxels. In the published KiTS19 training dataset (totally 210 patients), we divided 42 patients to be test dataset and finally obtained DICE scores of 0.969 and 0.805 for the kidney and tumor respectively. In the challenge, we finally achieved the 7th place among 106 teams with the Composite Dice of 0.8961, namely 0.9741 for kidney and 0.8181 for tumor." @default.
- W2965839964 created "2019-08-13" @default.
- W2965839964 creator A5024548740 @default.
- W2965839964 creator A5047124792 @default.
- W2965839964 date "2019-08-08" @default.
- W2965839964 modified "2023-10-17" @default.
- W2965839964 title "Multi Scale Supervised 3D U-Net for Kidney and Tumor Segmentation" @default.
- W2965839964 cites W1901129140 @default.
- W2965839964 cites W2078234387 @default.
- W2965839964 cites W2132695006 @default.
- W2965839964 cites W2791392402 @default.
- W2965839964 cites W2798122215 @default.
- W2965839964 cites W2891155035 @default.
- W2965839964 cites W2936835627 @default.
- W2965839964 cites W2949533892 @default.
- W2965839964 cites W2962914239 @default.
- W2965839964 cites W2963351448 @default.
- W2965839964 cites W2963429638 @default.
- W2965839964 cites W2964227007 @default.
- W2965839964 cites W3101414204 @default.
- W2965839964 doi "https://doi.org/10.48550/arxiv.1908.03204" @default.
- W2965839964 hasPublicationYear "2019" @default.
- W2965839964 type Work @default.
- W2965839964 sameAs 2965839964 @default.
- W2965839964 citedByCount "1" @default.
- W2965839964 countsByYear W29658399642020 @default.
- W2965839964 crossrefType "posted-content" @default.
- W2965839964 hasAuthorship W2965839964A5024548740 @default.
- W2965839964 hasAuthorship W2965839964A5047124792 @default.
- W2965839964 hasBestOaLocation W29658399641 @default.
- W2965839964 hasConcept C105795698 @default.
- W2965839964 hasConcept C119857082 @default.
- W2965839964 hasConcept C134306372 @default.
- W2965839964 hasConcept C14166107 @default.
- W2965839964 hasConcept C153180895 @default.
- W2965839964 hasConcept C154945302 @default.
- W2965839964 hasConcept C162324750 @default.
- W2965839964 hasConcept C177148314 @default.
- W2965839964 hasConcept C185592680 @default.
- W2965839964 hasConcept C187736073 @default.
- W2965839964 hasConcept C198531522 @default.
- W2965839964 hasConcept C205649164 @default.
- W2965839964 hasConcept C22029948 @default.
- W2965839964 hasConcept C2524010 @default.
- W2965839964 hasConcept C2778755073 @default.
- W2965839964 hasConcept C2780451532 @default.
- W2965839964 hasConcept C33923547 @default.
- W2965839964 hasConcept C41008148 @default.
- W2965839964 hasConcept C43617362 @default.
- W2965839964 hasConcept C50644808 @default.
- W2965839964 hasConcept C54170458 @default.
- W2965839964 hasConcept C58640448 @default.
- W2965839964 hasConcept C89600930 @default.
- W2965839964 hasConceptScore W2965839964C105795698 @default.
- W2965839964 hasConceptScore W2965839964C119857082 @default.
- W2965839964 hasConceptScore W2965839964C134306372 @default.
- W2965839964 hasConceptScore W2965839964C14166107 @default.
- W2965839964 hasConceptScore W2965839964C153180895 @default.
- W2965839964 hasConceptScore W2965839964C154945302 @default.
- W2965839964 hasConceptScore W2965839964C162324750 @default.
- W2965839964 hasConceptScore W2965839964C177148314 @default.
- W2965839964 hasConceptScore W2965839964C185592680 @default.
- W2965839964 hasConceptScore W2965839964C187736073 @default.
- W2965839964 hasConceptScore W2965839964C198531522 @default.
- W2965839964 hasConceptScore W2965839964C205649164 @default.
- W2965839964 hasConceptScore W2965839964C22029948 @default.
- W2965839964 hasConceptScore W2965839964C2524010 @default.
- W2965839964 hasConceptScore W2965839964C2778755073 @default.
- W2965839964 hasConceptScore W2965839964C2780451532 @default.
- W2965839964 hasConceptScore W2965839964C33923547 @default.
- W2965839964 hasConceptScore W2965839964C41008148 @default.
- W2965839964 hasConceptScore W2965839964C43617362 @default.
- W2965839964 hasConceptScore W2965839964C50644808 @default.
- W2965839964 hasConceptScore W2965839964C54170458 @default.
- W2965839964 hasConceptScore W2965839964C58640448 @default.
- W2965839964 hasConceptScore W2965839964C89600930 @default.
- W2965839964 hasLocation W29658399641 @default.
- W2965839964 hasOpenAccess W2965839964 @default.
- W2965839964 hasPrimaryLocation W29658399641 @default.
- W2965839964 hasRelatedWork W118753260 @default.
- W2965839964 hasRelatedWork W1573877189 @default.
- W2965839964 hasRelatedWork W2041273352 @default.
- W2965839964 hasRelatedWork W2091724545 @default.
- W2965839964 hasRelatedWork W2146691973 @default.
- W2965839964 hasRelatedWork W2753174232 @default.
- W2965839964 hasRelatedWork W2965839964 @default.
- W2965839964 hasRelatedWork W2989932438 @default.
- W2965839964 hasRelatedWork W3152950745 @default.
- W2965839964 hasRelatedWork W4206076898 @default.
- W2965839964 isParatext "false" @default.
- W2965839964 isRetracted "false" @default.
- W2965839964 magId "2965839964" @default.
- W2965839964 workType "article" @default.