{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T12:08:45Z","timestamp":1779970125469,"version":"3.53.1"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Displays"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.displa.2026.103525","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T16:04:31Z","timestamp":1778861071000},"page":"103525","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Retrieval-augmented multimodal deep learning for interpretable lung nodule malignancy prediction"],"prefix":"10.1016","volume":"95","author":[{"given":"Ruibo","family":"Hou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shurong","family":"Chai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul Kumar","family":"Jain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinhao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyu","family":"Teng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanfen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yen-Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.displa.2026.103525_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2019.101628","article-title":"Shape and margin-aware lung nodule classification in low-dose CT images via soft activation mapping","volume":"60","author":"Lei","year":"2020","journal-title":"Med. Image Anal."},{"issue":"7","key":"10.1016\/j.displa.2026.103525_b2","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1109\/TMI.2022.3149344","article-title":"Learning from ambiguous labels for lung nodule malignancy prediction","volume":"41","author":"Liao","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.displa.2026.103525_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108309","article-title":"ProCAN: Progressive growing channel attentive non-local network for lung nodule classification","volume":"122","author":"Al-Shabi","year":"2022","journal-title":"Pattern Recognit."},{"issue":"5","key":"10.1016\/j.displa.2026.103525_b4","doi-asserted-by":"crossref","first-page":"3220","DOI":"10.1109\/JBHI.2024.3471194","article-title":"SAMA: A self-and-mutual attention network for accurate recurrence prediction of non-small cell lung cancer using genetic and CT data","volume":"29","author":"Ai","year":"2025","journal-title":"IEEE J. Biomed. Health Informatics"},{"key":"10.1016\/j.displa.2026.103525_b5","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.media.2019.07.004","article-title":"Semi-supervised adversarial model for benign\u2013malignant lung nodule classification on chest CT","volume":"57","author":"Xie","year":"2019","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.displa.2026.103525_b6","series-title":"International Conference on Machine Learning","first-page":"411","article-title":"Unimodal probability distributions for deep ordinal classification","author":"Beckham","year":"2017"},{"issue":"8","key":"10.1016\/j.displa.2026.103525_b7","doi-asserted-by":"crossref","first-page":"4084","DOI":"10.1109\/TNNLS.2021.3055816","article-title":"Convolutional ordinal regression forest for image ordinal estimation","volume":"33","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.displa.2026.103525_b8","series-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","article-title":"Ordinal regression with neuron stick-breaking for medical diagnosis","author":"Liu","year":"2018"},{"key":"10.1016\/j.displa.2026.103525_b9","doi-asserted-by":"crossref","unstructured":"B. Wu, X. Sun, L. Hu, Y. Wang, Learning with unsure data for medical image diagnosis, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 10590\u201310599.","DOI":"10.1109\/ICCV.2019.01069"},{"key":"10.1016\/j.displa.2026.103525_b10","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"403","article-title":"CLIP-lung: Textual knowledge-guided lung nodule malignancy prediction","author":"Lei","year":"2023"},{"key":"10.1016\/j.displa.2026.103525_b11","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.displa.2026.103525_b12","series-title":"International Conference on Learning Representations","article-title":"Generalization through memorization: Nearest neighbor language models","author":"Khandelwal","year":"2020"},{"key":"10.1016\/j.displa.2026.103525_b13","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103525_b14","series-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume","first-page":"874","article-title":"Leveraging passage retrieval with generative models for open domain question answering","author":"Izacard","year":"2021"},{"key":"10.1016\/j.displa.2026.103525_b15","doi-asserted-by":"crossref","unstructured":"C.-W. Xie, S. Sun, X. Xiong, Y. Zheng, D. Zhao, J. Zhou, Ra-clip: Retrieval augmented contrastive language-image pre-training, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19265\u201319274.","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"10.1016\/j.displa.2026.103525_b16","unstructured":"A. Iscen, M. Caron, A. Fathi, C. Schmid, Retrieval-Enhanced Contrastive Vision-Text Models, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.displa.2026.103525_b17","series-title":"International Conference on Machine Learning","first-page":"39755","article-title":"Retrieval-augmented multimodal language modeling","author":"Yasunaga","year":"2023"},{"issue":"2","key":"10.1016\/j.displa.2026.103525_b18","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1118\/1.3528204","article-title":"The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on ct scans","volume":"38","author":"Armato","year":"2011","journal-title":"Med. Phys."},{"key":"10.1016\/j.displa.2026.103525_b19","series-title":"Proceedings of Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025","first-page":"109","article-title":"Clinical Data-Driven Retrieval-Augmented Model for Lung Nodule Malignancy Prediction","volume":"LNCS 15969","author":"Hou","year":"2025"},{"key":"10.1016\/j.displa.2026.103525_b20","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"issue":"1","key":"10.1016\/j.displa.2026.103525_b21","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","article-title":"Deep learning in medical image analysis","volume":"19","author":"Shen","year":"2017","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"10.1016\/j.displa.2026.103525_b22","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.displa.2026.103525_b23","series-title":"Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19","first-page":"424","article-title":"3D U-net: learning dense volumetric segmentation from sparse annotation","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"10.1016\/j.displa.2026.103525_b24","series-title":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1055","article-title":"Unet 3+: A full-scale connected unet for medical image segmentation","author":"Huang","year":"2020"},{"key":"10.1016\/j.displa.2026.103525_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102802","article-title":"Transformers in medical imaging: A survey","volume":"88","author":"Shamshad","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.displa.2026.103525_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106791","article-title":"MedViT: A robust vision transformer for generalized medical image classification","volume":"157","author":"Manzari","year":"2023","journal-title":"Comput. Biol. Med."},{"issue":"4","key":"10.1016\/j.displa.2026.103525_b27","doi-asserted-by":"crossref","first-page":"81","DOI":"10.3390\/jimaging9040081","article-title":"Deep learning approaches for data augmentation in medical imaging: a review","volume":"9","author":"Kebaili","year":"2023","journal-title":"J. Imaging"},{"key":"10.1016\/j.displa.2026.103525_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2021.101985","article-title":"A survey on incorporating domain knowledge into deep learning for medical image analysis","volume":"69","author":"Xie","year":"2021","journal-title":"Med. Image Anal."},{"issue":"4","key":"10.1016\/j.displa.2026.103525_b29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3625287","article-title":"Explainable deep learning methods in medical image classification: A survey","volume":"56","author":"Patr\u00edcio","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.displa.2026.103525_b30","series-title":"2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society","first-page":"4881","article-title":"Deep learning-based radiomics models for early recurrence prediction of hepatocellular carcinoma with multi-phase CT images and clinical data","author":"Weibin","year":"2019"},{"key":"10.1016\/j.displa.2026.103525_b31","series-title":"International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.displa.2026.103525_b32","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.displa.2026.103525_b33","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103525_b34","series-title":"MICCAI","article-title":"Text-guided foundation model adaptation for pathological image classification","author":"Zhang","year":"2023"},{"key":"10.1016\/j.displa.2026.103525_b35","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"3876","article-title":"MedCLIP: Contrastive learning from unpaired medical images and text","author":"Wang","year":"2022"},{"key":"10.1016\/j.displa.2026.103525_b36","doi-asserted-by":"crossref","unstructured":"S.-C. Huang, L. Shen, M.P. Lungren, S. Yeung, 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, ICCV, 2021, pp. 3942\u20133951.","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"10.1016\/j.displa.2026.103525_b37","doi-asserted-by":"crossref","unstructured":"C. Wu, X. Zhang, Y. Zhang, Y. Wang, W. Xie, Medklip: Medical knowledge enhanced language-image pre-training for x-ray diagnosis, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 21372\u201321383.","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"10.1016\/j.displa.2026.103525_b38","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"525","article-title":"Pmc-clip: Contrastive language-image pre-training using biomedical documents","author":"Lin","year":"2023"},{"key":"10.1016\/j.displa.2026.103525_b39","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"547","article-title":"RAMM: Retrieval-augmented biomedical visual question answering with multi-modal pre-training","author":"Yuan","year":"2023"},{"key":"10.1016\/j.displa.2026.103525_b40","series-title":"International Conference on Machine Learning","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","author":"Borgeaud","year":"2022"},{"key":"10.1016\/j.displa.2026.103525_b41","doi-asserted-by":"crossref","unstructured":"J. Rao, Z. Shan, L. Liu, Y. Zhou, Y. Yang, Retrieval-based knowledge augmented vision language pre-training, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 5399\u20135409.","DOI":"10.1145\/3581783.3613848"},{"key":"10.1016\/j.displa.2026.103525_b42","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"11844","article-title":"Re-viLM: Retrieval-augmented visual language model for zero and few-shot image captioning","author":"Yang","year":"2023"},{"key":"10.1016\/j.displa.2026.103525_b43","series-title":"Retrieval-enhanced contrastive vision-text models","author":"Iscen","year":"2023"},{"key":"10.1016\/j.displa.2026.103525_b44","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"5000","article-title":"Writing by memorizing: Hierarchical retrieval-based medical report generation","author":"Yang","year":"2021"},{"issue":"2","key":"10.1016\/j.displa.2026.103525_b45","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","article-title":"The use of multiple measurements in taxonomic problems","volume":"7","author":"Fisher","year":"1936","journal-title":"Ann. Eugen."},{"key":"10.1016\/j.displa.2026.103525_b46","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.displa.2026.103525_b47","series-title":"Neural Networks: Tricks of the Trade","first-page":"9","article-title":"Efficient backprop","author":"LeCun","year":"2002"},{"issue":"3","key":"10.1016\/j.displa.2026.103525_b48","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2019","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.displa.2026.103525_b49","doi-asserted-by":"crossref","unstructured":"K. Zhou, J. Yang, C.C. Loy, Z. Liu, Conditional Prompt Learning for Vision-Language Models, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022.","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"201","key":"10.1016\/j.displa.2026.103525_b50","first-page":"1","article-title":"Understanding how dimension reduction tools work: an empirical approach to deciphering t-SNE, UMAP, TriMAP, and PaCMAP for data visualization","volume":"22","author":"Wang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.displa.2026.103525_b51","series-title":"AMIA Annual Symposium Proceedings","first-page":"438","article-title":"Launching into clinical space with medspacy: A new clinical text processing toolkit in python","volume":"vol. 2021","author":"Eyre","year":"2021"},{"issue":"5","key":"10.1016\/j.displa.2026.103525_b52","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1136\/jamia.2009.001560","article-title":"Mayo clinical text analysis and knowledge extraction system (cTAKES): Architecture, component evaluation and applications","volume":"17","author":"Savova","year":"2010","journal-title":"J. Am. Med. Informatics Assoc."},{"key":"10.1016\/j.displa.2026.103525_b53","series-title":"Proceedings of the Neural Information Processing Systems (Neurips 2021) Track on Datasets and Benchmarks","article-title":"RadGraph: Extracting clinical entities and relations from radiology reports","volume":"vol. 1","author":"Jain","year":"2021"},{"key":"10.1016\/j.displa.2026.103525_b54","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"12902","article-title":"RadGraph-XL: A large-scale expert-annotated dataset for entity and relation extraction from radiology reports","author":"Delbrouck","year":"2024"},{"key":"10.1016\/j.displa.2026.103525_b55","series-title":"A foundation model utilizing chest CT volumes and radiology reports for supervised-level zero-shot detection of abnormalities","author":"Hamamci","year":"2024"}],"container-title":["Displays"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938226001885?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938226001885?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T11:46:35Z","timestamp":1779968795000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0141938226001885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":55,"alternative-id":["S0141938226001885"],"URL":"https:\/\/doi.org\/10.1016\/j.displa.2026.103525","relation":{},"ISSN":["0141-9382"],"issn-type":[{"value":"0141-9382","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Retrieval-augmented multimodal deep learning for interpretable lung nodule malignancy prediction","name":"articletitle","label":"Article Title"},{"value":"Displays","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.displa.2026.103525","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103525"}}