{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:14:06Z","timestamp":1777058046037,"version":"3.51.4"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049261","type":"print"},{"value":"9783032049278","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T00:00:00Z","timestamp":1758412800000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04927-8_56","type":"book-chapter","created":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T17:09:20Z","timestamp":1758388160000},"page":"589-598","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Small Lesions-aware Bidirectional Multimodal Multiscale Fusion Network for\u00a0Lung Disease Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4443-6443","authenticated-orcid":false,"given":"Jianxun","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3380-7970","authenticated-orcid":false,"given":"Ruiquan","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1856-360X","authenticated-orcid":false,"given":"Zhipeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0947-656X","authenticated-orcid":false,"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7991-1918","authenticated-orcid":false,"given":"Chenyu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianjun","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jikui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Elazab","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changmiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,21]]},"reference":[{"key":"56_CR1","doi-asserted-by":"crossref","unstructured":"Chen, X., Pan, J., Dong, J.: Bidirectional multi-scale implicit neural representations for image deraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 25627\u201325636 (2024)","DOI":"10.1109\/CVPR52733.2024.02421"},{"key":"56_CR2","doi-asserted-by":"crossref","unstructured":"Guo, Z., Gan, H.: CPP-NET: embracing multi-scale feature fusion into deep unfolding CP-PPA network for compressive sensing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 25086\u201325095 (2024)","DOI":"10.1109\/CVPR52733.2024.02370"},{"key":"56_CR3","doi-asserted-by":"crossref","unstructured":"Hager, P., Menten, M.J., Rueckert, D.: Best of both worlds: multimodal contrastive learning with tabular and imaging data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23924\u201323935 (2023)","DOI":"10.1109\/CVPR52729.2023.02291"},{"key":"56_CR4","unstructured":"Hayat, N., Geras, K.J., Shamout, F.E.: Medfuse: multi-modal fusion with clinical time-series data and chest x-ray images. In: Machine Learning for Healthcare Conference, pp. 479\u2013503. PMLR (2022)"},{"key":"56_CR5","doi-asserted-by":"crossref","unstructured":"Huang, S.C., et al.: Peneta scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging. NPJ Digit. Med. 3(1), 61 (2020)","DOI":"10.1038\/s41746-020-0266-y"},{"issue":"1","key":"56_CR6","doi-asserted-by":"publisher","first-page":"22147","DOI":"10.1038\/s41598-020-78888-w","volume":"10","author":"SC Huang","year":"2020","unstructured":"Huang, S.C., Pareek, A., Zamanian, R., Banerjee, I., Lungren, M.P.: Multimodal fusion with deep neural networks for leveraging CT imaging and electronic health record: a case-study in pulmonary embolism detection. Sci. Rep. 10(1), 22147 (2020)","journal-title":"Sci. Rep."},{"key":"56_CR7","unstructured":"Jiang, J.P., Ye, H.J., Wang, L., Yang, Y., Jiang, Y., Zhan, D.C.: Tabular insights, visual impacts: transferring expertise from tables to images. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"56_CR8","unstructured":"Joze, H.R.V., Shaban, A., Iuzzolino, M.L., Koishida, K.: MMTM: multimodal transfer module for cnn fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13289\u201313299 (2020)"},{"key":"56_CR9","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"56_CR10","unstructured":"Li, P., Wang, S., Li, T., Lu, J., HuangFu, Y., Wang, D.: A large-scale CT and PET\/CT dataset for lung cancer diagnosis (lung-PET-CT-dx). https:\/\/doi.org\/10.7937\/TCIA.2020.NNC2-0461 (2020)"},{"key":"56_CR11","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Rotated multi-scale interaction network for referring remote sensing image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26658\u201326668 (2024)","DOI":"10.1109\/CVPR52733.2024.02517"},{"key":"56_CR12","unstructured":"Liu, Z., et al.: KAN: Kolmogorov-arnold networks. arXiv preprint arXiv:2404.19756 (2024)"},{"key":"56_CR13","doi-asserted-by":"crossref","unstructured":"Ma, T., Dai, X., Zhang, S., Wen, Y.: PIVIT: Large deformation image registration with pyramid-iterative vision transformer. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 602\u2013612. Springer (2023)","DOI":"10.1007\/978-3-031-43999-5_57"},{"key":"56_CR14","doi-asserted-by":"crossref","unstructured":"P\u00f6lsterl, S., Wolf, T.N., Wachinger, C.: Combining 3D image and tabular data via the dynamic affine feature map transform. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 688\u2013698. Springer (2021)","DOI":"10.1007\/978-3-030-87240-3_66"},{"key":"56_CR15","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"56_CR16","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Munir, M., Marculescu, R.: EMCAD: efficient multi-scale convolutional attention decoding for medical image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11769\u201311779 (2024)","DOI":"10.1109\/CVPR52733.2024.01118"},{"key":"56_CR17","doi-asserted-by":"crossref","unstructured":"Sanjeev, S., Al\u00a0Khatib, S.K., Shaaban, M.A., Almakky, I., Papineni, V.R., Yaqub, M.: PECON: contrastive pretraining to enhance feature alignment between CT and EHR data for improved pulmonary embolism diagnosis. In: International Workshop on Machine Learning in Medical Imaging, pp. 434\u2013443. Springer (2023)","DOI":"10.1007\/978-3-031-45673-2_43"},{"key":"56_CR18","doi-asserted-by":"crossref","unstructured":"Yao, W., Yin, K., Cheung, W.K., Liu, J., Qin, J.: Drfuse: learning disentangled representation for clinical multi-modal fusion with missing modality and modal inconsistency. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 16416\u201316424 (2024)","DOI":"10.1609\/aaai.v38i15.29578"},{"key":"56_CR19","doi-asserted-by":"crossref","unstructured":"Yu, X., et al.: ICH-SCNET: Intracerebral hemorrhage segmentation and prognosis classification network using clip-guided SAM mechanism. In: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 2795\u20132800. IEEE (2024)","DOI":"10.1109\/BIBM62325.2024.10822098"},{"key":"56_CR20","doi-asserted-by":"crossref","unstructured":"Zhu, V., et al.: Low-rank continual pyramid vision transformer: incrementally segment whole-body organs in CT with light-weighted adaptation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 371\u2013381. Springer (2024)","DOI":"10.1007\/978-3-031-72111-3_35"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04927-8_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T17:09:30Z","timestamp":1758388170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04927-8_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,21]]},"ISBN":["9783032049261","9783032049278"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04927-8_56","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,21]]},"assertion":[{"value":"21 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}