{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T14:16:25Z","timestamp":1787926585008,"version":"build-2784847793"},"reference-count":40,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Ultrason Imaging"],"abstract":"<jats:p>Accurate standard-view classification is essential for pediatric echocardiographic image analysis and downstream automated interpretation. This task remains challenging because discriminative view information is often encoded in subtle chamber configurations, outflow-tract morphology, and weak anatomical boundaries, whereas conventional classifiers may underuse shallow and intermediate representations that preserve spatial structure. We propose PVTv2-ASEF, a structure-aware framework for 4-class pediatric echocardiographic standard-view classification. The framework introduces an Adaptive Structural Enhancement Module that performs residual input-side conditioning through channel recalibration, local convolutional mixing, multi-scale structural modeling, and input-dependent branch weighting. It further employs a Dual Auxiliary Fusion Head to transform Stage 2 and Stage 3 representations into class-level evidence and fuse them with the final-stage logits during inference. PVTv2-ASEF was evaluated on a private pediatric ventricular septal defect echocardiography dataset comprising 4 standard views under repeated patient-disjoint evaluation, with macro-F1 used as the primary class-balanced metric. Compared with PVTv2-B2, the proposed framework improved macro-F1 by 0.093 on the private dataset and by 0.023 in cross-task evaluation on FETAL_PLANES_DB. These results support the utility of coordinated input-side structural enhancement and intermediate logit fusion for ultrasound view and plane classification.<\/jats:p>","DOI":"10.1177\/01617346261478257","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T05:31:17Z","timestamp":1787635877000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Structure-Aware Deep Learning for Pediatric Echocardiographic Standard-View Classification in Ultrasonic Imaging"],"prefix":"10.1177","author":[{"given":"Yanfeng","family":"Liu","sequence":"first","affiliation":[{"name":"Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, China"},{"name":"Guizhou Equipment Manufacturing Digital Workshop Modeling and Simulation Engineering Research Center, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibin","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, China"},{"name":"Guizhou Equipment Manufacturing Digital Workshop Modeling and Simulation Engineering Research Center, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3750-6537","authenticated-orcid":false,"given":"Haisong","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, China"},{"name":"Guizhou Equipment Manufacturing Digital Workshop Modeling and Simulation Engineering Research Center, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanping","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Pediatric Cardiology, Shanghai Children\u2019s Medical Center, School of Medicine, Shanghai Jiao Tong University, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziteng","family":"Lu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang, China"},{"name":"Guizhou Equipment Manufacturing Digital Workshop Modeling and Simulation Engineering Research Center, Guiyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2020.04.025"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2023.11.015"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-017-0013-1"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0216-8"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2145-8"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2021.6059"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02959-y"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2022.08.009"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.3389\/fped.2021.770182"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1136\/wjps-2023-000580"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2026.104006"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Liu ZE Lin Y Cao Y et al. Swin transformer: hierarchical vision transformer using shifted windows arXiv\u2013CS\u2013Machine Learning 2021. doi:arxiv-2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_14_2","article-title":"PVTv2: improved baselines with pyramid vision transformer","author":"Wang W","year":"2021","unstructured":"Wang W, Xie E, Li X, et al. PVTv2: improved baselines with pyramid vision transformer. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2021. doi:arxiv-2106.13797","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3143707"},{"key":"e_1_3_2_16_2","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger O","year":"2015","unstructured":"Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2015. doi:arxiv-1505.04597","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_17_2","article-title":"Going Deeper with convolutions","author":"Szegedy C","year":"2014","unstructured":"Szegedy C, Liu W, Jia Y, et al. Going Deeper with convolutions. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2014. doi:arxiv-1409.4842","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_18_2","article-title":"Deeply-supervised nets","author":"Lee C-Y","year":"2014","unstructured":"Lee C-Y, Xie S, Gallagher P, Zhang Z, Tu Z. Deeply-supervised nets. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2014. doi:arxiv-1409.5185","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1093\/ehjdh\/ztae015"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1101\/2023.06.11.23290759"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.3390\/biom10050665"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-67076-5"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2017.2712367"},{"key":"e_1_3_2_24_2","article-title":"EfficientNetV2: smaller models and faster training","author":"Tan M","year":"2021","unstructured":"Tan M, Le QV. EfficientNetV2: smaller models and faster training. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2021. doi:arxiv-2104.00298","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_25_2","article-title":"A ConvNet for the 2020s","author":"Liu Z","year":"2022","unstructured":"Liu Z, Mao H, Wu C-Y, et al. A ConvNet for the 2020s. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2022. doi:arxiv-2201.03545","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_26_2","article-title":"ConvNeXt V2: Co-designing and Scaling ConvNets with masked autoencoders","author":"Woo S","year":"2023","unstructured":"Woo S, Debnath S, Hu R, et al. ConvNeXt V2: Co-designing and Scaling ConvNets with masked autoencoders. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2023. doi:arxiv-2301.00808","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_27_2","article-title":"CvT: introducing convolutions to vision transformers","author":"Wu H","year":"2021","unstructured":"Wu H, Xiao B, Codella N, et al. CvT: introducing convolutions to vision transformers. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2021. doi:arxiv-2103.15808","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_28_2","article-title":"CoAtNet: marrying convolution and attention for all data sizes","author":"Dai Z","year":"2021","unstructured":"Dai Z, Liu H, Le QV, Tan M. CoAtNet: marrying convolution and attention for all data sizes. arXiv\u2013CS\u2013Machine Learning, 2021. doi:arxiv-2106.04803","journal-title":"arXiv\u2013CS\u2013Machine Learning"},{"key":"e_1_3_2_29_2","article-title":"MaxViT: multi-axis vision transformer","author":"Tu Z","year":"2022","unstructured":"Tu Z, Talebi H, Zhang H, et al. MaxViT: multi-axis vision transformer. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2022. doi:arxiv-2204.01697","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_30_2","article-title":"Focal modulation networks","author":"Yang J","year":"2022","unstructured":"Yang J, Li C, Gao J. Focal modulation networks. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2022. doi:arxiv-2203.11926","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_31_2","article-title":"DaViT: dual attention vision transformers","author":"Ding M","year":"2022","unstructured":"Ding M, Xiao B, Codella N, et al. DaViT: dual attention vision transformers. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2022. doi:arxiv-2204.03645","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103000"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2018.11.020"},{"key":"e_1_3_2_34_2","article-title":"CBAM: convolutional block attention module","author":"Woo S","year":"2018","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS. CBAM: convolutional block attention module. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2018. doi:arxiv-1807.06521","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_35_2","article-title":"ECA-Net: efficient channel attention for deep convolutional neural networks","author":"Wang Q","year":"2019","unstructured":"Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2019. doi:arxiv-1910.03151","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_36_2","article-title":"Selective kernel networks","author":"Li X","year":"2019","unstructured":"Li X, Wang W, Hu X, Yang J. Selective kernel networks. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2019. doi:arxiv-1903.06586","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_37_2","article-title":"Dynamic convolution: attention over convolution kernels","author":"Chen Y","year":"2019","unstructured":"Chen Y, Dai X, Liu M, et al. Dynamic convolution: attention over convolution kernels. arXiv\u2013CS\u2013Computer Vision and Pattern Recognition, 2019. doi:arxiv-1912.03458","journal-title":"arXiv\u2013CS\u2013Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_38_2","article-title":"Deep layer aggregation","author":"Yu F","year":"2017","unstructured":"Yu F, Wang D, Shelhamer E, Darrell T. Deep layer aggregation. arXiv\u2013CS\u2013Machine Learning, 2017. doi:arxiv-1707.06484","journal-title":"arXiv\u2013CS\u2013Machine Learning"},{"key":"e_1_3_2_39_2","unstructured":"Huang G Chen D Li T et al. Multi-scale dense networks for resource efficient image classification arXiv\u2013CS\u2013Machine Learning 2017. doi:arxiv-1703.09844"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1024068626366"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2023.2197686"}],"container-title":["Ultrasonic Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01617346261478257","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/01617346261478257","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01617346261478257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:16:18Z","timestamp":1787922978000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/01617346261478257"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":40,"alternative-id":["10.1177\/01617346261478257"],"URL":"https:\/\/doi.org\/10.1177\/01617346261478257","relation":{},"ISSN":["0161-7346","1096-0910"],"issn-type":[{"value":"0161-7346","type":"print"},{"value":"1096-0910","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"article-number":"01617346261478257"}}