{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:33:27Z","timestamp":1742974407398,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985579"},{"type":"electronic","value":"9789819985586"}],"license":[{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T00:00:00Z","timestamp":1703548800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8558-6_12","type":"book-chapter","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T20:02:02Z","timestamp":1703534522000},"page":"136-148","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FlashViT: A Flash Vision Transformer with\u00a0Large-Scale Token Merging for\u00a0Congenital Heart Disease Detection"],"prefix":"10.1007","author":[{"given":"Lei","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junlong","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jilong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peilun","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,26]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Arnaout, R., Curran, L., Zhao, Y., Levine, J.C., Chinn, E., Moon-Grady, A.J.: Expert-level prenatal detection of complex congenital heart disease from screening ultrasound using deep learning. medRxiv, pp. 2020\u201306 (2020)","DOI":"10.1101\/2020.06.22.20137786"},{"key":"12_CR2","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. arXiv preprint arXiv:2210.09461 (2022)"},{"key":"12_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"12_CR4","doi-asserted-by":"publisher","first-page":"102313","DOI":"10.1016\/j.media.2021.102313","volume":"76","author":"J Cheng","year":"2022","unstructured":"Cheng, J., et al.: ResGANet: residual group attention network for medical image classification and segmentation. Med. Image Anal. 76, 102313 (2022)","journal-title":"Med. Image Anal."},{"key":"12_CR5","doi-asserted-by":"publisher","first-page":"101899","DOI":"10.1016\/j.artmed.2020.101899","volume":"107","author":"J Cheng","year":"2020","unstructured":"Cheng, J., Tian, S., Yu, L., Lu, H., Lv, X.: Fully convolutional attention network for biomedical image segmentation. Artif. Intell. Med. 107, 101899 (2020)","journal-title":"Artif. Intell. Med."},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"12_CR7","unstructured":"Desai, G., Elsayed, N., Elsayed, Z., Ozer, M.: A transfer learning based approach for classification of COVID-19 and pneumonia in CT scan imaging. arXiv preprint arXiv:2210.09403 (2022)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: CSWin transformer: a general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"12_CR11","unstructured":"Huang, X., Deng, Z., Li, D., Yuan, X.: MISSFormer: an effective medical image segmentation transformer. arXiv preprint arXiv:2109.07162 (2021)"},{"issue":"3","key":"12_CR12","doi-asserted-by":"publisher","first-page":"034501","DOI":"10.1117\/1.JMI.3.3.034501","volume":"3","author":"BQ Huynh","year":"2016","unstructured":"Huynh, B.Q., Li, H., Giger, M.L.: Digital mammographic tumor classification using transfer learning from deep convolutional neural networks. J. Med. Imaging 3(3), 034501\u2013034501 (2016)","journal-title":"J. Med. Imaging"},{"key":"12_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"12_CR14","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Not all patches are what you need: expediting vision transformers via token reorganizations. arXiv preprint arXiv:2202.07800 (2022)"},{"key":"12_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12872-020-01781-x","volume":"20","author":"Y Liu","year":"2020","unstructured":"Liu, Y., et al.: Global prevalence of congenital heart disease in school-age children: a meta-analysis and systematic review. BMC Cardiovasc. Disord. 20, 1\u201310 (2020)","journal-title":"BMC Cardiovasc. Disord."},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"12_CR17","doi-asserted-by":"publisher","unstructured":"Maaz, M., et al.: EdgeNeXt: efficiently amalgamated CNN-transformer architecture for mobile vision applications. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision, ECCV 2022 Workshops, ECCV 2022, Part VII. LNCS, vol. 13807, pp. 3\u201320. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25082-8_1","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"12_CR18","unstructured":"Mehta, S., Rastegari, M.: MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 (2021)"},{"key":"12_CR19","doi-asserted-by":"publisher","first-page":"101794","DOI":"10.1016\/j.media.2020.101794","volume":"65","author":"S Minaee","year":"2020","unstructured":"Minaee, S., Kafieh, R., Sonka, M., Yazdani, S., Soufi, G.J.: Deep-COVID: predicting COVID-19 from chest X-ray images using deep transfer learning. Med. Image Anal. 65, 101794 (2020)","journal-title":"Med. Image Anal."},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Perera, S., Adhikari, S., Yilmaz, A.: POCFormer: a lightweight transformer architecture for detection of COVID-19 using point of care ultrasound. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 195\u2013199. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506353"},{"key":"12_CR21","first-page":"13937","volume":"34","author":"Y Rao","year":"2021","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. Adv. Neural. Inf. Process. Syst. 34, 13937\u201313949 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"3","key":"12_CR22","doi-asserted-by":"publisher","first-page":"210","DOI":"10.4103\/0974-2069.189125","volume":"9","author":"U Rashid","year":"2016","unstructured":"Rashid, U., Qureshi, A.U., Hyder, S.N., Sadiq, M.: Pattern of congenital heart disease in a developing country tertiary care center: factors associated with delayed diagnosis. Ann. Pediatr. Cardiol. 9(3), 210 (2016)","journal-title":"Ann. Pediatr. Cardiol."},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"12_CR25","doi-asserted-by":"publisher","unstructured":"Tu, Z., et al.: MaxViT: multi-axis vision transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022, Part XXIV. LNCS, vol. 13684, pp. 459\u2013479. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_27","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2097\u20132106 (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"12_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/978-3-030-59719-1_8","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"X Xu","year":"2020","unstructured":"Xu, X., et al.: ImageCHD: a 3D computed tomography image dataset for classification of congenital heart disease. In: Martel, A.L., et al. (eds.) MICCAI 2020, Part IV 23. LNCS, vol. 12264, pp. 77\u201387. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59719-1_8"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8558-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T20:03:09Z","timestamp":1703534589000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8558-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,26]]},"ISBN":["9789819985579","9789819985586"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8558-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,26]]},"assertion":[{"value":"26 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}