{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T01:30:30Z","timestamp":1768872630537,"version":"3.49.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"MIT-Spain MISTI program"}],"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>Medical image segmentation plays a crucial role in diagnostic pipelines. This study investigates the integration of lesion-specific metadata with image data to enhance segmentation accuracy and reduce predictive uncertainty.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>The standard U-Net architecture was modified to incorporate lesion-specific metadata (Meta-UNet). Various integration strategies, including addition, weighted addition, and embedding layers, were evaluated. Additionally, a Bayesian Meta-UNet with Monte Carlo Dropout (MCD) was developed to assess the impact of metadata integration on model uncertainty. Uncertainty was quantified using measures such as Confidence Maps, Entropy, Mutual Information, and Expected Pairwise Kullback\u2013Leibler divergence (EPKL). An aggregation strategy was also introduced to provide a single comprehensive uncertainty score per image.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>Meta-UNet outperformed standard U-Net across PH2, ISIC 2018, and HAM10000 datasets. On PH2, it achieved 84.64% accuracy and 90.62% Intersection over Union (IoU), compared to 83.36% and 89.19%. On ISIC 2018, U-Net scored 71.02 \u00b1 6.69 IoU and 79.89 \u00b1 5.09 Dice. On HAM10000, Meta-UNet achieved 88.66 \u00b1 6.09 IoU and 93.42 \u00b1 5.19 Dice. Meta-UNet reduced uncertainty (e.g., 0.149 vs. 0.1745), highlighting the benefit of metadata integration in improving segmentation accuracy and model confidence.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>Integrating lesion-specific metadata into the U-Net architecture significantly improves segmentation accuracy and reduces predictive uncertainty. The inclusion of metadata enhances model confidence and reliability, underscoring its potential to strengthen diagnostic segmentation pipelines.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s11548-025-03490-2","type":"journal-article","created":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T06:09:23Z","timestamp":1753855763000},"page":"1911-1922","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Meta-UNet: enhancing skin-lesion segmentation with multimodal feature integration and uncertainty estimation"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3499-8062","authenticated-orcid":false,"given":"O. K.","family":"Sikha","sequence":"first","affiliation":[]},{"given":"Alaysia Leilani B.","family":"Stone","sequence":"additional","affiliation":[]},{"given":"Miguel A.","family":"Gonz\u00e1lez Ballester","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,30]]},"reference":[{"key":"3490_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108238","volume":"171","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Shen Z, Jiao R (2024) Segment anything model for medical image segmentation: current applications and future directions. Comput Biol Med 171:108238","journal-title":"Comput Biol Med"},{"key":"3490_CR2","doi-asserted-by":"crossref","unstructured":"Sikha O, Galdran A, Riera-Marin M, Garc\u00eda J, Rodr\u00edguez-Comas J, Piella G, Ballester MAG (2024) Uncertainty aware segmentation quality assessment in medical images. In: 2024 IEEE international symposium on biomedical imaging (ISBI), IEEE, pp 1\u20135","DOI":"10.1109\/ISBI56570.2024.10635509"},{"key":"3490_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115486","volume":"184","author":"L Vasquez-Espinoza","year":"2021","unstructured":"Vasquez-Espinoza L, Castillo-Cara M, Orozco-Barbosa L (2021) On the relevance of the metadata used in the semantic segmentation of indoor image spaces. Expert Syst Appl 184:115486","journal-title":"Expert Syst Appl"},{"key":"3490_CR4","doi-asserted-by":"crossref","unstructured":"Jha D, Riegler MA, Johansen D, Halvorsen P, Johansen HD (2020) Doubleu-net: A deep convolutional neural network for medical image segmentation. In: 2020 IEEE 33rd international symposium on computer-based medical systems (CBMS), IEEE, pp 558\u2013564","DOI":"10.1109\/CBMS49503.2020.00111"},{"key":"3490_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108673","volume":"128","author":"H Basak","year":"2022","unstructured":"Basak H, Kundu R, Sarkar R (2022) Mfsnet: a multi focus segmentation network for skin lesion segmentation. Pattern Recogn 128:108673","journal-title":"Pattern Recogn"},{"key":"3490_CR6","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3490_CR7","doi-asserted-by":"crossref","unstructured":"Yagi N, Nii M, Kobashi S (2019) Abdominal organ area segmentation using u-net for cancer radiotherapy support. In: 2019 IEEE international conference on systems, man and cybernetics (SMC), pp 1210\u20131214","DOI":"10.1109\/SMC.2019.8913943"},{"key":"3490_CR8","doi-asserted-by":"crossref","unstructured":"Kakeya H, Okada T, Oshiro Y (2018) 3D UJAPANet: mixture of convolutional networks for abdominal multi-organ CT segmentation. In: MICCAI 2018, pp 426\u2013433","DOI":"10.1007\/978-3-030-00937-3_49"},{"key":"3490_CR9","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi S-A (2016) V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 4th international conference on 3D vision (3DV), pp 565\u2013571","DOI":"10.1109\/3DV.2016.79"},{"key":"3490_CR10","unstructured":"Oktay O, Schlemper J, Folgoc LL, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B, et al (2018) Attention u-net: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999"},{"key":"3490_CR11","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/JBHI.2020.2986926","volume":"25","author":"A Sinha","year":"2019","unstructured":"Sinha A, Dolz J (2019) Multi-scale self-guided attention for medical image segmentation. IEEE J Biomed Health Inform 25:121\u2013130","journal-title":"IEEE J Biomed Health Inform"},{"issue":"2","key":"3490_CR12","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/TMI.2020.3035253","volume":"40","author":"R Gu","year":"2020","unstructured":"Gu R, Wang G, Song T, Huang R, Aertsen M, Deprest J, Ourselin S, Vercauteren T, Zhang S (2020) CA-Net: comprehensive attention convolutional neural networks for explainable medical image segmentation. IEEE Trans Med Imaging 40(2):699\u2013711","journal-title":"IEEE Trans Med Imaging"},{"key":"3490_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104836","volume":"137","author":"Y Li","year":"2021","unstructured":"Li Y, Yang J, Ni J, Elazab A, Wu J (2021) TA-Net: triple attention network for medical image segmentation. Comput Biol Med 137:104836","journal-title":"Comput Biol Med"},{"key":"3490_CR14","doi-asserted-by":"crossref","unstructured":"Zhang Z, Fu H, Dai H, Shen J, Pang Y, Shao L (2019) ET-Net: A generic edge-attention guidance network for medical image segmentation. In: Medical image computing and computer assisted intervention\u2013miccai 2019: 22nd international conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part I 22, Springer, pp 442\u2013450","DOI":"10.1007\/978-3-030-32239-7_49"},{"key":"3490_CR15","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In: International conference on machine learning, PMLR, pp 1050\u20131059"},{"key":"3490_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106321","volume":"152","author":"C Dong","year":"2023","unstructured":"Dong C, Dai D, Zhang Y, Zhang C, Li Z, Xu S (2023) Learning from dermoscopic images in association with clinical metadata for skin lesion segmentation and classification. Comput Biol Med 152:106321","journal-title":"Comput Biol Med"},{"key":"3490_CR17","unstructured":"Kendall A, Gal Y (2017) What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in neural information processing Systems, vol 30"},{"key":"3490_CR18","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"3490_CR19","unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille AL, Zhou Y (2021) Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306"},{"key":"3490_CR20","doi-asserted-by":"crossref","unstructured":"Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, Wang M (2022) Swin-unet: Unet-like pure transformer for medical image segmentation. In: European conference on computer vision, Springer, pp 205\u2013218","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"3490_CR21","doi-asserted-by":"crossref","unstructured":"Perera S, Erzurumlu Y, Gulati D, Yilmaz A (2024) Mobileunetr: A lightweight end-to-end hybrid vision transformer for efficient medical image segmentation. arXiv preprint arXiv:2409.03062","DOI":"10.1007\/978-3-031-91721-9_18"},{"key":"3490_CR22","doi-asserted-by":"crossref","unstructured":"Wang J, Wei L, Wang L, Zhou Q, Zhu L, Qin J (2021) Boundary-aware transformers for skin lesion segmentation. In: Medical image computing and computer assisted intervention\u2013mICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part i 24, pp. 206\u2013216. Springer","DOI":"10.1007\/978-3-030-87193-2_20"},{"issue":"6","key":"3490_CR23","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","volume":"39","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Siddiquee MMR, Tajbakhsh N, Liang J (2019) Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans Med Imaging 39(6):1856\u20131867","journal-title":"IEEE Trans Med Imaging"},{"key":"3490_CR24","doi-asserted-by":"crossref","unstructured":"Jha D, Smedsrud PH, Riegler MA, Johansen D, De\u00a0Lange T, Halvorsen P, Johansen HD (2019) Resunet++: An advanced architecture for medical image segmentation. In: 2019 IEEE International Symposium on Multimedia (ISM), IEEE, pp 225\u20132255","DOI":"10.1109\/ISM46123.2019.00049"},{"key":"3490_CR25","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2020","unstructured":"Isensee F, Jaeger PF, Kohl SAA, Peterson J, Maier-Hein KH (2020) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203\u2013211","journal-title":"Nat Methods"},{"key":"3490_CR26","doi-asserted-by":"crossref","unstructured":"Plutenko I, Papkov M, Palo K, Parts L, Fishman D (2023) Metadata improves segmentation through multitasking elicitation. In: MICCAI workshop on domain adaptation and representation transfer, Springer, pp 147\u2013155","DOI":"10.1007\/978-3-031-45857-6_15"},{"key":"3490_CR27","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/s00530-024-01260-9","volume":"30","author":"R Gu","year":"2024","unstructured":"Gu R, Zhang Y, Wang L, Chen D, Wang Y, Ge R, Jiao Z, Ye J, Jia G, Wang L (2024) Mmy-net: a multimodal network exploiting image and patient metadata for simultaneous segmentation and diagnosis. Multimedia Syst 30:72","journal-title":"Multimedia Syst"},{"key":"3490_CR28","doi-asserted-by":"crossref","unstructured":"Khan A, Asad M, Benning M, Roney C, Slabaugh G (2024) Compositional segmentation of cardiac images leveraging metadata","DOI":"10.1109\/WACV61041.2025.00919"},{"key":"3490_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2025.102547","volume":"123","author":"O Sikha","year":"2025","unstructured":"Sikha O, Riera-Mar\u00edn M, Galdran A, L\u00f3pez JG, Rodr\u00edguez-Comas J, Piella G, Ballester MAG (2025) Uncertainty-aware segmentation quality prediction via deep learning Bayesian modeling: comprehensive evaluation and interpretation on skin cancer and liver segmentation. Comput Med Imaging Graph 123:102547","journal-title":"Comput Med Imaging Graph"},{"issue":"12","key":"3490_CR30","doi-asserted-by":"publisher","first-page":"3868","DOI":"10.1109\/TMI.2020.3006437","volume":"39","author":"A Mehrtash","year":"2020","unstructured":"Mehrtash A, Wells WM, Tempany CM, Abolmaesumi P, Kapur T (2020) Confidence calibration and predictive uncertainty estimation for deep medical image segmentation. IEEE Trans Med Imaging 39(12):3868\u20133878","journal-title":"IEEE Trans Med Imaging"},{"key":"3490_CR31","doi-asserted-by":"crossref","unstructured":"Mendon\u00e7a T, Ferreira PM, Marques J, Marcal ARS, Rozeira J (2013) $$\\text{Ph}^{2}$$ - a dermoscopic image database for research and benchmarking. In: 35th international conference of the IEEE engineering in medicine and biology society","DOI":"10.1109\/EMBC.2013.6610779"},{"key":"3490_CR32","unstructured":"Codella N, Rotemberg V, Tschandl P, Celebi ME, Dusza S, Gutman D, Helba B, Kalloo A, Liopyris K, Marchetti M, et al (2019) Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1902.03368"},{"issue":"1","key":"3490_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.161","volume":"5","author":"P Tschandl","year":"2018","unstructured":"Tschandl P, Rosendahl C, Kittler H (2018) The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci Data 5(1):1\u20139","journal-title":"Sci Data"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03490-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03490-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03490-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T11:22:07Z","timestamp":1758972127000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03490-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,30]]},"references-count":33,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["3490"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03490-2","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,30]]},"assertion":[{"value":"13 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 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":"Alaysia Leilani B. Stone received support from the MIT-Spain MISTI Program. AI tools were used for language editing, with all content reviewed and revised by the authors for accuracy and originality.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}