{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T07:09:28Z","timestamp":1778310568849,"version":"3.51.4"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:00:00Z","timestamp":1778284800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:00:00Z","timestamp":1778284800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001652","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001652","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Vision-Language (VL) models such as Contrastive Language-Image pretraining (CLIP) have shown remarkable zero-shot classification capabilities by jointly learning from large-scale image\u2013text datasets using multimodal self-supervised learning (SSL). However, while these models capture strong global semantics, they often struggle with fine-grained spatial understanding, thereby limiting their effectiveness in downstream tasks like object detection and medical abnormality localization\n                    <jats:sup>2<\/jats:sup>\n                    . To address this limitation, we propose Patch-CLIP, a novel VL framework that introduces a contrastive loss aligning image patch-level embeddings with text embeddings. Unlike conventional VL approaches that only leverage global image representations, our method utilizes local patch-level features to encode spatial context, enabling effective learning of localization cues. Applied to two Chest X-ray (CXR) datasets, Patch-CLIP achieves state-of-the-art (SOTA) performance across eight abnormality detection tasks. Furthermore, the resulting patch prediction maps substantially reduce false positives at comparable sensitivity levels compared to standard saliency-based methods, providing more precise and interpretable localization of key findings. The code is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/Siemens-Healthineers\/patch-clip\" ext-link-type=\"uri\">https:\/\/github.com\/Siemens-Healthineers\/patch-clip<\/jats:ext-link>\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-52235-x","type":"journal-article","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T06:03:10Z","timestamp":1778306590000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PatchCLIP enables region specific contrastive health record and image joint training with patch embedding loss"],"prefix":"10.1038","volume":"16","author":[{"given":"Sheethal","family":"Bhat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Awais","family":"Mansoor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Georgescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Zinnen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pranjal","family":"Sahu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adarsh B.","family":"Panambur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florin C.","family":"Ghesu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sasa","family":"Grbic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,9]]},"reference":[{"key":"52235_CR1","unstructured":"Oquab, M. et al. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"52235_CR2","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning, 8748\u20138763 (PMLR, 2021)."},{"issue":"1","key":"52235_CR3","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1038\/s41597-022-01498-w","volume":"9","author":"HQ Nguyen","year":"2022","unstructured":"Nguyen, H. Q. et al. Vindr-cxr: An open dataset of chest x-rays with radiologist\u2019s annotations. Sci. Data 9(1), 429 (2022).","journal-title":"Sci. Data"},{"key":"52235_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101855","volume":"68","author":"FC Ghesu","year":"2021","unstructured":"Ghesu, F. C. et al. Quantifying and leveraging predictive uncertainty for medical image assessment. Med. Image Anal. 68, 101855 (2021).","journal-title":"Med. Image Anal."},{"issue":"6","key":"52235_CR5","doi-asserted-by":"publisher","first-page":"064503","DOI":"10.1117\/1.JMI.9.6.064503","volume":"9","author":"FC Ghesu","year":"2022","unstructured":"Ghesu, F. C. et al. Contrastive self-supervised learning from 100 million medical images with optional supervision. J. Med. Imaging 9(6), 064503\u2013064503 (2022).","journal-title":"J. Med. Imaging"},{"issue":"12","key":"52235_CR6","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","volume":"6","author":"E Tiu","year":"2022","unstructured":"Tiu, E. et al. Expert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning. Nat. Biomed. Eng. 6(12), 1399\u20131406 (2022).","journal-title":"Nat. Biomed. Eng."},{"key":"52235_CR7","doi-asserted-by":"crossref","unstructured":"Vandenbroucke, J. P. In defense of case reports and case series. American College of Physicians (2001).","DOI":"10.7326\/0003-4819-134-4-200102200-00017"},{"key":"52235_CR8","doi-asserted-by":"crossref","unstructured":"Mansoor, A. et al. Using ai to identify chest radiographs with no actionable disease in outpatient imaging (2023).","DOI":"10.21203\/rs.3.rs-2924070\/v1"},{"key":"52235_CR9","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., & Xie, W. Medklip: Medical knowledge enhanced language-image pre-training. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023).","DOI":"10.1101\/2023.01.10.23284412"},{"key":"52235_CR10","doi-asserted-by":"crossref","unstructured":"Huang, S.-C., Shen, L., Lungren, M.P., & Yeung, S. Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 3942\u20133951 (2021).","DOI":"10.1109\/ICCV48922.2021.00391"},{"issue":"4\u20135","key":"52235_CR11","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.compmedimag.2007.02.002","volume":"31","author":"K Doi","year":"2007","unstructured":"Doi, K. Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput. Med. Imaging Graph. 31(4\u20135), 198\u2013211 (2007).","journal-title":"Comput. Med. Imaging Graph."},{"issue":"8","key":"52235_CR12","doi-asserted-by":"publisher","DOI":"10.1118\/1.4816310","volume":"40","author":"N Petrick","year":"2013","unstructured":"Petrick, N. et al. Evaluation of computer-aided detection and diagnosis systems a. Med. Phys. 40(8), 087001 (2013).","journal-title":"Med. Phys."},{"key":"52235_CR13","doi-asserted-by":"crossref","unstructured":"Danu, M. D. et al. Generation of radiology findings in chest x-ray by leveraging collaborative knowledge. arXiv preprint arXiv:2306.10448 (2023).","DOI":"10.1016\/j.procs.2023.08.094"},{"key":"52235_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision (2017).","DOI":"10.1109\/ICCV.2017.324"},{"issue":"8","key":"52235_CR15","doi-asserted-by":"publisher","first-page":"2042","DOI":"10.1109\/TMI.2021.3070847","volume":"40","author":"J Lian","year":"2021","unstructured":"Lian, J. et al. A structure-aware relation network for thoracic diseases detection and segmentation. IEEE Trans. Med. Imaging 40(8), 2042\u20132052. https:\/\/doi.org\/10.1109\/TMI.2021.3070847 (2021).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"52235_CR16","doi-asserted-by":"crossref","unstructured":"Ghesu, F. C., et al. Robust multi-scale anatomical landmark detection in incomplete 3d-ct data. In Medical Image Computing and Computer Assisted Intervention- MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11\u201313, 2017, Proceedings, Part I 20, 194\u2013202 (Springer, 2017).","DOI":"10.1007\/978-3-319-66182-7_23"},{"issue":"12","key":"52235_CR17","doi-asserted-by":"publisher","first-page":"2141096","DOI":"10.1001\/jamanetworkopen.2021.41096","volume":"4","author":"F Homayounieh","year":"2021","unstructured":"Homayounieh, F. et al. An artificial intelligence-based chest x-ray model on human nodule detection accuracy from a multicenter study. JAMA Netw. Open 4(12), 2141096\u20132141096 (2021).","journal-title":"JAMA Netw. Open"},{"issue":"2","key":"52235_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2024.100080","volume":"2","author":"L Pan","year":"2024","unstructured":"Pan, L. et al. Opportunities and challenges in the application of large artificial intelligence models in radiology. Meta-Radiology 2(2), 100080 (2024).","journal-title":"Meta-Radiology"},{"issue":"1","key":"52235_CR19","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1038\/s41746-022-00658-x","volume":"5","author":"SY Lee","year":"2022","unstructured":"Lee, S. Y. et al. Localization-adjusted diagnostic performance and assistance effect of a computer-aided detection system for pneumothorax and consolidation. npj Digit. Med. 5(1), 107 (2022).","journal-title":"npj Digit. Med."},{"issue":"1","key":"52235_CR20","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":"10","key":"52235_CR21","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1038\/s42256-022-00536-x","volume":"4","author":"A Saporta","year":"2022","unstructured":"Saporta, A. et al. Benchmarking saliency methods for chest x-ray interpretation. Nat. Mach. Intell. 4(10), 867\u2013878 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"52235_CR22","doi-asserted-by":"crossref","unstructured":"Ambati, A., & Dubey, S.R. Ac-covidnet: Attention guided contrastive cnn for recognition of covid-19 in chest x-ray images. In International Conference on Computer Vision and Image Processing, 71\u201382 (Springer, 2021).","DOI":"10.1007\/978-3-031-11346-8_7"},{"issue":"1","key":"52235_CR23","doi-asserted-by":"publisher","first-page":"3848","DOI":"10.1038\/s41467-022-31514-x","volume":"13","author":"S Park","year":"2022","unstructured":"Park, S. et al. Self-evolving vision transformer for chest x-ray diagnosis through knowledge distillation. Nat. Commun. 13(1), 3848 (2022).","journal-title":"Nat. Commun."},{"key":"52235_CR24","doi-asserted-by":"crossref","unstructured":"Santosh, K., Dhar, M.K., Rajbhandari, R., & Neupane, A. Deep neural network for foreign object detection in chest x-rays. In 2020 IEEE 33rd International Symposium on Computer-based Medical Systems (CBMS), 538\u2013541 (IEEE, 2020).","DOI":"10.1109\/CBMS49503.2020.00107"},{"key":"52235_CR25","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.measurement.2019.05.076","volume":"145","author":"AK Jaiswal","year":"2019","unstructured":"Jaiswal, A. K. et al. Identifying pneumonia in chest x-rays: A deep learning approach. Measurement 145, 511\u2013518 (2019).","journal-title":"Measurement"},{"key":"52235_CR26","doi-asserted-by":"crossref","unstructured":"Silva-Rodr\u00edguez, J., Dolz, J., & Ayed, I. B. A reality check of vision-language pre-training in radiology: Have we progressed using text? In International Conference on Information Processing in Medical Imaging, 294\u2013309 (Springer, 2025).","DOI":"10.1007\/978-3-031-96625-5_20"},{"key":"52235_CR27","doi-asserted-by":"crossref","unstructured":"Arora, R., Saini, I., & Sood, N. Dual-encoder framework for multi-abnormality classification of vindr-cxr dataset. In 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), 207\u2013211 (IEEE, 2023).","DOI":"10.1109\/ICSCCC58608.2023.10176862"},{"key":"52235_CR28","doi-asserted-by":"crossref","unstructured":"Wu, H. et al. Vlce: Unified vision-language collaborative enhancement for facial expression recognition. In 2024 5th International Conference on Computers and Artificial Intelligence Technology (CAIT), 94\u201399 (IEEE, 2024).","DOI":"10.1109\/CAIT64506.2024.10963325"},{"key":"52235_CR29","unstructured":"Sowrirajan, H., Yang, J., Ng, A.Y., & Rajpurkar, P. Moco pretraining improves representation and transferability of chest x-ray models. In: Medical Imaging with Deep Learning, 728\u2013744 (PMLR, 2021)."},{"issue":"2","key":"52235_CR30","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1097\/RLI.0000000000000813","volume":"57","author":"J Rudolph","year":"2022","unstructured":"Rudolph, J. et al. Artificial intelligence in chest radiography reporting accuracy: added clinical value in the emergency unit setting without 24\/7 radiology coverage. Investig. Radiol. 57(2), 90\u201398 (2022).","journal-title":"Investig. Radiol."},{"key":"52235_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102087","volume":"72","author":"S G\u00fcndel","year":"2021","unstructured":"G\u00fcndel, S. et al. Robust classification from noisy labels: Integrating additional knowledge for chest radiography abnormality assessment. Med. Image Anal. 72, 102087 (2021).","journal-title":"Med. Image Anal."},{"key":"52235_CR32","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., & Langlotz, C.P. Contrastive learning of medical visual representations from paired images and text. In: Lipton, Z., Ranganath, R., Sendak, M., Sjoding, M., & Yeung, S. (eds.) Proceedings of the 7th Machine Learning for Healthcare Conference. Proceedings of Machine Learning Research, vol. 182, 2\u201325 (PMLR, 2022). https:\/\/proceedings.mlr.press\/v182\/zhang22a.html"},{"key":"52235_CR33","doi-asserted-by":"crossref","unstructured":"Mu, N., Kirillov, A., Wagner, D., & Xie, S. Slip: Self-supervision meets language-image pre-training. arXiv preprint arXiv:2112.12750 (2021).","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"52235_CR34","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248\u2013255 (IEEE, 2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"52235_CR35","doi-asserted-by":"crossref","unstructured":"Boecking, B. et al. Making the most of text semantics to improve biomedical vision\u2013language processing. In European Conference on Computer Vision, 1\u201321 (Springer, 2022).","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"52235_CR36","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","volume":"29","author":"Z Huang","year":"2023","unstructured":"Huang, Z. et al. A visual-language foundation model for pathology image analysis using medical twitter. Nat. Med. 29, 2307\u20132316. https:\/\/doi.org\/10.1038\/s41591-023-02504-3 (2023).","journal-title":"Nat. Med."},{"key":"52235_CR37","doi-asserted-by":"publisher","unstructured":"Kim, C., Gadgil, S.U., DeGrave, A.J., Cai, Z.R., Daneshjou, R., Lee, S.I.: Fostering transparent medical image ai via an image-text foundation model grounded in medical literature. medRxiv. https:\/\/doi.org\/10.1101\/2023.06.07.23291119 (2023). Update in: Nat Med. 2024 Apr;30(4):1154-1165.","DOI":"10.1101\/2023.06.07.23291119"},{"key":"52235_CR38","doi-asserted-by":"publisher","unstructured":"You, K. et al. CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training. In Greenspan, H. et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023, 101\u2013111 (Springer, Cham, 2023). https:\/\/doi.org\/10.1007\/978-3-031-43895-0_10","DOI":"10.1007\/978-3-031-43895-0_10"},{"issue":"8","key":"52235_CR39","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1007\/s11227-025-07409-1","volume":"81","author":"Z Zheng","year":"2025","unstructured":"Zheng, Z. et al. Merge: multimodal-enhanced representation and guided ensemble for pneumonia recognition in chest x-ray images: Z. Zheng et al. J. Supercomput. 81(8), 907 (2025).","journal-title":"J. Supercomput."},{"key":"52235_CR40","doi-asserted-by":"crossref","unstructured":"Carion, N. et al. End-to-end object detection with transformers. In European Conference on Computer Vision, 213\u2013229 (Springer, 2020).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"52235_CR41","doi-asserted-by":"crossref","unstructured":"Li, L. H. et al. Grounded language-image pre-training. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10965\u201310975 (2022).","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"52235_CR42","doi-asserted-by":"crossref","unstructured":"Minderer, M. et al. Simple open-vocabulary object detection. In European Conference on Computer Vision, 728\u2013755 (Springer, 2022).","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"52235_CR43","doi-asserted-by":"crossref","unstructured":"Liu, S. et al. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"52235_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, H., & Wang, J. Towards adversarially robust object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 421\u2013430 (2019)","DOI":"10.1109\/ICCV.2019.00051"},{"key":"52235_CR45","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H.,& He, T. Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"52235_CR46","doi-asserted-by":"publisher","first-page":"104512","DOI":"10.1109\/ACCESS.2022.3210468","volume":"10","author":"HH Pham","year":"2022","unstructured":"Pham, H. H., Nguyen, H. Q., Nguyen, H. T., Le, L. T. & Khanh, L. An accurate and explainable deep learning system improves interobserver agreement in the interpretation of chest radiograph. IEEE Access 10, 104512\u2013104531 (2022).","journal-title":"IEEE Access"},{"issue":"4","key":"52235_CR47","doi-asserted-by":"publisher","first-page":"1922","DOI":"10.1109\/TPAMI.2020.3032166","volume":"44","author":"Z Tian","year":"2022","unstructured":"Tian, Z., Shen, C., Chen, H. & He, T. Fcos: A simple and strong anchor-free object detector. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 1922\u20131933. https:\/\/doi.org\/10.1109\/TPAMI.2020.3032166 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"52235_CR48","doi-asserted-by":"crossref","unstructured":"Xu, B., Guo, Y., Jiang, L., Yu, M., & Chen, J. Downscaled representation matters: Improving image rescaling with collaborative downscaled images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 12237\u201312247 (2023).","DOI":"10.1109\/ICCV51070.2023.01124"},{"key":"52235_CR49","doi-asserted-by":"crossref","unstructured":"Hesse, R., Schaub-Meyer, S., & Roth, S. Content-adaptive downsampling in convolutional neural networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 4544\u20134553 (2023).","DOI":"10.1109\/CVPRW59228.2023.00478"},{"key":"52235_CR50","unstructured":"Marin, D. et al. Token pooling in vision transformers. arXiv:2110.03860 (2021)."},{"key":"52235_CR51","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1016\/j.patcog.2019.02.021","volume":"91","author":"J Gu","year":"2019","unstructured":"Gu, J., Meng, G., Xiang, S. & Pan, C. Blind image quality assessment via learnable attention-based pooling. Pattern Recognit. 91, 332\u2013344 (2019).","journal-title":"Pattern Recognit."},{"issue":"1","key":"52235_CR52","doi-asserted-by":"publisher","first-page":"21097","DOI":"10.1038\/s41598-023-48482-x","volume":"13","author":"S Bhat","year":"2023","unstructured":"Bhat, S. et al. Aucreshaping: improved sensitivity at high-specificity. Sci. Rep. 13(1), 21097 (2023).","journal-title":"Sci. Rep."},{"issue":"6B","key":"52235_CR53","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1121\/1.1911889","volume":"46","author":"H Miller","year":"1969","unstructured":"Miller, H. The froc curve: A representation of the observer\u2019s performance for the method of free response. J. Acoust. Soc. America 46(6B), 1473\u20131476 (1969).","journal-title":"J. Acoust. Soc. America"},{"issue":"2","key":"52235_CR54","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1109\/JBHI.2017.2661805","volume":"22","author":"X Li","year":"2018","unstructured":"Li, X., Shen, L. & Luo, S. A solitary feature-based lung nodule detection approach for chest x-ray radiographs. IEEE J. Biomed. Health Inform. 22(2), 516\u2013524. https:\/\/doi.org\/10.1109\/JBHI.2017.2661805 (2018).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"52235_CR55","doi-asserted-by":"publisher","unstructured":"Lu, L., Miao, S., & Ye, L. Fracture detection and localization in chest x-rays using semi-supervised learning with dynamic sharpening. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1271\u20131275. https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746079 (2022).","DOI":"10.1109\/ICASSP43922.2022.9746079"},{"issue":"3","key":"52235_CR56","doi-asserted-by":"publisher","first-page":"191095","DOI":"10.1001\/jamanetworkopen.2019.1095","volume":"2","author":"EJ Hwang","year":"2019","unstructured":"Hwang, E. J. et al. Development and validation of a deep learning-based automated detection algorithm for major thoracic diseases on chest radiographs. JAMA Netw. Open 2(3), 191095\u2013191095 (2019).","journal-title":"JAMA Netw. Open"},{"key":"52235_CR57","first-page":"599","volume-title":"Inf. Process. Med. Imaging","author":"Y Wang","year":"2021","unstructured":"Wang, Y. et al. Knowledge distillation with adaptive asymmetric label sharpening for semi-supervised fracture detection in chest x-rays. In Inf. Process. Med. Imaging (eds Feragen, A. et al.) 599\u2013610 (Springer, Cham, 2021)."},{"key":"52235_CR58","doi-asserted-by":"publisher","first-page":"90380","DOI":"10.1109\/ACCESS.2020.2993872","volume":"8","author":"Q Zhang","year":"2020","unstructured":"Zhang, Q. & Kong, X. Design of automatic lung nodule detection system based on multi-scene deep learning framework. IEEE Access 8, 90380\u201390389. https:\/\/doi.org\/10.1109\/ACCESS.2020.2993872 (2020).","journal-title":"IEEE Access"},{"key":"52235_CR59","unstructured":"Lyu, C. et al. RTMDet: An Empirical Study of Designing Real-Time Object Detectors (2022)"},{"key":"52235_CR60","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"52235_CR61","doi-asserted-by":"crossref","unstructured":"Bhat, S. et al. Towards robust zero-shot chest x-ray classification: Exploring data distribution bias in chest x-ray datasets. In BVM Workshop, 191\u2013196 (Springer, 2025).","DOI":"10.1007\/978-3-658-47422-5_42"},{"key":"52235_CR62","doi-asserted-by":"crossref","unstructured":"Bhardwaj, P., Bhat, S., & Maier, A. Enhancing zero-shot learning in chest x-ray diagnostics. In Bildverarbeitung F\u00fcr die Medizin 2025: Proceedings, German Conference on Medical Image Computing, Regensburg March 09\u201311, 2025, 270 (Springer-Verlag, 2025).","DOI":"10.1007\/978-3-658-47422-5_61"},{"key":"52235_CR63","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113761","volume":"323","author":"Z Zheng","year":"2025","unstructured":"Zheng, Z. et al. Sge: Semantic-guided generalization enhancement for few-shot learning. Knowl.-Based Syst. 323, 113761 (2025).","journal-title":"Knowl.-Based Syst."},{"issue":"2","key":"52235_CR64","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1007\/s11227-024-06886-0","volume":"81","author":"H Wu","year":"2025","unstructured":"Wu, H. et al. Dara: distribution-aware representation alignment for semi-supervised domain adaptation in image classification. J. Supercomput. 81(2), 376 (2025).","journal-title":"J. Supercomput."},{"key":"52235_CR65","doi-asserted-by":"crossref","unstructured":"Zheng, Z. et al. Cross-domain few-shot chest x-ray recognition. In 2024 5th International Conference on Computers and Artificial Intelligence Technology (CAIT), 224\u2013229 (IEEE, 2024).","DOI":"10.1109\/CAIT64506.2024.10963262"},{"key":"52235_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2022.11.073","volume":"520","author":"H Wu","year":"2023","unstructured":"Wu, H., Zhao, Y. & Li, J. Invariant and consistent: Unsupervised representation learning for few-shot visual recognition. Neurocomputing 520, 1\u201314 (2023).","journal-title":"Neurocomputing"},{"key":"52235_CR67","doi-asserted-by":"crossref","unstructured":"Cui, Y. Feature aggregated queries for transformer-based video object detectors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 6365\u20136376 (2023).","DOI":"10.1109\/CVPR52729.2023.00616"},{"key":"52235_CR68","doi-asserted-by":"publisher","first-page":"4128","DOI":"10.1109\/TIP.2023.3285136","volume":"32","author":"Q Qi","year":"2023","unstructured":"Qi, Q., Hou, T., Lu, Y., Yan, Y. & Wang, H. Dgrnet: A dual-level graph relation network for video object detection. IEEE Trans. Image Process. 32, 4128\u20134141 (2023).","journal-title":"IEEE Trans. Image Process."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52235-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52235-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52235-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T06:14:25Z","timestamp":1778307265000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-52235-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,9]]},"references-count":68,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["52235"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-52235-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,9]]},"assertion":[{"value":"7 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"14688"}}