{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T19:01:28Z","timestamp":1772823688240,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030597184","type":"print"},{"value":"9783030597191","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-59719-1_5","type":"book-chapter","created":{"date-parts":[[2020,10,2]],"date-time":"2020-10-02T14:02:56Z","timestamp":1601647376000},"page":"45-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Weakly Supervised One-Stage Vision and Language Disease Detection Using Large Scale Pneumonia and Pneumothorax Studies"],"prefix":"10.1007","author":[{"given":"Leo K.","family":"Tam","sequence":"first","affiliation":[]},{"given":"Xiaosong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Evrim","family":"Turkbey","sequence":"additional","affiliation":[]},{"given":"Kevin","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Yuhong","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Daguang","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"5_CR1","unstructured":"Bergstra, J., Bardenet, R., Bengio, Y., K\u00e9gl, B.: Algorithms for hyper-parameter optimization. In: Shawe-Taylor, J., Zemel, R.S., Bartlett, P.L., Pereira, F.C.N., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12\u201314 December 2011, Granada, Spain, pp. 2546\u20132554 (2011). http:\/\/papers.nips.cc\/paper\/4443-algorithms-for-hyper-parameter-optimization"},{"key":"5_CR2","unstructured":"Brooks, J.: Coco annotator (2019). https:\/\/github.com\/jsbroks\/coco-annotator\/"},{"key":"5_CR3","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805 (2018). http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"5_CR4","doi-asserted-by":"publisher","unstructured":"Girshick, R.B.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision, ICCV 2015, Santiago, Chile, 7\u201313 December 2015, pp. 1440\u20131448. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"5_CR5","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. CoRR abs\/1611.10012 (2016). http:\/\/arxiv.org\/abs\/1611.10012"},{"key":"5_CR6","unstructured":"Irvin, J., et al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. CoRR abs\/1901.07031 (2019). http:\/\/arxiv.org\/abs\/1901.07031"},{"key":"5_CR7","unstructured":"Johnson, A.E.W., et al.: MIMIC-CXR: a large publicly available database of labeled chest radiographs. CoRR abs\/1901.07042 (2019). http:\/\/arxiv.org\/abs\/1901.07042"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: Densecap: fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.494"},{"key":"5_CR9","unstructured":"Kao, H.: Gradcam on chexnet, March 2020. https:\/\/github.com\/thtang\/CheXNet-with-localization"},{"key":"5_CR10","doi-asserted-by":"publisher","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.L.: Referitgame: referring to objects in photographs of natural scenes. In: Moschitti, A., Pang, B., Daelemans, W. (eds.) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, 25\u201329 October 2014, A meeting of SIGDAT, a Special Interest Group of the ACL, pp. 787\u2013798. ACL (2014). https:\/\/doi.org\/10.3115\/v1\/d14-1086","DOI":"10.3115\/v1\/d14-1086"},{"key":"5_CR11","unstructured":"Li, Z., et al.: Thoracic disease identification and localization with limited supervision. CoRR abs\/1711.06373 (2017). http:\/\/arxiv.org\/abs\/1711.06373"},{"key":"5_CR12","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, 14\u201316 April 2014, Conference Track Proceedings (2014). http:\/\/arxiv.org\/abs\/1312.4400"},{"key":"5_CR13","unstructured":"Loper, E., Bird, S.: NLTK: the natural language toolkit. CoRR cs.CL\/0205028 (2002). https:\/\/arxiv.org\/abs\/cs\/0205028"},{"key":"5_CR14","unstructured":"Lyubinets, V., Boiko, T., Nicholas, D.: Automated labeling of bugs and tickets using attention-based mechanisms in recurrent neural networks. CoRR abs\/1807.02892 (2018). http:\/\/arxiv.org\/abs\/1807.02892"},{"key":"5_CR15","doi-asserted-by":"publisher","unstructured":"Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J.R., Bethard, S., McClosky, D.: The stanford corenlp natural language processing toolkit. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, Baltimore, MD, USA, 22\u201327 June 2014, System Demonstrations, pp. 55\u201360. The Association for Computer Linguistics (2014). https:\/\/doi.org\/10.3115\/v1\/p14-5010","DOI":"10.3115\/v1\/p14-5010"},{"key":"5_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-030-00928-1_51","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"M Moradi","year":"2018","unstructured":"Moradi, M., Madani, A., Gur, Y., Guo, Y., Syeda-Mahmood, T.: Bimodal network architectures for automatic generation of image annotation from text. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 449\u2013456. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00928-1_51"},{"key":"5_CR17","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. CoRR abs\/1912.01703 (2019). http:\/\/arxiv.org\/abs\/1912.01703"},{"key":"5_CR18","unstructured":"Rajpurkar, P., et al.: Chexnet: radiologist-level pneumonia detection on chest x-rays with deep learning. CoRR abs\/1711.05225 (2017). http:\/\/arxiv.org\/abs\/1711.05225"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Jia, R., Liang, P.: Know what you don\u2019t know: unanswerable questions for squad. CoRR abs\/1806.03822 (2018). http:\/\/arxiv.org\/abs\/1806.03822","DOI":"10.18653\/v1\/P18-2124"},{"key":"5_CR20","unstructured":"Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: Unified, real-time object detection. CoRR abs\/1506.02640 (2015). http:\/\/arxiv.org\/abs\/1506.02640"},{"key":"5_CR21","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. CoRR abs\/1804.02767 (2018). http:\/\/arxiv.org\/abs\/1804.02767"},{"key":"5_CR22","unstructured":"Selvaraju, R.R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., Batra, D.: Grad-cam: why did you say that? Visual explanations from deep networks via gradient-based localization. CoRR abs\/1610.02391 (2016). http:\/\/arxiv.org\/abs\/1610.02391"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Tenney, I., Das, D., Pavlick, E.: BERT rediscovers the classical NLP pipeline. CoRR abs\/1905.05950 (2019). http:\/\/arxiv.org\/abs\/1905.05950","DOI":"10.18653\/v1\/P19-1452"},{"key":"5_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. CoRR abs\/1706.03762 (2017). http:\/\/arxiv.org\/abs\/1706.03762"},{"key":"5_CR25","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. CoRR abs\/1705.02315 (2017). http:\/\/arxiv.org\/abs\/1705.02315","DOI":"10.1109\/CVPR.2017.369"},{"key":"5_CR26","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Summers, R.M.: Tienet: text-image embedding network for common thorax disease classification and reporting in chest x-rays. CoRR abs\/1801.04334 (2018). http:\/\/arxiv.org\/abs\/1801.04334"},{"key":"5_CR27","unstructured":"Yan, K., Wang, X., Lu, L., Summers, R.M.: Deeplesion: automated deep mining, categorization and detection of significant radiology image findings using large-scale clinical lesion annotations. CoRR abs\/1710.01766 (2017). http:\/\/arxiv.org\/abs\/1710.01766"},{"key":"5_CR28","doi-asserted-by":"publisher","unstructured":"Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), 27 October\u20132 November 2019, pp. 4682\u20134692. IEEE (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00478","DOI":"10.1109\/ICCV.2019.00478"},{"key":"5_CR29","unstructured":"Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. CoRR abs\/1908.06354 (2019). http:\/\/arxiv.org\/abs\/1908.06354"},{"key":"5_CR30","unstructured":"Zhou, B., Khosla, A., Lapedriza, \u00c0., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. CoRR abs\/1512.04150 (2015). http:\/\/arxiv.org\/abs\/1512.04150"},{"key":"5_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1007\/978-3-030-00934-2_90","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"W Zhu","year":"2018","unstructured":"Zhu, W., Vang, Y.S., Huang, Y., Xie, X.: DeepEM: deep 3D ConvNets with EM for weakly supervised pulmonary nodule detection. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 812\u2013820. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00934-2_90"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-59719-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T22:07:22Z","timestamp":1759356442000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-59719-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030597184","9783030597191"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-59719-1_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","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":"Lima","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Peru","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.miccai2020.org\/en\/","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":"1809","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":"542","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":"30% - 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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}