{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T23:48:29Z","timestamp":1781653709964,"version":"3.54.5"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T00:00:00Z","timestamp":1746748800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T00:00:00Z","timestamp":1746748800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100019180","name":"HORIZON EUROPE European Research Council","doi-asserted-by":"publisher","award":["101002198"],"award-info":[{"award-number":["101002198"]}],"id":[{"id":"10.13039\/100019180","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Purpose<\/jats:title>\n            <jats:p>Shortcut learning has been identified as a source of algorithmic unfairness in medical imaging artificial intelligence (AI), but its impact on photoacoustic tomography (PAT), particularly concerning sex bias, remains underexplored. This study investigates this issue using peripheral artery disease (PAD) diagnosis as a specific clinical application.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>To examine the potential for sex bias due to shortcut learning in convolutional neural network (CNNs) and assess how such biases might affect diagnostic predictions, we created training and test datasets with varying PAD prevalence between sexes. Using these datasets, we explored (1) whether CNNs can classify the sex from imaging data, (2) how sex-specific prevalence shifts impact PAD diagnosis performance and underdiagnosis disparity between sexes, and (3) how similarly CNNs encode sex and PAD features.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>Our study with 147 individuals demonstrates that CNNs can classify the sex from calf muscle PAT images, achieving an AUROC of 0.75. For PAD diagnosis, models trained on data with imbalanced sex-specific disease prevalence experienced significant performance drops (up to 0.21 AUROC) when applied to balanced test sets. Additionally, greater imbalances in sex-specific prevalence within the training data exacerbated underdiagnosis disparities between sexes. Finally, we identify evidence of shortcut learning by demonstrating the effective reuse of learned feature representations between PAD diagnosis and sex classification tasks.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>CNN-based models trained on PAT data may engage in shortcut learning by leveraging sex-related features, leading to biased and unreliable diagnostic predictions. Addressing demographic-specific prevalence imbalances and preventing shortcut learning is critical for developing models in the medical field that are both accurate and equitable across diverse patient populations.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s11548-025-03370-9","type":"journal-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T13:15:50Z","timestamp":1746796550000},"page":"1325-1333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Shortcut learning leads to sex bias in deep learning models for photoacoustic tomography"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8754-5811","authenticated-orcid":false,"given":"Marcel","family":"Knopp","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5432-774X","authenticated-orcid":false,"given":"Christoph J.","family":"Bender","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4440-2047","authenticated-orcid":false,"given":"Niklas","family":"Holzwarth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julius","family":"Kempf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milenko","family":"Caranovic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3535-2626","authenticated-orcid":false,"given":"Ferdinand","family":"Knieling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4114-7589","authenticated-orcid":false,"given":"Werner","family":"Lang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4016-5673","authenticated-orcid":false,"given":"Ulrich","family":"Rother","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5919-9646","authenticated-orcid":false,"given":"Alexander","family":"Seitel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4910-9368","authenticated-orcid":false,"given":"Lena","family":"Maier-Hein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9179-9414","authenticated-orcid":false,"given":"Kris K.","family":"Dreher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,9]]},"reference":[{"key":"3370_CR1","doi-asserted-by":"publisher","unstructured":"Zong Y, Yang Y, Hospedales TM (2023) MEDFAIR: benchmarking fairness for medical imaging. In: The eleventh international conference on learning representations: ICLR. https:\/\/doi.org\/10.48550\/arXiv.2210.01725 . https:\/\/openreview.net\/forum?id=6ve2CkeQe5S","DOI":"10.48550\/arXiv.2210.01725"},{"issue":"1","key":"3370_CR2","doi-asserted-by":"publisher","first-page":"4314","DOI":"10.1038\/s41467-023-39902-7","volume":"14","author":"A Brown","year":"2023","unstructured":"Brown A, Tomasev N, Freyberg J, Liu Y, Karthikesalingam A, Schrouff J (2023) Detecting shortcut learning for fair medical AI using shortcut testing. Nat Commun 14(1):4314. https:\/\/doi.org\/10.1038\/s41467-023-39902-7","journal-title":"Nat Commun"},{"key":"3370_CR3","doi-asserted-by":"publisher","unstructured":"Jones C, Roschewitz M, Glocker B (2023) The role of subgroup separability in\u00c2 group-fair medical image classification. In: Medical image computing and computer assisted intervention - MICCAI, pp 179\u2013188. https:\/\/doi.org\/10.1007\/978-3-031-43898-1_18","DOI":"10.1007\/978-3-031-43898-1_18"},{"key":"3370_CR4","doi-asserted-by":"publisher","unstructured":"Jim\u00e9nez-S\u00e0nchez A, Juodelyte D, Chamberlain B, Cheplygina V (2023) Detecting shortcuts in medical images\u2014a case study in chest X-Rays. In: 2023 IEEE 20th international symposium on biomedical imaging (ISBI).https:\/\/doi.org\/10.1109\/ISBI53787.2023.10230572","DOI":"10.1109\/ISBI53787.2023.10230572"},{"issue":"6","key":"3370_CR5","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230060","volume":"5","author":"B Glocker","year":"2023","unstructured":"Glocker B, Jones C, Roschewitz M, Winzeck S (2023) Risk of bias in chest radiography deep learning foundation models. Radiol Artif Intell 5(6):230060. https:\/\/doi.org\/10.1148\/ryai.230060","journal-title":"Radiol Artif Intell"},{"issue":"4","key":"3370_CR6","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1098\/rsfs.2011.0028","volume":"1","author":"P Beard","year":"2011","unstructured":"Beard P (2011) Biomedical photoacoustic imaging. Interface Focus 1(4):602\u2013631. https:\/\/doi.org\/10.1098\/rsfs.2011.0028","journal-title":"Interface Focus"},{"key":"3370_CR7","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.pacs.2018.05.001","volume":"10","author":"M Li","year":"2018","unstructured":"Li M, Tang Y, Yao J (2018) Photoacoustic tomography of blood oxygenation: a mini review. Photoacoustics 10:65\u201373. https:\/\/doi.org\/10.1016\/j.pacs.2018.05.001","journal-title":"Photoacoustics"},{"issue":"12","key":"3370_CR8","doi-asserted-by":"publisher","first-page":"3279","DOI":"10.1109\/TMI.2021.3082555","volume":"40","author":"A Wiacek","year":"2021","unstructured":"Wiacek A, Wang KC, Wu H, Bell MAL (2021) Photoacoustic-guided laparoscopic and open hysterectomy procedures demonstrated with human cadavers. IEEE Trans Med Imaging 40(12):3279\u20133292. https:\/\/doi.org\/10.1109\/TMI.2021.3082555","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"3370_CR9","doi-asserted-by":"publisher","first-page":"15519","DOI":"10.1038\/s41598-018-33931-9","volume":"8","author":"MA Lediju Bell","year":"2018","unstructured":"Lediju Bell MA, Shubert J (2018) Photoacoustic-based visual servoing of a needle tip. Sci Rep 8(1):15519. https:\/\/doi.org\/10.1038\/s41598-018-33931-9","journal-title":"Sci Rep"},{"issue":"16","key":"3370_CR10","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1088\/1361-6560\/ab1ede","volume":"64","author":"S Iskander-Rizk","year":"2019","unstructured":"Iskander-Rizk S, Steen AFW, Soest G (2019) Photoacoustic imaging for guidance of interventions in cardiovascular medicine. Phys Med Biol 64(16):16. https:\/\/doi.org\/10.1088\/1361-6560\/ab1ede","journal-title":"Phys Med Biol"},{"issue":"6","key":"3370_CR11","doi-asserted-by":"publisher","DOI":"10.1063\/5.0018190","volume":"128","author":"MA Lediju Bell","year":"2020","unstructured":"Lediju Bell MA (2020) Photoacoustic imaging for surgical guidance: principles, applications, and outlook. J Appl Phys 128(6):060904. https:\/\/doi.org\/10.1063\/5.0018190","journal-title":"J Appl Phys"},{"issue":"12","key":"3370_CR12","doi-asserted-by":"publisher","DOI":"10.1117\/1.JBO.22.12.121606","volume":"22","author":"N Gandhi","year":"2017","unstructured":"Gandhi N, Allard M, Kim S, Kazanzides P, Bell MAL (2017) Photoacoustic-based approach to surgical guidance performed with and without a da Vinci robot. J Biomed Opt 22(12):121606. https:\/\/doi.org\/10.1117\/1.JBO.22.12.121606","journal-title":"J Biomed Opt"},{"key":"3370_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.pacs.2021.100241","volume":"22","author":"J Gr\u00f6hl","year":"2021","unstructured":"Gr\u00f6hl J, Schellenberg M, Dreher K, Maier-Hein L (2021) Deep learning for biomedical photoacoustic imaging: a review. Photoacoustics 22:100241. https:\/\/doi.org\/10.1016\/j.pacs.2021.100241","journal-title":"Photoacoustics"},{"key":"3370_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.pacs.2020.100220","volume":"21","author":"AL Wagner","year":"2021","unstructured":"Wagner AL, Danko V, Federle A, Klett D, Simon D, Heiss R, J\u00fcngert J, Uder M, Schett G, Neurath MF, Woelfle J, Waldner MJ, Trollmann R, Regensburger AP, Knieling F (2021) Precision of handheld multispectral optoacoustic tomography for muscle imaging. Photoacoustics 21:100220. https:\/\/doi.org\/10.1016\/j.pacs.2020.100220","journal-title":"Photoacoustics"},{"issue":"S1","key":"3370_CR15","doi-asserted-by":"publisher","first-page":"11506","DOI":"10.1117\/1.JBO.29.S1.S11506","volume":"29","author":"TR Else","year":"2023","unstructured":"Else TR, Hacker L, Gr\u00f6hl J, Bunce EV, Tao R, Bohndiek SE (2023) Effects of skin tone on photoacoustic imaging and oximetry. J Biomed Opt 29(S1):11506. https:\/\/doi.org\/10.1117\/1.JBO.29.S1.S11506","journal-title":"J Biomed Opt"},{"issue":"1","key":"3370_CR16","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1111\/j.1751-1097.2012.01220.x","volume":"89","author":"AE Karsten","year":"2013","unstructured":"Karsten AE, Singh A, Karsten PA, Braun MWH (2013) Diffuse reflectance spectroscopy as a tool to measure the absorption coefficient in skin: South African skin phototypes. Photochem Photobiol 89(1):227\u2013233. https:\/\/doi.org\/10.1111\/j.1751-1097.2012.01220.x","journal-title":"Photochem Photobiol"},{"issue":"23","key":"3370_CR17","doi-asserted-by":"publisher","first-page":"12592","DOI":"10.1073\/pnas.1919012117","volume":"117","author":"AJ Larrazabal","year":"2020","unstructured":"Larrazabal AJ, Nieto N, Peterson V, Milone DH, Ferrante E (2020) Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proc Natl Acad Sci 117(23):12592\u201312594. https:\/\/doi.org\/10.1073\/pnas.1919012117","journal-title":"Proc Natl Acad Sci"},{"issue":"1","key":"3370_CR18","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1055\/s-0038-1636515","volume":"35","author":"K Schramm","year":"2018","unstructured":"Schramm K, Rochon PJ (2018) Gender differences in peripheral vascular disease. Semin Interv Radiol 35(1):9. https:\/\/doi.org\/10.1055\/s-0038-1636515","journal-title":"Semin Interv Radiol"},{"key":"3370_CR19","doi-asserted-by":"publisher","DOI":"10.1101\/2023.10.19.23297246","author":"M Caranovic","year":"2023","unstructured":"Caranovic M, Kempf J, Li Y, Regensburger AP, G\u00fcnther JS, Tr\u00e4ger AP, Lang W, Meyer A, Wagner AL, Woelfle J, Raming R, Paulus L-P, Buehler A, Uter W, Uder M, Behrendt C-A, Neurath MF, Waldner MJ, Knieling F, Rother U (2023) Derivation and validation of a non-invasive optoacoustic imaging biomarker for patients with intermittent claudication. medRxiv. https:\/\/doi.org\/10.1101\/2023.10.19.23297246","journal-title":"medRxiv"},{"key":"3370_CR20","doi-asserted-by":"publisher","unstructured":"Tan M, Le Q (2021) EfficientNetV2: smaller models and faster training. In: Proceedings of the 38th international conference on machine learning, pp 10096\u201310106. https:\/\/doi.org\/10.48550\/arXiv.2104.00298 . https:\/\/proceedings.mlr.press\/v139\/tan21a.html","DOI":"10.48550\/arXiv.2104.00298"},{"key":"3370_CR21","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848 . ISSN: 1063-6919","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"2","key":"3370_CR22","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41592-023-02151-z","volume":"21","author":"L Maier-Hein","year":"2024","unstructured":"Maier-Hein L, Reinke A, Godau P, Tizabi MD, Buettner F, Christodoulou E, Glocker B, Isensee F, Kleesiek J, Kozubek M, Reyes M, Riegler MA, Wiesenfarth M, Kavur AE, Sudre CH, Baumgartner M, Eisenmann M, Heckmann-N\u00f6tzel D, R\u00e4dsch T, Acion L, Antonelli M, Arbel T, Bakas S, Benis A, Blaschko MB, Cardoso MJ, Cheplygina V, Cimini BA, Collins GS, Farahani K, Ferrer L, Galdran A, Ginneken B, Haase R, Hashimoto DA, Hoffman MM, Huisman M, Jannin P, Kahn CE, Kainmueller D, Kainz B, Karargyris A, Karthikesalingam A, Kofler F, Kopp-Schneider A, Kreshuk A, Kurc T, Landman BA, Litjens G, Madani A, Maier-Hein K, Martel AL, Mattson P, Meijering E, Menze B, Moons KGM, M\u00fcller H, Nichyporuk B, Nickel F, Petersen J, Rajpoot N, Rieke N, Saez-Rodriguez J, S\u00e0nchez CI, Shetty S, Smeden M, Summers RM, Taha AA, Tiulpin A, Tsaftaris SA, Van Calster B, Varoquaux G, J\u00e4ger PF (2024) Metrics reloaded: recommendations for image analysis validation. Nature Methods 21(2):195\u2013212. https:\/\/doi.org\/10.1038\/s41592-023-02151-z","journal-title":"Nature Methods"},{"key":"3370_CR23","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1007\/978-3-031-72117-5_12","volume-title":"Medical Image Computing and Computer Assisted Intervention MICCAI 2024","author":"E Christodoulou","year":"2024","unstructured":"Christodoulou E, Reinke A, Houhou R, Kalinowski P, Erkan S, Sudre CH, Burgos N, Boutaj S, Loizillon S, Solal M, Rieke N, Cheplygina V, Antonelli M, Mayer LD, Tizabi MD, Cardoso MJ, Simpson A, J\u00e4ger PF, Kopp-Schneider A, Varoquaux G, Colliot O, Maier-Hein L (2024) Confidence Intervals Uncovered: Are We Ready for Real-World Medical Imaging AI? In: Linguraru MG, Dou Q, Feragen A, Giannarou S, Glocker B, Lekadir K, Schnabel JA (eds) Medical Image Computing and Computer Assisted Intervention MICCAI 2024. Springer, Cham, pp 124\u2013132. https:\/\/doi.org\/10.1007\/978-3-031-72117-5_12"},{"key":"3370_CR24","doi-asserted-by":"publisher","unstructured":"Yang Y, Liu Y, Liu X, Gulhane A, Mastrodicasa D, Wu W, Wang EJ, Sahani DW, Patel S (2024) Demographic bias of expert-level vision-language foundation models in medical imaging. arXiv .https:\/\/doi.org\/10.48550\/arXiv.2402.14815","DOI":"10.48550\/arXiv.2402.14815"},{"issue":"2","key":"3370_CR25","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1096\/fj.15-279554","volume":"30","author":"JA Clayton","year":"2015","unstructured":"Clayton JA (2015) Studying both sexes: a guiding principle for biomedicine. FASEB J 30(2):519. https:\/\/doi.org\/10.1096\/fj.15-279554. (Accessed 2024-10-23)","journal-title":"FASEB J"},{"key":"3370_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s44222-024-00240-y","volume":"2024","author":"J Park","year":"2024","unstructured":"Park J, Choi S, Knieling F, Clingman B, Bohndiek S, Wang LV, Kim C (2024) Clinical translation of photoacoustic imaging. Nat Rev Bioeng 2024:1\u201320. https:\/\/doi.org\/10.1038\/s44222-024-00240-y","journal-title":"Nat Rev Bioeng"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03370-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03370-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03370-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T14:47:56Z","timestamp":1751554076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03370-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,9]]},"references-count":26,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["3370"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03370-9","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,9]]},"assertion":[{"value":"4 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"F.K. is a co-inventor together with iThera Medical GmbH, Munich, Germany, on an EU patent application (EP 19 163 304.9). F.K. and U.R. are members of the advisory board of iThera Medical GmbH, Munich, Germany. F.K. received travel support from iThera Medical GmbH, Munich, Germany.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The studies performed for data collection were approved by the ethics committee of the FAU Erlangen-Nuremberg and performed by the ethical standards as laid down in the 1964 Declaration of Helsinki and its later amendments. Informed consent was obtained from all individual participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}