{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T11:10:40Z","timestamp":1771067440433,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031340475","type":"print"},{"value":"9783031340482","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\/978-3-031-34048-2_36","type":"book-chapter","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T12:03:35Z","timestamp":1686139415000},"page":"471-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["X-TRA: Improving Chest X-ray Tasks with Cross-Modal Retrieval Augmentation"],"prefix":"10.1007","author":[{"given":"Tom","family":"van Sonsbeek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcel","family":"Worring","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,8]]},"reference":[{"key":"36_CR1","unstructured":"Chambon, P., et al.: RoentGen: vision-language foundation model for chest x-ray generation. arXiv preprint arXiv:2211.12737 (2022)"},{"key":"36_CR2","unstructured":"Endo, M., Krishnan, R., Krishna, V., Ng, A.Y., Rajpurkar, P.: Retrieval-based chest x-ray report generation using a pre-trained contrastive language-image model. In: Machine Learning for Health, pp. 209\u2013219. PMLR (2021)"},{"key":"36_CR3","unstructured":"Eslami, S., de Melo, G., Meinel, C.: Does CLIP benefit visual question answering in the medical domain as much as it does in the general domain? arXiv e-prints arXiv:2112.13906 (Dec 2021)"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Gur, S., Neverova, N., Stauffer, C., Lim, S.N., Kiela, D., Reiter, A.: Cross-modal retrieval augmentation for multi-modal classification. In: Findings of EMNLP 2021, pp. 111\u2013123 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.11"},{"key":"36_CR5","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: ICML, pp. 3929\u20133938 (2020)"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Hu, B., Vasu, B., Hoogs, A.: X-MIR: explainable medical image retrieval. In: WACV, pp. 440\u2013450 (2022)","DOI":"10.1109\/WACV51458.2022.00161"},{"key":"36_CR7","unstructured":"Huang, K., Altosaar, J., Ranganath, R.: ClinicalBERT: modeling clinical notes and predicting hospital readmission. arXiv preprint arXiv:1904.05342 (2019)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Ionescu, B., et al.: Overview of the ImageCLEF 2022: multimedia retrieval in medical, social media and nature applications. In: CLEF, pp. 541\u2013564 (2022)","DOI":"10.1007\/978-3-031-13643-6_31"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: AAAI, vol. 33, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"36_CR10","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML, pp. 4904\u20134916 (2021)"},{"issue":"1","key":"36_CR11","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AE Johnson","year":"2019","unstructured":"Johnson, A.E., et al.: MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","journal-title":"Sci. Data"},{"issue":"3","key":"36_CR12","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7(3), 535\u2013547 (2019)","journal-title":"IEEE Trans. Big Data"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Komeili, M., Shuster, K., Weston, J.: Internet-augmented dialogue generation. In: ACL, pp. 8460\u20138478 (2022)","DOI":"10.18653\/v1\/2022.acl-long.579"},{"key":"36_CR14","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. NeurIPS 33, 9459\u20139474 (2020)","journal-title":"NeurIPS"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., Li, S., Hu, Y., Tao, H.: A self-guided framework for radiology report generation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 588\u2013598 (2022)","DOI":"10.1007\/978-3-031-16452-1_56"},{"key":"36_CR16","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.media.2017.09.007","volume":"43","author":"Z Li","year":"2018","unstructured":"Li, Z., Zhang, X., M\u00fcller, H., Zhang, S.: Large-scale retrieval for medical image analytics: a comprehensive review. Med. Image Anal. 43, 66\u201384 (2018)","journal-title":"Med. Image Anal."},{"key":"36_CR17","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388 (2017)","journal-title":"Med. Image Anal."},{"issue":"6","key":"36_CR18","doi-asserted-by":"publisher","first-page":"e271","DOI":"10.1016\/S2589-7500(19)30123-2","volume":"1","author":"X Liu","year":"2019","unstructured":"Liu, X., et al.: A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit. Health 1(6), e271\u2013e297 (2019)","journal-title":"Lancet Digit. Health"},{"key":"36_CR19","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. NeurIPS 32 (2019)"},{"key":"36_CR20","unstructured":"OpenI: Indiana University - chest x-rays (PNG images). https:\/\/openi.nlm.nih.gov\/faq.php"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Pasupat, P., Zhang, Y., Guu, K.: Controllable semantic parsing via retrieval augmentation. In: EMNLP, pp. 7683\u20137698 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.607"},{"key":"36_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/978-3-030-01364-6_20","volume-title":"Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis","author":"O Pelka","year":"2018","unstructured":"Pelka, O., Koitka, S., R\u00fcckert, J., Nensa, F., Friedrich, C.M.: Radiology Objects in COntext (ROCO): a multimodal image dataset. In: Stoyanov, D., et al. (eds.) LABELS\/CVII\/STENT -2018. LNCS, vol. 11043, pp. 180\u2013189. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01364-6_20"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Pino, P., Parra, D., Besa, C., Lagos, C.: Clinically correct report generation from chest x-rays using templates. In: International Workshop on Machine Learning in Medical Imaging, pp. 654\u2013663 (2021)","DOI":"10.1007\/978-3-030-87589-3_67"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Pooch, E.H., Ballester, P.L., Barros, R.C.: Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification. arXiv preprint arXiv:1909.01940 (2019)","DOI":"10.1007\/978-3-030-62469-9_7"},{"key":"36_CR25","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.inffus.2020.10.005","volume":"67","author":"D Priyasad","year":"2021","unstructured":"Priyasad, D., Fernando, T., Denman, S., Sridharan, S., Fookes, C.: Memory based fusion for multi-modal deep learning. Inf. Fusion 67, 136\u2013146 (2021)","journal-title":"Inf. Fusion"},{"key":"36_CR26","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.neucom.2017.05.025","volume":"266","author":"A Qayyum","year":"2017","unstructured":"Qayyum, A., Anwar, S.M., Awais, M., Majid, M.: Medical image retrieval using deep convolutional neural network. Neurocomputing 266, 8\u201320 (2017)","journal-title":"Neurocomputing"},{"key":"36_CR27","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Ramos, R., Martins, B., Elliott, D., Kementchedjhieva, Y.: SmallCap: lightweight image captioning prompted with retrieval augmentation. arXiv preprint arXiv:2209.15323 (2022)","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Siriwardhana, S., Weerasekera, R., Wen, E., Kaluarachchi, T., Rana, R., Nanayakkara, S.: Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering. arXiv preprint arXiv:2210.02627 (2022)","DOI":"10.1162\/tacl_a_00530"},{"key":"36_CR30","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: EMNLP, pp. 5100\u20135111 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"36_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. NeurIPS 30 (2017)"},{"key":"36_CR32","doi-asserted-by":"publisher","unstructured":"Wang, J., Bhalerao, A., He, Y.: Cross-modal prototype driven network for radiology report generation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision (ECCV 2022). LNCS, vol. 13695, pp. 563\u2013579. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_33","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"36_CR33","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: SimVLM: simple visual language model pretraining with weak supervision. In: ICLR (2021)"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Yang, X., Ye, M., You, Q., Ma, F.: Writing by memorizing: hierarchical retrieval-based medical report generation. In: ACL, pp. 5000\u20135009 (2021)","DOI":"10.18653\/v1\/2021.acl-long.387"},{"key":"36_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1007\/978-3-030-87240-3_58","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Yu","year":"2021","unstructured":"Yu, Y., Hu, P., Lin, J., Krishnaswamy, P.: Multimodal multitask deep learning for x-ray image retrieval. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 603\u2013613. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_58"},{"key":"36_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107673","volume":"98","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Ou, W., Zhang, J., Deng, J.: Category supervised cross-modal hashing retrieval for chest x-ray and radiology reports. Comput. Electr. Eng. 98, 107673 (2022)","journal-title":"Comput. Electr. Eng."},{"issue":"5","key":"36_CR37","doi-asserted-by":"publisher","first-page":"820","DOI":"10.1109\/JPROC.2021.3054390","volume":"109","author":"SK Zhou","year":"2021","unstructured":"Zhou, S.K., et al.: A review of deep learning in medical imaging: imaging traits, technology trends, case studies with progress highlights, and future promises. Proc. IEEE 109(5), 820\u2013838 (2021)","journal-title":"Proc. IEEE"}],"container-title":["Lecture Notes in Computer Science","Information Processing in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-34048-2_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T19:48:44Z","timestamp":1702583324000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-34048-2_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031340475","9783031340482"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-34048-2_36","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":"8 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IPMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information Processing in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Carlos de Bariloche","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Argentina","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":"12 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ipmi2023","order":10,"name":"conference_id","label":"Conference ID","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"169","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":"63","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","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":"4","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}