FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2797790897> ?p ?o ?g. }

• W2797790897 abstract "Fully convolutional deep neural networks have been asserted to be fast and precise frameworks with great potential in image segmentation. One of the major challenges in utilizing such networks raises when data is unbalanced, which is common in many medical imaging applications such as lesion segmentation where lesion class voxels are often much lower in numbers than non-lesion voxels. A trained network with unbalanced data may make predictions with high precision and low recall, being severely biased towards the non-lesion class which is particularly undesired in medical applications where false negatives are actually more important than false positives. Various methods have been proposed to address this problem including two step training, sample re-weighting, balanced sampling, and similarity loss functions. In this paper we developed a patch-wise 3D densely connected network with an asymmetric loss function, where we used large overlapping image patches for intrinsic and extrinsic data augmentation, a patch selection algorithm, and a patch prediction fusion strategy based on B-spline weighted soft voting to take into account the uncertainty of prediction in patch borders. We applied this method to lesion segmentation based on the MSSEG 2016 and ISBI 2015 challenges, where we achieved average Dice similarity coefficient of 69.8% and 65.74%, respectively, using our proposed patch-wise 3D densely connected network. Significant improvement in $F_1$ and $F_2$ scores and the area under the precision-recall curve was achieved in test using the asymmetric similarity loss layer and our 3D patch prediction fusion method. The asymmetric similarity loss function based on $F_beta$ scores generalizes the Dice similarity coefficient and can be effectively used with the patch-wise strategy developed here to train fully convolutional deep neural networks for highly unbalanced image segmentation." @default.
• W2797790897 created "2018-04-24" @default.
• W2797790897 creator A5013523388 @default.
• W2797790897 creator A5027934129 @default.
• W2797790897 creator A5052394541 @default.
• W2797790897 creator A5054913205 @default.
• W2797790897 creator A5058812679 @default.
• W2797790897 creator A5083261801 @default.
• W2797790897 date "2018-03-28" @default.
• W2797790897 modified "2023-09-26" @default.
• W2797790897 title "Asymmetric Similarity Loss Function to Balance Precision and Recall in Highly Unbalanced Deep Medical Image Segmentation" @default.
• W2797790897 cites W1522301498 @default.
• W2797790897 cites W1523762189 @default.
• W2797790897 cites W1901129140 @default.
• W2797790897 cites W1903029394 @default.
• W2797790897 cites W1971449558 @default.
• W2797790897 cites W1976526581 @default.
• W2797790897 cites W2028094999 @default.
• W2797790897 cites W2036564586 @default.
• W2797790897 cites W2059975159 @default.
• W2797790897 cites W2082526668 @default.
• W2797790897 cites W2106412194 @default.
• W2797790897 cites W2146233371 @default.
• W2797790897 cites W2175642482 @default.
• W2797790897 cites W2284198383 @default.
• W2797790897 cites W2301358467 @default.
• W2797790897 cites W2310992461 @default.
• W2797790897 cites W2342591535 @default.
• W2797790897 cites W2432481613 @default.
• W2797790897 cites W2556967412 @default.
• W2797790897 cites W2589409328 @default.
• W2797790897 cites W2589647984 @default.
• W2797790897 cites W2592329056 @default.
• W2797790897 cites W2596905414 @default.
• W2797790897 cites W2729876886 @default.
• W2797790897 cites W2734349601 @default.
• W2797790897 cites W2743473392 @default.
• W2797790897 cites W274818618 @default.
• W2797790897 cites W2755764120 @default.
• W2797790897 cites W2759532730 @default.
• W2797790897 cites W2766785165 @default.
• W2797790897 cites W2784851205 @default.
• W2797790897 cites W2787687030 @default.
• W2797790897 cites W2950975557 @default.
• W2797790897 cites W2951839332 @default.
• W2797790897 cites W2963446712 @default.
• W2797790897 cites W2963542991 @default.
• W2797790897 cites W2964227007 @default.
• W2797790897 hasPublicationYear "2018" @default.
• W2797790897 type Work @default.
• W2797790897 sameAs 2797790897 @default.
• W2797790897 citedByCount "6" @default.
• W2797790897 countsByYear W27977908972018 @default.
• W2797790897 countsByYear W27977908972020 @default.
• W2797790897 countsByYear W27977908972021 @default.
• W2797790897 crossrefType "posted-content" @default.
• W2797790897 hasAuthorship W2797790897A5013523388 @default.
• W2797790897 hasAuthorship W2797790897A5027934129 @default.
• W2797790897 hasAuthorship W2797790897A5052394541 @default.
• W2797790897 hasAuthorship W2797790897A5054913205 @default.
• W2797790897 hasAuthorship W2797790897A5058812679 @default.
• W2797790897 hasAuthorship W2797790897A5083261801 @default.
• W2797790897 hasConcept C103278499 @default.
• W2797790897 hasConcept C108583219 @default.
• W2797790897 hasConcept C112789634 @default.
• W2797790897 hasConcept C115961682 @default.
• W2797790897 hasConcept C124504099 @default.
• W2797790897 hasConcept C126838900 @default.
• W2797790897 hasConcept C153180895 @default.
• W2797790897 hasConcept C154945302 @default.
• W2797790897 hasConcept C163892561 @default.
• W2797790897 hasConcept C183115368 @default.
• W2797790897 hasConcept C203519979 @default.
• W2797790897 hasConcept C41008148 @default.
• W2797790897 hasConcept C54170458 @default.
• W2797790897 hasConcept C64869954 @default.
• W2797790897 hasConcept C71924100 @default.
• W2797790897 hasConcept C81363708 @default.
• W2797790897 hasConcept C89600930 @default.
• W2797790897 hasConceptScore W2797790897C103278499 @default.
• W2797790897 hasConceptScore W2797790897C108583219 @default.
• W2797790897 hasConceptScore W2797790897C112789634 @default.
• W2797790897 hasConceptScore W2797790897C115961682 @default.
• W2797790897 hasConceptScore W2797790897C124504099 @default.
• W2797790897 hasConceptScore W2797790897C126838900 @default.
• W2797790897 hasConceptScore W2797790897C153180895 @default.
• W2797790897 hasConceptScore W2797790897C154945302 @default.
• W2797790897 hasConceptScore W2797790897C163892561 @default.
• W2797790897 hasConceptScore W2797790897C183115368 @default.
• W2797790897 hasConceptScore W2797790897C203519979 @default.
• W2797790897 hasConceptScore W2797790897C41008148 @default.
• W2797790897 hasConceptScore W2797790897C54170458 @default.
• W2797790897 hasConceptScore W2797790897C64869954 @default.
• W2797790897 hasConceptScore W2797790897C71924100 @default.
• W2797790897 hasConceptScore W2797790897C81363708 @default.
• W2797790897 hasConceptScore W2797790897C89600930 @default.
• W2797790897 hasLocation W27977908971 @default.
• W2797790897 hasOpenAccess W2797790897 @default.
• W2797790897 hasPrimaryLocation W27977908971 @default.
• W2797790897 hasRelatedWork W1545506100 @default.

• next