FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198532012> ?p ?o ?g. }

• W3198532012 endingPage "6975" @default.
• W3198532012 startingPage "6962" @default.
• W3198532012 abstract "Abstract Purpose : In neonatal brain magnetic resonance image (MRI) segmentation, the model we trained on the training set (source domain) often performs poorly in clinical practice (target domain). As the label of target‐domain images is unavailable, this cross‐domain segmentation needs unsupervised domain adaptation (UDA) to make the model adapt to the target domain. However, the shape and intensity distribution of neonatal brain MRI images across the domains are largely different from adults'. Current UDA methods aim to make synthesized images similar to the target domain as a whole. But it is impossible to synthesize images with intraclass similarity because of the regional misalignment caused by the cross‐domain difference. This will result in generating intraclassly incorrect intensity information from target‐domain images. To address this issue, we propose an IAS‐NET (joint intraclassly adaptive generative adversarial network (GAN) (IA‐NET) and segmentation) framework to bridge the gap between the two domains for intraclass alignment. Methods : Our proposed IAS‐NET is an elegant learning framework that transfers the appearance of images across the domains from both image and feature perspectives. It consists of the proposed IA‐NET and a segmentation network (S‐NET). The proposed IA‐NET is a GAN‐based adaptive network that contains one generator (including two encoders and one shared decoder) and four discriminators for cross‐domain transfer. The two encoders are implemented to extract original image, mean, and variance features from source and target domains. The proposed local adaptive instance normalization algorithm is used to perform intraclass feature alignment to the target domain in the feature‐map level. S‐NET is a U‐net structure network that is used to provide semantic constraint by a segmentation loss for the training of IA‐NET. Meanwhile, it offers pseudo‐label images for calculating intraclass features of the target domain. Source code (in Tensorflow) is available at https://github.com/lb‐whu/RAS‐NET/ . Results : Extensive experiments are carried out on two different data sets (NeoBrainS12 and dHCP), respectively. There exist great differences in the shape, size, and intensity distribution of magnetic resonance (MR) images in the two databases. Compared to baseline, we improve the average dice score of all tissues on NeoBrains12 by 6% through adaptive training with unlabeled dHCP images. Besides, we also conduct experiments on dHCP and improved the average dice score by 4%. The quantitative analysis of the mean and variance of the synthesized images shows that the synthesized image by the proposed is closer to the target domain both in the full brain or within each class than that of the compared methods. Conclusions : In this paper, the proposed IAS‐NET can improve the performance of the S‐NET effectively by its intraclass feature alignment in the target domain. Compared to the current UDA methods, the synthesized images by IAS‐NET are more intraclassly similar to the target domain for neonatal brain MR images. Therefore, it achieves state‐of‐the‐art results in the compared UDA models for the segmentation task." @default.
• W3198532012 created "2021-09-13" @default.
• W3198532012 creator A5008826095 @default.
• W3198532012 creator A5018389659 @default.
• W3198532012 creator A5020348343 @default.
• W3198532012 creator A5037677450 @default.
• W3198532012 creator A5048576240 @default.
• W3198532012 creator A5065877047 @default.
• W3198532012 creator A5069855669 @default.
• W3198532012 creator A5085607757 @default.
• W3198532012 date "2021-09-25" @default.
• W3198532012 modified "2023-09-25" @default.
• W3198532012 title "IAS‐NET: Joint intraclassly adaptive GAN and segmentation network for unsupervised cross‐domain in neonatal brain MRI segmentation" @default.
• W3198532012 cites W1901129140 @default.
• W3198532012 cites W1903029394 @default.
• W3198532012 cites W2016693709 @default.
• W3198532012 cites W2022560037 @default.
• W3198532012 cites W2040681266 @default.
• W3198532012 cites W2046105679 @default.
• W3198532012 cites W2071881327 @default.
• W3198532012 cites W2122363306 @default.
• W3198532012 cites W2171615840 @default.
• W3198532012 cites W2194775991 @default.
• W3198532012 cites W2593768305 @default.
• W3198532012 cites W2603777577 @default.
• W3198532012 cites W2733375200 @default.
• W3198532012 cites W2793351617 @default.
• W3198532012 cites W2895281799 @default.
• W3198532012 cites W2914057844 @default.
• W3198532012 cites W2953130519 @default.
• W3198532012 cites W2962793481 @default.
• W3198532012 cites W2962825119 @default.
• W3198532012 cites W2963076262 @default.
• W3198532012 cites W2963797156 @default.
• W3198532012 cites W2963890275 @default.
• W3198532012 cites W2964250774 @default.
• W3198532012 cites W2971013993 @default.
• W3198532012 cites W2971040714 @default.
• W3198532012 cites W2987385519 @default.
• W3198532012 cites W2994367160 @default.
• W3198532012 cites W3025869703 @default.
• W3198532012 cites W3025884872 @default.
• W3198532012 cites W3103943044 @default.
• W3198532012 cites W3104164805 @default.
• W3198532012 cites W3104258355 @default.
• W3198532012 cites W4302359066 @default.
• W3198532012 doi "https://doi.org/10.1002/mp.15212" @default.
• W3198532012 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34494276" @default.
• W3198532012 hasPublicationYear "2021" @default.
• W3198532012 type Work @default.
• W3198532012 sameAs 3198532012 @default.
• W3198532012 citedByCount "4" @default.
• W3198532012 countsByYear W31985320122022 @default.
• W3198532012 countsByYear W31985320122023 @default.
• W3198532012 crossrefType "journal-article" @default.
• W3198532012 hasAuthorship W3198532012A5008826095 @default.
• W3198532012 hasAuthorship W3198532012A5018389659 @default.
• W3198532012 hasAuthorship W3198532012A5020348343 @default.
• W3198532012 hasAuthorship W3198532012A5037677450 @default.
• W3198532012 hasAuthorship W3198532012A5048576240 @default.
• W3198532012 hasAuthorship W3198532012A5065877047 @default.
• W3198532012 hasAuthorship W3198532012A5069855669 @default.
• W3198532012 hasAuthorship W3198532012A5085607757 @default.
• W3198532012 hasConcept C111919701 @default.
• W3198532012 hasConcept C118505674 @default.
• W3198532012 hasConcept C124504099 @default.
• W3198532012 hasConcept C136886441 @default.
• W3198532012 hasConcept C138885662 @default.
• W3198532012 hasConcept C144024400 @default.
• W3198532012 hasConcept C153180895 @default.
• W3198532012 hasConcept C154945302 @default.
• W3198532012 hasConcept C19165224 @default.
• W3198532012 hasConcept C2776401178 @default.
• W3198532012 hasConcept C2779803651 @default.
• W3198532012 hasConcept C31972630 @default.
• W3198532012 hasConcept C41008148 @default.
• W3198532012 hasConcept C41895202 @default.
• W3198532012 hasConcept C76155785 @default.
• W3198532012 hasConcept C89600930 @default.
• W3198532012 hasConcept C94915269 @default.
• W3198532012 hasConceptScore W3198532012C111919701 @default.
• W3198532012 hasConceptScore W3198532012C118505674 @default.
• W3198532012 hasConceptScore W3198532012C124504099 @default.
• W3198532012 hasConceptScore W3198532012C136886441 @default.
• W3198532012 hasConceptScore W3198532012C138885662 @default.
• W3198532012 hasConceptScore W3198532012C144024400 @default.
• W3198532012 hasConceptScore W3198532012C153180895 @default.
• W3198532012 hasConceptScore W3198532012C154945302 @default.
• W3198532012 hasConceptScore W3198532012C19165224 @default.
• W3198532012 hasConceptScore W3198532012C2776401178 @default.
• W3198532012 hasConceptScore W3198532012C2779803651 @default.
• W3198532012 hasConceptScore W3198532012C31972630 @default.
• W3198532012 hasConceptScore W3198532012C41008148 @default.
• W3198532012 hasConceptScore W3198532012C41895202 @default.
• W3198532012 hasConceptScore W3198532012C76155785 @default.
• W3198532012 hasConceptScore W3198532012C89600930 @default.
• W3198532012 hasConceptScore W3198532012C94915269 @default.
• W3198532012 hasIssue "11" @default.

• next