{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T07:32:14Z","timestamp":1793345534170,"version":"4.5.0"},"reference-count":36,"publisher":"IOP Publishing","issue":"5","license":[{"start":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:00:00Z","timestamp":1793318400000},"content-version":"vor","delay-in-days":29,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:00:00Z","timestamp":1793318400000},"content-version":"tdm","delay-in-days":29,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"JST CREST, Japan","award":["JPMJCR25T4"],"award-info":[{"award-number":["JPMJCR25T4"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LZ22F020012"],"award-info":[{"award-number":["LZ22F020012"]}],"id":[{"id":"https:\/\/ror.org\/04aqat463","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Japanese Ministry of Education, Culture, Sports, Science and Technology","award":["20KK0234"],"award-info":[{"award-number":["20KK0234"]}],"id":[{"id":"https:\/\/ror.org\/048rj2z13","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Clinical metadata is widely used as auxiliary information in medical image analysis and provides important diagnostic cues for similar-case retrieval. With the development of biomedical language models, structured clinical metadata can be converted into natural-language descriptions and encoded as text representations. However, it remains unclear whether such verbalized metadata is consistently more effective than compact structured vectors when retrieval accuracy, computational efficiency, and robustness are considered together. We compare structured vector retrieval, sentence-level verbalized metadata retrieval, and phrase-level verbalized metadata retrieval using multiple biomedical text encoders. Experiments are conducted on three public medical datasets spanning lung CT (LIDC-IDRI), dermatology (PAD-UFES-20), and breast mammography (CBIS-DDSM). We report five-fold mean\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mo>\u00b1<\/mml:mo>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    standard deviation and paired statistical tests, and further evaluate robustness under missing and incorrect metadata perturbations. Across the three datasets, structured metadata provides a strong and computationally efficient baseline, while sentence- and phrase-level verbalization produce dataset- and metric-dependent changes. The key paired Recall@5 and MV@5 comparisons do not show a consistent statistically significant improvement over structured vectors. Robustness trends also vary with the dataset and perturbation type. These findings indicate that compact structured metadata remains a practical baseline for medical case retrieval, while the benefit of verbalization depends on the metadata structure and evaluation setting.\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/aeb80d","type":"journal-article","created":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T22:48:22Z","timestamp":1792709302000},"page":"055075","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A comparative study of structured and verbalized clinical metadata for robust medical case retrieval"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1720-4183","authenticated-orcid":true,"given":"Ruibo","family":"Hou","sequence":"first","affiliation":[{"name":"Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Rahul","family":"Kumar Jain","sequence":"additional","affiliation":[{"name":"Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Shurong","family":"Chai","sequence":"additional","affiliation":[{"name":"Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]},{"given":"Shiyu","family":"Teng","sequence":"additional","affiliation":[{"name":"Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"}]},{"given":"Yinhao","family":"Li","sequence":"additional","affiliation":[{"name":"Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"}]},{"given":"Jiaqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"}]},{"given":"Lanfen","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5952-0188","authenticated-orcid":true,"given":"Yen-Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Ritsumeikan University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]}],"member":"266","published-online":{"date-parts":[[2026,10,30]]},"reference":[{"key":"bpexaeb80dbib1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ijmedinf.2003.11.024","type":"journal-article","article-title":"A review of content-based image retrieval systems in medical applications\u2013clinical benefits and future directions","volume":"73","author":"M\u00fcller","year":"2004","journal-title":"Int. J. Med. Inform."},{"key":"bpexaeb80dbib2","first-page":"547","type":"conference-proceedings","article-title":"Ramm: retrieval-augmented biomedical visual question answering with multi-modal pre-training","author":"Yuan","year":"2023"},{"key":"bpexaeb80dbib3","first-page":"607","type":"conference-proceedings","article-title":"Semantic-aware chest x-ray report generation with domain-specific lexicon and diversity-controlled retrieval","volume":"LNCS 15965","author":"Zhang","year":"2025"},{"key":"bpexaeb80dbib4","first-page":"109","type":"conference-proceedings","article-title":"Clinical data-driven retrieval-augmented model for lung nodule malignancy prediction","volume":"LNCS 15969","author":"Hou","year":"2025"},{"key":"bpexaeb80dbib5","first-page":"8003","type":"conference-proceedings","article-title":"LinkBERT: pretraining language models with document links","author":"Yasunaga","year":"2022"},{"key":"bpexaeb80dbib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3458754","type":"journal-article","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2021","journal-title":"ACM Trans. Comput. Healthc."},{"key":"bpexaeb80dbib7","first-page":"72","type":"conference-proceedings","article-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019"},{"key":"bpexaeb80dbib8","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1118\/1.3528204","type":"journal-article","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":"bpexaeb80dbib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.106221","type":"journal-article","article-title":"PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones","volume":"32","author":"Pacheco","year":"2020","journal-title":"Data Br."},{"key":"bpexaeb80dbib10","article-title":"Curated breast imaging subset of DDSM (CBIS-DDSM)","author":"Lee","year":"2016","type":"other"},{"key":"bpexaeb80dbib11","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.177","type":"journal-article","article-title":"A curated mammography data set for use in computer-aided detection and diagnosis research","volume":"4","author":"Lee","year":"2017","journal-title":"Sci. Data"},{"key":"bpexaeb80dbib12","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/s10278-010-9290-9","type":"journal-article","article-title":"Content-based image retrieval in radiology: current status and future directions","volume":"24","author":"Akg\u00fcl","year":"2011","journal-title":"J. Digit. Imaging"},{"key":"bpexaeb80dbib13","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1007\/s10278-013-9619-2","type":"journal-article","article-title":"Content-based medical image retrieval: a survey of applications to multidimensional and multimodality data","volume":"26","author":"Kumar","year":"2013","journal-title":"J. Digit. Imaging"},{"key":"bpexaeb80dbib14","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1109\/TMI.2010.2063711","type":"journal-article","article-title":"Case retrieval in medical databases by fusing heterogeneous information","volume":"30","author":"Quellec","year":"2011","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexaeb80dbib15","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1109\/TMI.2014.2361481","type":"journal-article","article-title":"Towards large-scale histopathological image analysis: hashing-based image retrieval","volume":"34","author":"Zhang","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexaeb80dbib16","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1109\/TMI.2020.3043641","type":"journal-article","article-title":"Multi-modal siamese network for diagnostically similar lesion retrieval in prostate MRI","volume":"40","author":"Rossi","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexaeb80dbib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101981","type":"journal-article","article-title":"Deep triplet hashing network for case-based medical image retrieval","volume":"69","author":"Fang","year":"2021","journal-title":"Med. Image Anal."},{"key":"bpexaeb80dbib18","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102301","type":"journal-article","article-title":"Dermoscopic image retrieval based on rotation-invariance deep hashing","volume":"77","author":"Zhang","year":"2022","journal-title":"Med. Image Anal."},{"key":"bpexaeb80dbib19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102645","type":"journal-article","article-title":"RetCCL: clustering-guided contrastive learning for whole-slide image retrieval","volume":"83","author":"Wang","year":"2023","journal-title":"Med. Image Anal."},{"key":"bpexaeb80dbib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110571","type":"journal-article","article-title":"Evaluating pre-trained convolutional neural networks and foundation models as feature extractors for content-based medical image retrieval","volume":"150","author":"Mahbod","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"bpexaeb80dbib21","first-page":"5000","type":"conference-proceedings","article-title":"Writing by memorizing: hierarchical retrieval-based medical report generation","author":"Yang","year":"2021"},{"key":"bpexaeb80dbib22","first-page":"534","type":"conference-proceedings","article-title":"Pre-to-Post operative MRI generation with retrieval-based visual In-context learning","volume":"LNCS 15960","author":"Kang","year":"2025"},{"key":"bpexaeb80dbib23","first-page":"24859","article-title":"2023 retrieval-augmented multiple instance learning","author":"CUI","type":"conference-proceedings"},{"key":"bpexaeb80dbib24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JBHI.2026.3703057","type":"journal-article","article-title":"RAPT: retrieval-augmented visual prompting with text-guidance for pathological image classification","author":"Hou","year":"2026","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"bpexaeb80dbib25","first-page":"9927","type":"book","article-title":"Explainable depression detection in clinical interviews with personalized retrieval-augmented generation","author":"Zhang","year":"2025"},{"key":"bpexaeb80dbib26","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2026.103525","type":"journal-article","article-title":"Retrieval-augmented multimodal deep learning for interpretable lung nodule malignancy prediction","volume":"95","author":"Hou","year":"2026","journal-title":"Displays"},{"key":"bpexaeb80dbib27","article-title":"TabText: language-based representations of tabular health data for predictive modelling","author":"Carballo","year":"2025","type":"preprint"},{"key":"bpexaeb80dbib28","first-page":"12925","author":"Lin","year":"2024","type":"book"},{"key":"bpexaeb80dbib29","first-page":"5414","type":"book","article-title":"When raw data prevails: are large language model embeddings effective in numerical data representation for medical machine learning applications?","author":"Gao","year":"2024"},{"key":"bpexaeb80dbib30","article-title":"The faiss library","author":"Douze","year":"2024","type":"preprint"},{"key":"bpexaeb80dbib31","first-page":"10590","type":"conference-proceedings","article-title":"Learning with unsure data for medical image diagnosis","author":"Wu","year":"2019"},{"key":"bpexaeb80dbib32","first-page":"403","author":"Lei","year":"2023","type":"book"},{"key":"bpexaeb80dbib33","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","type":"journal-article","article-title":"The cancer imaging archive (tcia): maintaining and operating a public information repository","volume":"26","author":"Clark","year":"2013","journal-title":"J. Digit. Imaging"},{"key":"bpexaeb80dbib34","doi-asserted-by":"publisher","DOI":"10.7937\/K9\/TCIA.2015.LO9QL9SX","type":"journal-article","article-title":"Data From LIDC-IDRI, The Cancer Imaging Archive","author":"Armato III","year":"2015"},{"key":"bpexaeb80dbib35","doi-asserted-by":"publisher","DOI":"10.17632\/zr7vgbcyr2.1","type":"journal-article","article-title":"PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphones","author":"Pacheco","year":"2020","journal-title":"Mendeley Data"},{"key":"bpexaeb80dbib36","doi-asserted-by":"publisher","DOI":"10.7937\/K9\/TCIA.2016.7O02S9CY","type":"journal-article","article-title":"Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM The Cancer Imaging Archive","author":"Sawyer-Lee","year":"2016"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb80d","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb80d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb80d","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb80d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb80d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb80d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb80d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb80d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T06:52:29Z","timestamp":1793343149000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeb80d"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":36,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,10,30]]},"published-print":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/aeb80d","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"assertion":[{"value":"A comparative study of structured and verbalized clinical metadata for robust medical case retrieval","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-06-28","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-10-22","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-10-30","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}