{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:17:42Z","timestamp":1791303462064,"version":"4.1.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031164422","type":"print"},{"value":"9783031164439","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16443-9_69","type":"book-chapter","created":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T09:30:11Z","timestamp":1663234211000},"page":"725-734","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["BERTHop: An Effective Vision-and-Language Model for\u00a0Chest X-ray Disease Diagnosis"],"prefix":"10.1007","author":[{"given":"Masoud","family":"Monajatipoor","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mozhdeh","family":"Rouhsedaghat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liunian Harold","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C.-C.","family":"Jay Kuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aichi","family":"Chien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai-Wei","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,16]]},"reference":[{"key":"69_CR1","doi-asserted-by":"crossref","unstructured":"Abiyev, R.H., Ma\u2019aitah, M.K.S.: Deep convolutional neural networks for chest diseases detection. J. Healthc. Eng. 2018 (2018)","DOI":"10.1155\/2018\/4168538"},{"key":"69_CR2","doi-asserted-by":"crossref","unstructured":"Allaouzi, I., Ben Ahmed, M.: A novel approach for multi-label chest X-ray classification of common thorax diseases. IEEE Access 7, 64279\u201364288 (2019)","DOI":"10.1109\/ACCESS.2019.2916849"},{"key":"69_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"69_CR4","unstructured":"Buitinck, L., et al.: API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD Workshop: Languages for Data Mining and Machine Learning, pp. 108\u2013122 (2013)"},{"key":"69_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H.-S., Rouhsedaghat, M., Ghani, H., Shuowen, H., You, S., Jay Kuo, C.C.: DefakeHop: a light-weight high-performance Deepfake detector (2021)","DOI":"10.1109\/ICME51207.2021.9428361"},{"key":"69_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal Image-TExt Representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"69_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Rouhsedaghat, M., You, S., Rao, R., Jay Kuo, C.-C.: PixelHop++: a small successive-subspace-learning-based (SSL-based) model for image classification. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 3294\u20133298. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9191012"},{"key":"69_CR8","doi-asserted-by":"crossref","unstructured":"Chou, S.-H., Chao, W.-L., Lai, W.-S., Sun, M., Yang, M.-H.: Visual question answering on 360deg images. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1607\u20131616 (2020)","DOI":"10.1109\/WACV45572.2020.9093452"},{"key":"69_CR9","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"69_CR10","doi-asserted-by":"crossref","unstructured":"Giger, M.L., Suzuki, K.: Computer-aided diagnosis. In: Biomedical Information Technology, pp. 359-XXII. Elsevier (2008)","DOI":"10.1016\/B978-012373583-6.50020-7"},{"key":"69_CR11","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"69_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, A.E.W., et al.: MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"issue":"1","key":"69_CR13","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"69_CR14","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.-J., Chang, K.-W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"69_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, H., Luo, Y.: A comparison of pre-trained vision-and-language models for multimodal representation learning across medical images and reports. In: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 1999\u20132004. IEEE (2020)","DOI":"10.1109\/BIBM49941.2020.9313289"},{"key":"69_CR16","unstructured":"Liu, F., et al.: VoxelHop: successive subspace learning for ALS disease classification using structural MRI. arXiv preprint arXiv:2101.05131 (2021)"},{"key":"69_CR17","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10437\u201310446 (2020)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"69_CR18","doi-asserted-by":"crossref","unstructured":"Peng, Y., Yan, S., Lu, Z.: Transfer learning in biomedical natural language processing: an evaluation of BERT and ELMO on ten benchmarking datasets. arXiv preprint arXiv:1906.05474 (2019)","DOI":"10.18653\/v1\/W19-5006"},{"key":"69_CR19","unstructured":"Rajpurkar, P., et al.: CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv preprint arXiv:1711.05225 (2017)"},{"issue":"6","key":"69_CR20","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"69_CR21","unstructured":"Rouhsedaghat, M., Monajatipoor, M., Azizi, Z., Jay Kuo, C.-C.: Successive subspace learning: an overview. arXiv preprint arXiv:2103.00121 (2021)"},{"key":"69_CR22","doi-asserted-by":"crossref","unstructured":"Rouhsedaghat, M., Wang, Y., Ge, X., Hu, S., You, S., Jay Kuo, C.-C.: FaceHop: a light-weight low-resolution face gender classification method. arXiv preprint arXiv:2007.09510 (2020)","DOI":"10.1007\/978-3-030-68793-9_12"},{"key":"69_CR23","doi-asserted-by":"crossref","unstructured":"Rouhsedaghat, M., Wang, Y., Hu, S., You, S., Jay Kuo, C.-C.: Low-resolution face recognition in resource-constrained environments. arXiv preprint arXiv:2011.11674 (2020)","DOI":"10.1016\/j.patrec.2021.05.009"},{"issue":"5","key":"69_CR24","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"H-C Shin","year":"2016","unstructured":"Shin, H.-C., et al.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging 35(5), 1285\u20131298 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"69_CR25","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490, 2019","DOI":"10.18653\/v1\/D19-1514"},{"key":"69_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":"69_CR27","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"69_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Houdong, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16443-9_69","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:51:41Z","timestamp":1709830301000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16443-9_69"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164422","9783031164439"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16443-9_69","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2022","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":"Microsoft Conference","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1831","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":"574","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":"31% - 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":"5","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)"}}]}}