Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312912095> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4312912095 endingPage "260" @default.
- W4312912095 startingPage "241" @default.
- W4312912095 abstract "The semantic segmentation of a brain tumor is the essential stage in medical treatment planning. Due to the different characteristics of tumors, one of the main difficulties in image segmentation is the severe imbalance between classes. Also, a dataset with imbalanced classes is a common problem in multimodal 3D brain MRIs. Despite these problems, most studies in brain tumor segmentation are biased toward the overrepresented tumor class (majority class) and ignore the small size tumor class (minority class). In this paper, we propose an improved loss function Weighted Focal Loss (WFL), based on 3D U-Net to enhance the prediction of brain tumor segmentation. Using our proposed loss function (WFL) solves the imbalance between classes and the imbalance between weights by giving higher weights to the minority and lower weights to the majority. After assigning these weights to different pixel values, our work is able to resolve pixel degradation, which is one of the limitations of the loss function during model training. Based on our experiments, the proposed function (WFL) on the 3D U-Net model for high-grade glioma (HGG) and low-grade glioma (LGG) in the Brain Tumor Segmentation Challenge (BraTS) 2019 dataset has shown promising results for tumor core (TC), whole tumor (WT) and enhanced tumor (ET) with average dice scores of HGG: 0.830, 0.913, 0.815 and Dice scores of LGG for TC: 0.731, WT: 0.775 and ET: 0.685. Moreover, we deployed our training on BraTS 2020 in which we obtained mean Dice scores of HGG: TC: 0.843, WT: 0.892, ET: 0.871 and Dice scores of LGG: 0.7501, 0.7985, 0.6103 for TC, WT and ET, respectively." @default.
- W4312912095 created "2023-01-05" @default.
- W4312912095 creator A5017947172 @default.
- W4312912095 creator A5047994852 @default.
- W4312912095 creator A5068903779 @default.
- W4312912095 date "2022-01-01" @default.
- W4312912095 modified "2023-09-30" @default.
- W4312912095 title "Brain Tumor Segmentation of HGG and LGG MRI Images Using WFL-Based 3D U-Net" @default.
- W4312912095 cites W1901129140 @default.
- W4312912095 cites W2117340355 @default.
- W4312912095 cites W2464708700 @default.
- W4312912095 cites W2891155035 @default.
- W4312912095 cites W2891169321 @default.
- W4312912095 cites W2963351448 @default.
- W4312912095 cites W2964980777 @default.
- W4312912095 cites W3010030563 @default.
- W4312912095 cites W3014512070 @default.
- W4312912095 cites W3021659040 @default.
- W4312912095 cites W3081495241 @default.
- W4312912095 cites W3102069556 @default.
- W4312912095 cites W3118442183 @default.
- W4312912095 cites W3121627242 @default.
- W4312912095 cites W3127859904 @default.
- W4312912095 cites W3134261862 @default.
- W4312912095 cites W3139971561 @default.
- W4312912095 cites W3151900447 @default.
- W4312912095 cites W3154072362 @default.
- W4312912095 cites W3158845577 @default.
- W4312912095 cites W3167784297 @default.
- W4312912095 cites W3190789550 @default.
- W4312912095 cites W3203841574 @default.
- W4312912095 cites W3211488937 @default.
- W4312912095 cites W3211651961 @default.
- W4312912095 cites W3213928897 @default.
- W4312912095 cites W4220664643 @default.
- W4312912095 cites W4220792942 @default.
- W4312912095 cites W4223926709 @default.
- W4312912095 cites W4285195156 @default.
- W4312912095 cites W4293207870 @default.
- W4312912095 cites W4321260726 @default.
- W4312912095 cites W4323903843 @default.
- W4312912095 doi "https://doi.org/10.4236/jbise.2022.1510022" @default.
- W4312912095 hasPublicationYear "2022" @default.
- W4312912095 type Work @default.
- W4312912095 citedByCount "0" @default.
- W4312912095 crossrefType "journal-article" @default.
- W4312912095 hasAuthorship W4312912095A5017947172 @default.
- W4312912095 hasAuthorship W4312912095A5047994852 @default.
- W4312912095 hasAuthorship W4312912095A5068903779 @default.
- W4312912095 hasBestOaLocation W43129120951 @default.
- W4312912095 hasConcept C105795698 @default.
- W4312912095 hasConcept C14036430 @default.
- W4312912095 hasConcept C142724271 @default.
- W4312912095 hasConcept C154945302 @default.
- W4312912095 hasConcept C22029948 @default.
- W4312912095 hasConcept C2778227246 @default.
- W4312912095 hasConcept C2779130545 @default.
- W4312912095 hasConcept C33923547 @default.
- W4312912095 hasConcept C41008148 @default.
- W4312912095 hasConcept C502942594 @default.
- W4312912095 hasConcept C71924100 @default.
- W4312912095 hasConcept C78458016 @default.
- W4312912095 hasConcept C86803240 @default.
- W4312912095 hasConcept C89600930 @default.
- W4312912095 hasConceptScore W4312912095C105795698 @default.
- W4312912095 hasConceptScore W4312912095C14036430 @default.
- W4312912095 hasConceptScore W4312912095C142724271 @default.
- W4312912095 hasConceptScore W4312912095C154945302 @default.
- W4312912095 hasConceptScore W4312912095C22029948 @default.
- W4312912095 hasConceptScore W4312912095C2778227246 @default.
- W4312912095 hasConceptScore W4312912095C2779130545 @default.
- W4312912095 hasConceptScore W4312912095C33923547 @default.
- W4312912095 hasConceptScore W4312912095C41008148 @default.
- W4312912095 hasConceptScore W4312912095C502942594 @default.
- W4312912095 hasConceptScore W4312912095C71924100 @default.
- W4312912095 hasConceptScore W4312912095C78458016 @default.
- W4312912095 hasConceptScore W4312912095C86803240 @default.
- W4312912095 hasConceptScore W4312912095C89600930 @default.
- W4312912095 hasIssue "10" @default.
- W4312912095 hasLocation W43129120951 @default.
- W4312912095 hasOpenAccess W4312912095 @default.
- W4312912095 hasPrimaryLocation W43129120951 @default.
- W4312912095 hasRelatedWork W2748952813 @default.
- W4312912095 hasRelatedWork W2899084033 @default.
- W4312912095 hasRelatedWork W3035458717 @default.
- W4312912095 hasRelatedWork W3088332649 @default.
- W4312912095 hasRelatedWork W4213188021 @default.
- W4312912095 hasRelatedWork W4283266333 @default.
- W4312912095 hasRelatedWork W4286541714 @default.
- W4312912095 hasRelatedWork W4311739268 @default.
- W4312912095 hasRelatedWork W4360850309 @default.
- W4312912095 hasRelatedWork W4372049117 @default.
- W4312912095 hasVolume "15" @default.
- W4312912095 isParatext "false" @default.
- W4312912095 isRetracted "false" @default.
- W4312912095 workType "article" @default.