FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313280044> ?p ?o ?g. }

• W4313280044 endingPage "045010" @default.
• W4313280044 startingPage "045010" @default.
• W4313280044 abstract "Abstract Objective . Histopathology image segmentation can assist medical professionals in identifying and diagnosing diseased tissue more efficiently. Although fully supervised segmentation models have excellent performance, the annotation cost is extremely expensive. Weakly supervised models are widely used in medical image segmentation due to their low annotation cost. Nevertheless, these weakly supervised models have difficulty in accurately locating the boundaries between different classes of regions in pathological images, resulting in a high rate of false alarms Our objective is to design a weakly supervised segmentation model to resolve the above problems. Approach . The segmentation model is divided into two main stages, the generation of pseudo labels based on class residual attention accumulation network (CRAANet) and the semantic segmentation based on pixel feature space construction network (PFSCNet). CRAANet provides attention scores for each class through the class residual attention module, while the Attention Accumulation (AA) module overlays the attention feature maps generated in each training epoch. PFSCNet employs a network model containing an inflated convolutional residual neural network and a multi-scale feature-aware module as the segmentation backbone, and proposes dense energy loss and pixel clustering modules are based on contrast learning to solve the pseudo-labeling-inaccuracy problem. Main results . We validate our method using the lung adenocarcinoma (LUAD-HistoSeg) dataset and the breast cancer (BCSS) dataset. The results of the experiments show that our proposed method outperforms other state-of-the-art methods on both datasets in several metrics. This suggests that it is capable of performing well in a wide variety of histopathological image segmentation tasks. Significance . We propose a weakly supervised semantic segmentation network that achieves approximate fully supervised segmentation performance even in the case of incomplete labels. The proposed AA and pixel-level contrast learning also make the edges more accurate and can well assist pathologists in their research." @default.
• W4313280044 created "2023-01-06" @default.
• W4313280044 creator A5006709942 @default.
• W4313280044 creator A5010793258 @default.
• W4313280044 creator A5028576686 @default.
• W4313280044 creator A5028948536 @default.
• W4313280044 creator A5031371726 @default.
• W4313280044 creator A5032362514 @default.
• W4313280044 creator A5051381076 @default.
• W4313280044 creator A5061120613 @default.
• W4313280044 creator A5062888811 @default.
• W4313280044 creator A5063922467 @default.
• W4313280044 date "2023-02-07" @default.
• W4313280044 modified "2023-09-30" @default.
• W4313280044 title "Weakly supervised semantic segmentation of histological tissue via attention accumulation and pixel-level contrast learning" @default.
• W4313280044 cites W2124260943 @default.
• W4313280044 cites W2133059825 @default.
• W4313280044 cites W2256341952 @default.
• W4313280044 cites W2295107390 @default.
• W4313280044 cites W2321533354 @default.
• W4313280044 cites W2464708700 @default.
• W4313280044 cites W2558580397 @default.
• W4313280044 cites W2600144439 @default.
• W4313280044 cites W2765793020 @default.
• W4313280044 cites W2771978163 @default.
• W4313280044 cites W2776207810 @default.
• W4313280044 cites W2795587607 @default.
• W4313280044 cites W2798991696 @default.
• W4313280044 cites W2883554151 @default.
• W4313280044 cites W2884436604 @default.
• W4313280044 cites W2921993685 @default.
• W4313280044 cites W2922239620 @default.
• W4313280044 cites W2963979276 @default.
• W4313280044 cites W2964274719 @default.
• W4313280044 cites W2969656782 @default.
• W4313280044 cites W2971376088 @default.
• W4313280044 cites W2996952120 @default.
• W4313280044 cites W3004053956 @default.
• W4313280044 cites W3025387230 @default.
• W4313280044 cites W3031256816 @default.
• W4313280044 cites W3085331204 @default.
• W4313280044 cites W3092564080 @default.
• W4313280044 cites W3093690432 @default.
• W4313280044 cites W3098637688 @default.
• W4313280044 cites W3106105822 @default.
• W4313280044 cites W3118742971 @default.
• W4313280044 cites W3121959641 @default.
• W4313280044 cites W3175722450 @default.
• W4313280044 cites W3183511791 @default.
• W4313280044 cites W3192931333 @default.
• W4313280044 cites W3197468198 @default.
• W4313280044 cites W3207797062 @default.
• W4313280044 cites W343636949 @default.
• W4313280044 cites W4282962039 @default.
• W4313280044 cites W4298004188 @default.
• W4313280044 cites W4312647976 @default.
• W4313280044 doi "https://doi.org/10.1088/1361-6560/acaeee" @default.
• W4313280044 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36577142" @default.
• W4313280044 hasPublicationYear "2023" @default.
• W4313280044 type Work @default.
• W4313280044 citedByCount "1" @default.
• W4313280044 countsByYear W43132800442023 @default.
• W4313280044 crossrefType "journal-article" @default.
• W4313280044 hasAuthorship W4313280044A5006709942 @default.
• W4313280044 hasAuthorship W4313280044A5010793258 @default.
• W4313280044 hasAuthorship W4313280044A5028576686 @default.
• W4313280044 hasAuthorship W4313280044A5028948536 @default.
• W4313280044 hasAuthorship W4313280044A5031371726 @default.
• W4313280044 hasAuthorship W4313280044A5032362514 @default.
• W4313280044 hasAuthorship W4313280044A5051381076 @default.
• W4313280044 hasAuthorship W4313280044A5061120613 @default.
• W4313280044 hasAuthorship W4313280044A5062888811 @default.
• W4313280044 hasAuthorship W4313280044A5063922467 @default.
• W4313280044 hasConcept C11413529 @default.
• W4313280044 hasConcept C124504099 @default.
• W4313280044 hasConcept C138885662 @default.
• W4313280044 hasConcept C153180895 @default.
• W4313280044 hasConcept C154945302 @default.
• W4313280044 hasConcept C155512373 @default.
• W4313280044 hasConcept C160633673 @default.
• W4313280044 hasConcept C2776401178 @default.
• W4313280044 hasConcept C2776502983 @default.
• W4313280044 hasConcept C41008148 @default.
• W4313280044 hasConcept C41895202 @default.
• W4313280044 hasConcept C81363708 @default.
• W4313280044 hasConcept C89600930 @default.
• W4313280044 hasConceptScore W4313280044C11413529 @default.
• W4313280044 hasConceptScore W4313280044C124504099 @default.
• W4313280044 hasConceptScore W4313280044C138885662 @default.
• W4313280044 hasConceptScore W4313280044C153180895 @default.
• W4313280044 hasConceptScore W4313280044C154945302 @default.
• W4313280044 hasConceptScore W4313280044C155512373 @default.
• W4313280044 hasConceptScore W4313280044C160633673 @default.
• W4313280044 hasConceptScore W4313280044C2776401178 @default.
• W4313280044 hasConceptScore W4313280044C2776502983 @default.
• W4313280044 hasConceptScore W4313280044C41008148 @default.
• W4313280044 hasConceptScore W4313280044C41895202 @default.
• W4313280044 hasConceptScore W4313280044C81363708 @default.

• next