Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387413287> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4387413287 abstract "PET/CT images have the characteristics of accurate location and high sensitivity for tumor lesions, so the classification on PET/CT images is of great significance in clinical practice. In terms of visual tasks such as image classification, models such as vision transformer based on attention mechanism has been proved to be effective. However, medical images are different from natural images, and only using image information as model input can not fully and effectively express target characteristics. In this paper, we propose a method of adaptive extraction of the patch to maintain the morphological characteristics of the target, and add the radiomics features to the attention mechanism as a priori guidance knowledge for feature extraction, which is applied to the classification of PET/CT tumors. Firstly, for the original PET/CT image, the patch sequence is obtained by the adaptive patch extraction method based on overlapping region and sliding stride, which adapts to the input of the model while maintaining the morphological characteristics of the target; Secondly, the corresponding image token and radiomics feature vector of patches are obtained through linear projection layer and radiomics feature extractor respectively; Finally, the two are input into the multi-head attention module of the encoder to build a multi-feature attention mechanism, and complete the classification decision after the feature extraction. To verify the effectiveness of this method, we conducted experiments on the whole-body public dataset FDG-PET-CT-Lesions, and classified PET/CT images into negative, melanoma, lymphoma and non-small cell lung cancer, and the classification accuracy reached 0.8652. The experimental results show that the proposed method has a high performance on tumor classification in PET/CT images, and can be applied to classification of various tumors." @default.
- W4387413287 created "2023-10-07" @default.
- W4387413287 creator A5002329405 @default.
- W4387413287 creator A5036745253 @default.
- W4387413287 creator A5073727134 @default.
- W4387413287 creator A5081245464 @default.
- W4387413287 creator A5093019406 @default.
- W4387413287 date "2023-03-01" @default.
- W4387413287 modified "2023-10-08" @default.
- W4387413287 title "Application in Tumor Classification Based on Target Morphological Consistency Patches Adaptively Extracted and Priori Guided Feature Extraction Method" @default.
- W4387413287 cites W2097475056 @default.
- W4387413287 cites W2174661749 @default.
- W4387413287 cites W2409649574 @default.
- W4387413287 cites W2734955394 @default.
- W4387413287 cites W2739349903 @default.
- W4387413287 cites W2883645764 @default.
- W4387413287 cites W2910109668 @default.
- W4387413287 cites W2965367539 @default.
- W4387413287 cites W2980817460 @default.
- W4387413287 cites W2985928856 @default.
- W4387413287 cites W3006104185 @default.
- W4387413287 cites W3009486288 @default.
- W4387413287 cites W3025036301 @default.
- W4387413287 cites W3092827891 @default.
- W4387413287 cites W3119214506 @default.
- W4387413287 cites W3129007422 @default.
- W4387413287 doi "https://doi.org/10.1109/imip57114.2023.00012" @default.
- W4387413287 hasPublicationYear "2023" @default.
- W4387413287 type Work @default.
- W4387413287 citedByCount "0" @default.
- W4387413287 crossrefType "proceedings-article" @default.
- W4387413287 hasAuthorship W4387413287A5002329405 @default.
- W4387413287 hasAuthorship W4387413287A5036745253 @default.
- W4387413287 hasAuthorship W4387413287A5073727134 @default.
- W4387413287 hasAuthorship W4387413287A5081245464 @default.
- W4387413287 hasAuthorship W4387413287A5093019406 @default.
- W4387413287 hasConcept C138885662 @default.
- W4387413287 hasConcept C153180895 @default.
- W4387413287 hasConcept C154945302 @default.
- W4387413287 hasConcept C2776401178 @default.
- W4387413287 hasConcept C31972630 @default.
- W4387413287 hasConcept C41008148 @default.
- W4387413287 hasConcept C41895202 @default.
- W4387413287 hasConcept C52622490 @default.
- W4387413287 hasConcept C83665646 @default.
- W4387413287 hasConceptScore W4387413287C138885662 @default.
- W4387413287 hasConceptScore W4387413287C153180895 @default.
- W4387413287 hasConceptScore W4387413287C154945302 @default.
- W4387413287 hasConceptScore W4387413287C2776401178 @default.
- W4387413287 hasConceptScore W4387413287C31972630 @default.
- W4387413287 hasConceptScore W4387413287C41008148 @default.
- W4387413287 hasConceptScore W4387413287C41895202 @default.
- W4387413287 hasConceptScore W4387413287C52622490 @default.
- W4387413287 hasConceptScore W4387413287C83665646 @default.
- W4387413287 hasLocation W43874132871 @default.
- W4387413287 hasOpenAccess W4387413287 @default.
- W4387413287 hasPrimaryLocation W43874132871 @default.
- W4387413287 hasRelatedWork W2033213769 @default.
- W4387413287 hasRelatedWork W2056912418 @default.
- W4387413287 hasRelatedWork W2112208972 @default.
- W4387413287 hasRelatedWork W2123759770 @default.
- W4387413287 hasRelatedWork W2151520854 @default.
- W4387413287 hasRelatedWork W2373006798 @default.
- W4387413287 hasRelatedWork W2601157893 @default.
- W4387413287 hasRelatedWork W2768048376 @default.
- W4387413287 hasRelatedWork W2811390910 @default.
- W4387413287 hasRelatedWork W4312376745 @default.
- W4387413287 isParatext "false" @default.
- W4387413287 isRetracted "false" @default.
- W4387413287 workType "article" @default.