Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313897319> ?p ?o ?g. }
- W4313897319 endingPage "106501" @default.
- W4313897319 startingPage "106501" @default.
- W4313897319 abstract "Computerized tomography (CT) is of great significance for the localization and diagnosis of liver cancer. Many scholars have recently applied deep learning methods to segment CT images of liver and liver tumors. Unlike natural images, medical image segmentation is usually more challenging due to its nature. Aiming at the problem of blurry boundaries and complex gradients of liver tumor images, a deep supervision network based on the combination of high-efficiency channel attention and Res-UNet++ (ECA residual UNet++) is proposed for liver CT image segmentation, enabling fully automated end-to-end segmentation of the network. In this paper, the UNet++ structure is selected as the baseline. The residual block feature encoder based on context awareness enhances the feature extraction ability and solves the problem of deep network degradation. The introduction of an efficient attention module combines the depth of the feature map with spatial information to alleviate the uneven sample distribution impact; Use DiceLoss to replace the cross-entropy loss function to optimize network parameters. The liver and liver tumor segmentation accuracy on the LITS dataset was 95.8% and 89.3%, respectively. The results show that compared with other algorithms, the method proposed in this paper achieves a good segmentation performance, which has specific reference significance for computer-assisted diagnosis and treatment to attain fine segmentation of liver and liver tumors." @default.
- W4313897319 created "2023-01-10" @default.
- W4313897319 creator A5016654718 @default.
- W4313897319 creator A5024138459 @default.
- W4313897319 creator A5028441474 @default.
- W4313897319 creator A5039560137 @default.
- W4313897319 creator A5049586476 @default.
- W4313897319 creator A5052883326 @default.
- W4313897319 creator A5064544790 @default.
- W4313897319 creator A5072574495 @default.
- W4313897319 creator A5076083494 @default.
- W4313897319 date "2023-05-01" @default.
- W4313897319 modified "2023-10-11" @default.
- W4313897319 title "Eres-UNet++: Liver CT image segmentation based on high-efficiency channel attention and Res-UNet++" @default.
- W4313897319 cites W1702807959 @default.
- W4313897319 cites W1983248350 @default.
- W4313897319 cites W2001657034 @default.
- W4313897319 cites W2045922310 @default.
- W4313897319 cites W2103637700 @default.
- W4313897319 cites W2778609221 @default.
- W4313897319 cites W2889646458 @default.
- W4313897319 cites W2905103531 @default.
- W4313897319 cites W2913457010 @default.
- W4313897319 cites W2946233353 @default.
- W4313897319 cites W2963881378 @default.
- W4313897319 cites W2964312319 @default.
- W4313897319 cites W3016888800 @default.
- W4313897319 cites W3080797970 @default.
- W4313897319 cites W3098105350 @default.
- W4313897319 cites W3108605253 @default.
- W4313897319 cites W3123090129 @default.
- W4313897319 cites W3125726435 @default.
- W4313897319 cites W3126984895 @default.
- W4313897319 cites W3133325202 @default.
- W4313897319 cites W3134447168 @default.
- W4313897319 cites W3157477123 @default.
- W4313897319 cites W3163863039 @default.
- W4313897319 cites W3177310574 @default.
- W4313897319 cites W3179017527 @default.
- W4313897319 cites W3180424677 @default.
- W4313897319 cites W3181491309 @default.
- W4313897319 cites W3200644005 @default.
- W4313897319 cites W3203839559 @default.
- W4313897319 cites W3204514574 @default.
- W4313897319 cites W3206388375 @default.
- W4313897319 cites W3207846853 @default.
- W4313897319 cites W3209257685 @default.
- W4313897319 cites W3210193654 @default.
- W4313897319 cites W3211639065 @default.
- W4313897319 cites W4200018900 @default.
- W4313897319 cites W4200226729 @default.
- W4313897319 cites W4200372140 @default.
- W4313897319 cites W4205484788 @default.
- W4313897319 cites W4205544245 @default.
- W4313897319 cites W4206680344 @default.
- W4313897319 cites W4210370376 @default.
- W4313897319 cites W4214811678 @default.
- W4313897319 cites W4214935340 @default.
- W4313897319 cites W4220857768 @default.
- W4313897319 cites W4220964735 @default.
- W4313897319 cites W4221034033 @default.
- W4313897319 cites W4221070396 @default.
- W4313897319 cites W4283652716 @default.
- W4313897319 cites W4284708757 @default.
- W4313897319 cites W4285494545 @default.
- W4313897319 cites W4289883804 @default.
- W4313897319 cites W639708223 @default.
- W4313897319 doi "https://doi.org/10.1016/j.compbiomed.2022.106501" @default.
- W4313897319 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36635120" @default.
- W4313897319 hasPublicationYear "2023" @default.
- W4313897319 type Work @default.
- W4313897319 citedByCount "9" @default.
- W4313897319 countsByYear W43138973192023 @default.
- W4313897319 crossrefType "journal-article" @default.
- W4313897319 hasAuthorship W4313897319A5016654718 @default.
- W4313897319 hasAuthorship W4313897319A5024138459 @default.
- W4313897319 hasAuthorship W4313897319A5028441474 @default.
- W4313897319 hasAuthorship W4313897319A5039560137 @default.
- W4313897319 hasAuthorship W4313897319A5049586476 @default.
- W4313897319 hasAuthorship W4313897319A5052883326 @default.
- W4313897319 hasAuthorship W4313897319A5064544790 @default.
- W4313897319 hasAuthorship W4313897319A5072574495 @default.
- W4313897319 hasAuthorship W4313897319A5076083494 @default.
- W4313897319 hasConcept C108583219 @default.
- W4313897319 hasConcept C111919701 @default.
- W4313897319 hasConcept C11413529 @default.
- W4313897319 hasConcept C118505674 @default.
- W4313897319 hasConcept C124504099 @default.
- W4313897319 hasConcept C138885662 @default.
- W4313897319 hasConcept C151730666 @default.
- W4313897319 hasConcept C153180895 @default.
- W4313897319 hasConcept C154945302 @default.
- W4313897319 hasConcept C155512373 @default.
- W4313897319 hasConcept C2776401178 @default.
- W4313897319 hasConcept C2779343474 @default.
- W4313897319 hasConcept C31972630 @default.
- W4313897319 hasConcept C41008148 @default.
- W4313897319 hasConcept C41895202 @default.