FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386647208> ?p ?o ?g. }

• W4386647208 endingPage "205011" @default.
• W4386647208 startingPage "205011" @default.
• W4386647208 abstract "Objective. Although convolutional neural networks (CNN) and Transformers have performed well in many medical image segmentation tasks, they rely on large amounts of labeled data for training. The annotation of medical image data is expensive and time-consuming, so it is common to use semi-supervised learning methods that use a small amount of labeled data and a large amount of unlabeled data to improve the performance of medical imaging segmentation.Approach. This work aims to enhance the segmentation performance of medical images using a triple-teacher cross-learning semi-supervised medical image segmentation with shape perception and multi-scale consistency regularization. To effectively leverage the information from unlabeled data, we design a multi-scale semi-supervised method for three-teacher cross-learning based on shape perception, called Semi-TMS. The three teacher models engage in cross-learning with each other, where Teacher A and Teacher C utilize a CNN architecture, while Teacher B employs a transformer model. The cross-learning module consisting of Teacher A and Teacher C captures local and global information, generates pseudo-labels, and performs cross-learning using prediction results. Multi-scale consistency regularization is applied separately to the CNN and Transformer to improve accuracy. Furthermore, the low uncertainty output probabilities from Teacher A or Teacher C are utilized as input to Teacher B, enhancing the utilization of prior knowledge and overall segmentation robustness.Main results. Experimental evaluations on two public datasets demonstrate that the proposed method outperforms some existing semi-segmentation models, implicitly capturing shape information and effectively improving the utilization and accuracy of unlabeled data through multi-scale consistency.Significance. With the widespread utilization of medical imaging in clinical diagnosis, our method is expected to be a potential auxiliary tool, assisting clinicians and medical researchers in their diagnoses." @default.
• W4386647208 created "2023-09-13" @default.
• W4386647208 creator A5015045475 @default.
• W4386647208 creator A5032709994 @default.
• W4386647208 creator A5039144070 @default.
• W4386647208 creator A5057942393 @default.
• W4386647208 date "2023-10-04" @default.
• W4386647208 modified "2023-10-13" @default.
• W4386647208 title "Semi-TMS: an efficient regularization-oriented triple-teacher semi-supervised medical image segmentation model" @default.
• W4386647208 cites W1846543079 @default.
• W4386647208 cites W2052617496 @default.
• W4386647208 cites W2106033751 @default.
• W4386647208 cites W2118386984 @default.
• W4386647208 cites W2160754664 @default.
• W4386647208 cites W2764063958 @default.
• W4386647208 cites W2804047627 @default.
• W4386647208 cites W2947263797 @default.
• W4386647208 cites W2984353870 @default.
• W4386647208 cites W2998663558 @default.
• W4386647208 cites W3025299467 @default.
• W4386647208 cites W3112701542 @default.
• W4386647208 cites W3123982987 @default.
• W4386647208 cites W3135022261 @default.
• W4386647208 cites W3189420316 @default.
• W4386647208 cites W3216275916 @default.
• W4386647208 cites W3217586157 @default.
• W4386647208 cites W4210252486 @default.
• W4386647208 cites W4214622817 @default.
• W4386647208 cites W4224246723 @default.
• W4386647208 cites W4224279125 @default.
• W4386647208 cites W4280631251 @default.
• W4386647208 cites W4282935002 @default.
• W4386647208 cites W4285040393 @default.
• W4386647208 cites W4291730167 @default.
• W4386647208 cites W4294192129 @default.
• W4386647208 doi "https://doi.org/10.1088/1361-6560/acf90f" @default.
• W4386647208 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37699409" @default.
• W4386647208 hasPublicationYear "2023" @default.
• W4386647208 type Work @default.
• W4386647208 citedByCount "0" @default.
• W4386647208 crossrefType "journal-article" @default.
• W4386647208 hasAuthorship W4386647208A5015045475 @default.
• W4386647208 hasAuthorship W4386647208A5032709994 @default.
• W4386647208 hasAuthorship W4386647208A5039144070 @default.
• W4386647208 hasAuthorship W4386647208A5057942393 @default.
• W4386647208 hasConcept C104317684 @default.
• W4386647208 hasConcept C108583219 @default.
• W4386647208 hasConcept C119857082 @default.
• W4386647208 hasConcept C153083717 @default.
• W4386647208 hasConcept C153180895 @default.
• W4386647208 hasConcept C154945302 @default.
• W4386647208 hasConcept C185592680 @default.
• W4386647208 hasConcept C2776135515 @default.
• W4386647208 hasConcept C2776145971 @default.
• W4386647208 hasConcept C2776321320 @default.
• W4386647208 hasConcept C31601959 @default.
• W4386647208 hasConcept C41008148 @default.
• W4386647208 hasConcept C55493867 @default.
• W4386647208 hasConcept C58973888 @default.
• W4386647208 hasConcept C63479239 @default.
• W4386647208 hasConcept C81363708 @default.
• W4386647208 hasConcept C89600930 @default.
• W4386647208 hasConceptScore W4386647208C104317684 @default.
• W4386647208 hasConceptScore W4386647208C108583219 @default.
• W4386647208 hasConceptScore W4386647208C119857082 @default.
• W4386647208 hasConceptScore W4386647208C153083717 @default.
• W4386647208 hasConceptScore W4386647208C153180895 @default.
• W4386647208 hasConceptScore W4386647208C154945302 @default.
• W4386647208 hasConceptScore W4386647208C185592680 @default.
• W4386647208 hasConceptScore W4386647208C2776135515 @default.
• W4386647208 hasConceptScore W4386647208C2776145971 @default.
• W4386647208 hasConceptScore W4386647208C2776321320 @default.
• W4386647208 hasConceptScore W4386647208C31601959 @default.
• W4386647208 hasConceptScore W4386647208C41008148 @default.
• W4386647208 hasConceptScore W4386647208C55493867 @default.
• W4386647208 hasConceptScore W4386647208C58973888 @default.
• W4386647208 hasConceptScore W4386647208C63479239 @default.
• W4386647208 hasConceptScore W4386647208C81363708 @default.
• W4386647208 hasConceptScore W4386647208C89600930 @default.
• W4386647208 hasFunder F4320321001 @default.
• W4386647208 hasIssue "20" @default.
• W4386647208 hasLocation W43866472081 @default.
• W4386647208 hasLocation W43866472082 @default.
• W4386647208 hasOpenAccess W4386647208 @default.
• W4386647208 hasPrimaryLocation W43866472081 @default.
• W4386647208 hasRelatedWork W1991049327 @default.
• W4386647208 hasRelatedWork W2074435087 @default.
• W4386647208 hasRelatedWork W2186210338 @default.
• W4386647208 hasRelatedWork W2365028544 @default.
• W4386647208 hasRelatedWork W2371815184 @default.
• W4386647208 hasRelatedWork W2949671220 @default.
• W4386647208 hasRelatedWork W34092691 @default.
• W4386647208 hasRelatedWork W4245973528 @default.
• W4386647208 hasRelatedWork W4282977123 @default.
• W4386647208 hasRelatedWork W4309984931 @default.
• W4386647208 hasVolume "68" @default.
• W4386647208 isParatext "false" @default.
• W4386647208 isRetracted "false" @default.

• next