Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385325057> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4385325057 endingPage "100638" @default.
- W4385325057 startingPage "100638" @default.
- W4385325057 abstract "This paper aims to improve U-Net for more accurate segmentation of irregular intracranial hemorrhage lesions in CT images. The residual octave convolution (ResOctConv) module was introduced to overcome the semantic gap issue in U-Net, and a hybrid attention mechanism called mixed attention mechanism (MAM) was proposed to further enhance the performance of U-Net. 40 patients with irregular cerebral hemorrhage images were selected from head CT scans performed between August and December 2022. Two radiologists independently traced the edge of each selected image three times, and the final segmentation boundary was determined by consensus. The effectiveness of the lesion segmentation was measured using the Dice coefficient, Jaccard Index, and Relative volume difference. Based on the box plot of the Dice coefficient for all 40 patients, the improved U-Net demonstrated higher accuracy in segmenting irregular intracranial hemorrhage lesions in CT images compared to the original U-Net. Moreover, the comparison of Dice coefficient, Jaccard coefficient, and RVD indicates that the improved U-Net outperforms both the original U-Net and the region growing algorithm in segmenting irregular cerebral hemorrhage lesions. The proposed improved U-Net outperforms both the original U-Net and the region growing algorithm in segmenting irregular cerebral hemorrhage lesions, providing an advanced toolset for radiologists to accurately identify and diagnose irregular cerebral hemorrhage lesions." @default.
- W4385325057 created "2023-07-28" @default.
- W4385325057 creator A5009414991 @default.
- W4385325057 creator A5010066834 @default.
- W4385325057 creator A5025314697 @default.
- W4385325057 creator A5088250252 @default.
- W4385325057 date "2023-09-01" @default.
- W4385325057 modified "2023-10-12" @default.
- W4385325057 title "Computed tomography image segmentation of irregular cerebral hemorrhage lesions based on improved U-Net" @default.
- W4385325057 cites W1901129140 @default.
- W4385325057 cites W2793034486 @default.
- W4385325057 cites W2928133111 @default.
- W4385325057 cites W2976310255 @default.
- W4385325057 cites W3037506255 @default.
- W4385325057 cites W3040054640 @default.
- W4385325057 cites W3128009222 @default.
- W4385325057 cites W3159225726 @default.
- W4385325057 cites W3192691477 @default.
- W4385325057 cites W3201577723 @default.
- W4385325057 cites W3208066112 @default.
- W4385325057 cites W4214760846 @default.
- W4385325057 cites W4226334633 @default.
- W4385325057 cites W4280526620 @default.
- W4385325057 cites W4280617180 @default.
- W4385325057 cites W4309213146 @default.
- W4385325057 cites W4309364692 @default.
- W4385325057 cites W4322748699 @default.
- W4385325057 cites W4366748111 @default.
- W4385325057 cites W4366775665 @default.
- W4385325057 cites W4368367343 @default.
- W4385325057 doi "https://doi.org/10.1016/j.jrras.2023.100638" @default.
- W4385325057 hasPublicationYear "2023" @default.
- W4385325057 type Work @default.
- W4385325057 citedByCount "0" @default.
- W4385325057 crossrefType "journal-article" @default.
- W4385325057 hasAuthorship W4385325057A5009414991 @default.
- W4385325057 hasAuthorship W4385325057A5010066834 @default.
- W4385325057 hasAuthorship W4385325057A5025314697 @default.
- W4385325057 hasAuthorship W4385325057A5088250252 @default.
- W4385325057 hasBestOaLocation W43853250571 @default.
- W4385325057 hasConcept C124504099 @default.
- W4385325057 hasConcept C126838900 @default.
- W4385325057 hasConcept C153180895 @default.
- W4385325057 hasConcept C154945302 @default.
- W4385325057 hasConcept C163892561 @default.
- W4385325057 hasConcept C203519979 @default.
- W4385325057 hasConcept C2989005 @default.
- W4385325057 hasConcept C41008148 @default.
- W4385325057 hasConcept C71924100 @default.
- W4385325057 hasConcept C89600930 @default.
- W4385325057 hasConceptScore W4385325057C124504099 @default.
- W4385325057 hasConceptScore W4385325057C126838900 @default.
- W4385325057 hasConceptScore W4385325057C153180895 @default.
- W4385325057 hasConceptScore W4385325057C154945302 @default.
- W4385325057 hasConceptScore W4385325057C163892561 @default.
- W4385325057 hasConceptScore W4385325057C203519979 @default.
- W4385325057 hasConceptScore W4385325057C2989005 @default.
- W4385325057 hasConceptScore W4385325057C41008148 @default.
- W4385325057 hasConceptScore W4385325057C71924100 @default.
- W4385325057 hasConceptScore W4385325057C89600930 @default.
- W4385325057 hasIssue "3" @default.
- W4385325057 hasLocation W43853250571 @default.
- W4385325057 hasOpenAccess W4385325057 @default.
- W4385325057 hasPrimaryLocation W43853250571 @default.
- W4385325057 hasRelatedWork W2766422710 @default.
- W4385325057 hasRelatedWork W2953570019 @default.
- W4385325057 hasRelatedWork W3012828488 @default.
- W4385325057 hasRelatedWork W3093926553 @default.
- W4385325057 hasRelatedWork W3116883888 @default.
- W4385325057 hasRelatedWork W3164075923 @default.
- W4385325057 hasRelatedWork W4280645644 @default.
- W4385325057 hasRelatedWork W4287631720 @default.
- W4385325057 hasRelatedWork W4367019122 @default.
- W4385325057 hasRelatedWork W4385154950 @default.
- W4385325057 hasVolume "16" @default.
- W4385325057 isParatext "false" @default.
- W4385325057 isRetracted "false" @default.
- W4385325057 workType "article" @default.