{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:11:47Z","timestamp":1771956707111,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031445200","type":"print"},{"value":"9783031445217","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44521-7_9","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T19:01:58Z","timestamp":1696100518000},"page":"89-99","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Synthetic Boost: Leveraging Synthetic Data for\u00a0Enhanced Vision-Language Segmentation in\u00a0Echocardiography"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5019-2205","authenticated-orcid":false,"given":"Rabin","family":"Adhikari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0101-5592","authenticated-orcid":false,"given":"Manish","family":"Dhakal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4463-6700","authenticated-orcid":false,"given":"Safal","family":"Thapaliya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7249-5494","authenticated-orcid":false,"given":"Kanchan","family":"Poudel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0836-8253","authenticated-orcid":false,"given":"Prasiddha","family":"Bhandari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2775-4748","authenticated-orcid":false,"given":"Bishesh","family":"Khanal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"issue":"3","key":"9_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447243","volume":"54","author":"D Avola","year":"2021","unstructured":"Avola, D., Cinque, L., Fagioli, A., Foresti, G., Mecca, A.: Ultrasound medical imaging techniques: a survey. ACM Comput. Surv. (CSUR) 54(3), 1\u201338 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"9_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/978-3-030-87583-1_7","volume-title":"Simplifying Medical Ultrasound","author":"K Deng","year":"2021","unstructured":"Deng, K., et al.: Transbridge: a lightweight transformer for left ventricle segmentation in\u00a0echocardiography. In: Noble, J.A., Aylward, S., Grimwood, A., Min, Z., Lee, S.-L., Hu, Y. (eds.) ASMUS 2021. LNCS, vol. 12967, pp. 63\u201372. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87583-1_7"},{"key":"9_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"9_CR4","first-page":"20450","volume":"35","author":"A F\u00fcrst","year":"2022","unstructured":"F\u00fcrst, A., et al.: Cloob: modern hopfield networks with infoloob outperform clip. Adv. Neural Inf. Process. Syst. 35, 20450\u201320468 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"9_CR5","first-page":"2672","volume":"27","author":"I Goodfellow","year":"2014","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27, 2672\u20132680 (2014)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., et al.: UNETR: transformers for 3D medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 574\u2013584 (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"9_CR7","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"9_CR8","unstructured":"Huang, Z., Zeng, Z., Liu, B., Fu, D., Fu, J.: Pixel-BERT: aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849 (2020)"},{"issue":"2","key":"9_CR9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203\u2013211 (2021)","journal-title":"Nat. Methods"},{"key":"9_CR10","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: Referitgame: referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 787\u2013798 (2014)","DOI":"10.3115\/v1\/D14-1086"},{"issue":"9","key":"9_CR12","doi-asserted-by":"publisher","first-page":"2198","DOI":"10.1109\/TMI.2019.2900516","volume":"38","author":"S Leclerc","year":"2019","unstructured":"Leclerc, S., et al.: Deep learning for segmentation using an open large-scale dataset in 2d echocardiography. IEEE Trans. Med. Imaging 38(9), 2198\u20132210 (2019)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"9_CR13","unstructured":"Li, Y., et al.: Supervision exists everywhere: a data efficient contrastive language-image pre-training paradigm. In: International Conference on Learning Representations (2021)"},{"key":"9_CR14","unstructured":"Ling, H.J., Garcia, D., Bernard, O.: Reaching intra-observer variability in 2-d echocardiographic image segmentation with a simple u-net architecture. In: IEEE International Ultrasonics Symposium (IUS) (2022)"},{"key":"9_CR15","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"9_CR17","unstructured":"Poudel, K., Dhakal, M., Bhandari, P., Adhikari, R., Thapaliya, S., Khanal, B.: Exploring transfer learning in medical image segmentation using vision-language models. arXiv preprint arXiv:2308.07706 (2023)"},{"key":"9_CR18","unstructured":"Qin, Z., Yi, H.H., Lao, Q., Li, K.: Medical image understanding with pretrained vision language models: a comprehensive study. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"9_CR19","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18082\u201318091 (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"9_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Flava: a foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15638\u201315650 (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Stojanovski, D., Hermida, U., Lamata, P., Beqiri, A., Gomez, A.: Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation. arXiv preprint arXiv:2305.05424 (2023)","DOI":"10.1007\/978-3-031-44521-7_4"},{"key":"9_CR24","unstructured":"Wang, P., et al.: OFA: unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In: International Conference on Machine Learning, pp. 23318\u201323340. PMLR (2022)"},{"key":"9_CR25","unstructured":"Wang, W., et al.: Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050 (2022)"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CRIS: clip-driven referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"9_CR27","doi-asserted-by":"publisher","unstructured":"Wilcoxon, F.: Individual comparisons by ranking methods. In: Kotz, S., Johnson, N.L. (eds.) Breakthroughs in Statistics: Methodology and Distribution, pp. 196\u2013202. Springer Series in Statistics. Springer, New York (1992). https:\/\/doi.org\/10.1007\/978-1-4612-4380-9_16","DOI":"10.1007\/978-1-4612-4380-9_16"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Wu, C., Lin, Z., Cohen, S., Bui, T., Maji, S.: PhraseCut: language-based image segmentation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10216\u201310225 (2020)","DOI":"10.1109\/CVPR42600.2020.01023"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: Lit: zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"}],"container-title":["Lecture Notes in Computer Science","Simplifying Medical Ultrasound"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44521-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T04:06:33Z","timestamp":1703304393000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44521-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031445200","9783031445217"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44521-7_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ASMUS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Advances in Simplifying Medical Ultrasound","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"asmus2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miccai-ultrasound.github.io\/#\/asmus23","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":"EquinOCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30","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":"19","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":"63% - 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","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","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)"}}]}}