{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T04:20:19Z","timestamp":1791865219561,"version":"4.3.4"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["TED2021-131913B-I00"],"award-info":[{"award-number":["TED2021-131913B-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PID2020-115468RB-I00"],"award-info":[{"award-number":["PID2020-115468RB-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PID2023-148895OB-I00"],"award-info":[{"award-number":["PID2023-148895OB-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007515","name":"Universidad de Valladolid","doi-asserted-by":"publisher","award":["PIF-UVa grant"],"award-info":[{"award-number":["PIF-UVa grant"]}],"id":[{"id":"10.13039\/501100007515","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007515","name":"Universidad de Valladolid","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007515","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Ann Biomed Eng"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Early detection of retinal lesions helps to avoid visual loss or blindness. The main lesions associated with eye diseases include soft exudates, hard exudates, microaneurysms, and hemorrhages. However, the segmentation of these four kinds of lesions is difficult and time-consuming due to their uncertainty in size, contrast, and high inter-class similarity. To address these issues, this study presents Deep Decoder-Focused U-Net (DDFU-Net), an asymmetric dense U-Net model for automatic and accurate multi-lesion segmentation using fundus images. Our approach simultaneously segments all four kinds of retinal lesions after proving that multi-task learning yields better results than single-task learning. DDFU-Net incorporates an asymmetric design with five dense blocks in the encoder and seven dense blocks in the decoder. This design enhances feature extraction while ensuring a more refined reconstruction of lesion boundaries, particularly for small and complex structures. By allocating more layers to the decoder, the model improves segmentation accuracy by gradually restoring spatial details lost during down-sampling, mitigating over-compression, and enhancing fine-grained feature preservation. Comprehensive experiments on IDRiD and DDR datasets well demonstrate the superiority of our approach, which outperforms state-of-the-art segmentation methods. Specifically, DDFU-Net achieved a mean Area Under the Precision-Recall Curve of 54.86%, a mean Intersection Over Union of 36.96%, and mean Dice scores of 52.24% on the DDR test set. On the IDRiD test set, it achieved 66.69%, 57.31%, and 69.93%, respectively. The asymmetric structure outperforms traditional symmetric U-Nets by capturing more detailed features during encoding while reducing complexity during decoding. The proposed method can be useful to aid in the diagnosis of eye diseases, reducing the workload of specialists and improving the attention to patients.<\/jats:p>","DOI":"10.1007\/s10439-026-04032-w","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T14:46:04Z","timestamp":1773326764000},"page":"3231-3251","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DDFU-Net: A Deep Decoder-Focused U-Net Model for Retinal Lesion Segmentation"],"prefix":"10.1007","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0678-4638","authenticated-orcid":false,"given":"Mar\u00eda","family":"Herrero-Tudela","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Romero-Ora\u00e1","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gonzalo C.","family":"Guti\u00e9rrez-Tobal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Hornero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mar\u00eda I.","family":"L\u00f3pez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro","family":"Romero-Aroca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mar\u00eda","family":"Garc\u00eda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,12]]},"reference":[{"issue":"3","key":"4032_CR1","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/TBME.2017.2707578","volume":"65","author":"SS Kar","year":"2018","unstructured":"Kar, S. S., and S. P. Maity. Automatic detection of retinal lesions for screening of diabetic retinopathy. IEEE Trans. Biomed. Eng. 65(3):608\u2013618, 2018. https:\/\/doi.org\/10.1109\/TBME.2017.2707578.","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"4032_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122742","volume":"241","author":"QV Do","year":"2024","unstructured":"Do, Q. V., H. T. Hoang, N. V. Vu, D. A. De Jesus, L. Sanchez Brea, H. X. Nguyen, A. T. L. Nguyen, T. N. Le, D. T. M. Dinh, M. T. B. Nguyen, H. C. Nguyen, A. T. V. Bui, H. V. Le, K. Gillen, T. T. Vu, and H. M. Luu. Segmentation of hard exudate lesions in color fundus image using two-stage CNN-based methods. Exp. Syst. Appl.241:122742, 2024. https:\/\/doi.org\/10.1016\/j.eswa.2023.122742.","journal-title":"Exp. Syst. Appl."},{"issue":"6","key":"4032_CR3","doi-asserted-by":"publisher","first-page":"1596","DOI":"10.1109\/TMI.2022.3143833","volume":"41","author":"S Huang","year":"2022","unstructured":"Huang, S., J. Li, Y. Xiao, N. Shen, and T. Xu. RTNet: Relation transformer network for diabetic retinopathy multi-lesion segmentation. IEEE Trans. Med. Imaging. 41(6):1596\u20131607, 2022. https:\/\/doi.org\/10.1109\/TMI.2022.3143833.","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"22","key":"4032_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s20226549","volume":"20","author":"R Romero-Ora\u00e1","year":"2020","unstructured":"Romero-Ora\u00e1, R., M. Garc\u00eda, J. Ora\u00e1-P\u00e9rez, M. I. L\u00f3pez-G\u00e1lvez, and R. Hornero. Effective fundus image decomposition for the detection of red lesions and hard exudates to aid in the diagnosis of diabetic retinopathy. Sensors. 20(22):1\u201310, 2020.","journal-title":"Sensors"},{"key":"4032_CR5","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.cmpb.2016.05.016","volume":"133","author":"E Imani","year":"2016","unstructured":"Imani, E., and H.-R. Pourreza. A novel method for retinal exudate segmentation using signal separation algorithm. Comput. Methods Programs Biomed. 133:195\u2013205, 2016. https:\/\/doi.org\/10.1016\/j.cmpb.2016.05.016.","journal-title":"Comput. Methods Programs Biomed."},{"issue":"1","key":"4032_CR6","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.bbe.2017.10.003","volume":"38","author":"J Kaur","year":"2018","unstructured":"Kaur, J., and D. Mittal. A generalized method for the segmentation of exudates from pathological retinal fundus images. Biocybern. Biomed. Eng. 38(1):27\u201353, 2018. https:\/\/doi.org\/10.1016\/j.bbe.2017.10.003.","journal-title":"Biocybern. Biomed. Eng."},{"key":"4032_CR7","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.neucom.2019.04.019","volume":"349","author":"S Guo","year":"2019","unstructured":"Guo, S., T. Li, H. Kang, N. Li, Y. Zhang, and K. Wang. L-Seg: An end-to-end unified framework for multi-lesion segmentation of fundus images. Neurocomputing. 349:52\u201363, 2019. https:\/\/doi.org\/10.1016\/j.neucom.2019.04.019.","journal-title":"Neurocomputing"},{"key":"4032_CR8","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.inffus.2021.02.017","volume":"73","author":"W He","year":"2021","unstructured":"He, W., X. Wang, L. Wang, Y. Huang, Z. Yang, X. Yao, X. Zhao, L. Ju, L. Wu, L. Wu, H. Lu, and Z. Ge. Incremental learning for exudate and hemorrhage segmentation on fundus images. Inf. Fusion. 73:157\u2013164, 2021. https:\/\/doi.org\/10.1016\/j.inffus.2021.02.017.","journal-title":"Inf. Fusion"},{"key":"4032_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105050","volume":"88","author":"T Guo","year":"2024","unstructured":"Guo, T., J. Yang, and Q. Yu. Diabetic retinopathy lesion segmentation using deep multi-scale framework. Biomed. Signal Process. Control.88:105050, 2024. https:\/\/doi.org\/10.1016\/j.bspc.2023.105050.","journal-title":"Biomed. Signal Process. Control"},{"key":"4032_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101561","volume":"59","author":"P Porwal","year":"2020","unstructured":"Porwal, P., S. Pachade, M. Kokare, G. Deshmukh, J. Son, W. Bae, L. Liu, J. Wang, X. Liu, L. Gao, T. Wu, J. Xiao, F. Wang, B. Yin, Y. Wang, G. Danala, L. He, Y. H. Choi, Y. C. Lee, S.-H. Jung, Z. Li, X. Sui, J. Wu, X. Li, T. Zhou, J. Toth, A. Baran, A. Kori, S. S. Chennamsetty, M. Safwan, V. Alex, X. Lyu, L. Cheng, Q. Chu, P. Li, X. Ji, S. Zhang, Y. Shen, L. Dai, O. Saha, R. Sathish, T. Melo, T. Ara\u00fajo, B. Harangi, B. Sheng, R. Fang, D. Sheet, A. Hajdu, Y. Zheng, A. M. Mendon\u00e7a, S. Zhang, A. Campilho, B. Zheng, D. Shen, L. Giancardo, G. Quellec, and F. M\u00e9riaudeau. IDRiD: Diabetic retinopathy-segmentation and grading challenge. Med. Image Anal.59:101561, 2020. https:\/\/doi.org\/10.1016\/j.media.2019.101561.","journal-title":"Med. Image Anal."},{"issue":"11","key":"4032_CR11","doi-asserted-by":"publisher","first-page":"3146","DOI":"10.1109\/TMI.2022.3177803","volume":"41","author":"A He","year":"2022","unstructured":"He, A., K. Wang, T. Li, B. Wang, H. Kang, and H. Fu. Progressive multiscale consistent network for multiclass fundus lesion segmentation. IEEE Trans. Med. Imaging. 41(11):3146\u20133157, 2022. https:\/\/doi.org\/10.1109\/TMI.2022.3177803.","journal-title":"IEEE Trans. Med. Imaging"},{"key":"4032_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109191","volume":"136","author":"Q Liu","year":"2023","unstructured":"Liu, Q., H. Liu, W. Ke, and Y. Liang. Automated lesion segmentation in fundus images with many-to-many reassembly of features. Pattern Recognit.136:109191, 2023. https:\/\/doi.org\/10.1016\/j.patcog.2022.109191.","journal-title":"Pattern Recognit."},{"issue":"25","key":"4032_CR13","doi-asserted-by":"publisher","first-page":"39327","DOI":"10.1007\/s11042-023-15045-1","volume":"82","author":"P Saranya","year":"2023","unstructured":"Saranya, P., R. Pranati, and S. S. Patro. Detection and classification of red lesions from retinal images for diabetic retinopathy detection using deep learning models. Multimed. Tools Appl. 82(25):39327\u201339347, 2023. https:\/\/doi.org\/10.1007\/s11042-023-15045-1.","journal-title":"Multimed. Tools Appl."},{"key":"4032_CR14","doi-asserted-by":"publisher","first-page":"130451","DOI":"10.1109\/ACCESS.2023.3333364","volume":"11","author":"M Yin","year":"2023","unstructured":"Yin, M., T. A. Soomro, F. A. Jandan, A. Fatihi, F. B. Ubaid, M. Irfan, A. J. Afifi, S. Rahman, S. Telenyk, and G. Nowakowski. Dual-branch U-Net architecture for retinal lesions segmentation on fundus image. IEEE Access. 11:130451\u2013130465, 2023. https:\/\/doi.org\/10.1109\/ACCESS.2023.3333364.","journal-title":"IEEE Access"},{"key":"4032_CR15","first-page":"234","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015, edited by N. Navab, J. Hornegger, W. M. Wells, and A. F. Frangi. Cham: Springer, 2015, pp. 234\u2013241."},{"key":"4032_CR16","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Y. Zhu, G. Papandreou, F. Schroff, and H. Adam. Encoder-decoder with atrous separable convolution for semantic image segmentation. Proc. Eur. Conf. Comput. Vision (ECCV), 2018.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"4032_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, and B. Guo. Swin transformer: Hierarchical vision transformer using shifted windows. Proc. IEEE\/CVF Int. Conf. Comput. Vis., pp. 10012\u201310022, 2021.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"4032_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104699","volume":"136","author":"H Zunair","year":"2021","unstructured":"Zunair, H., and A. B. Hamza. Sharp U-Net: depthwise convolutional network for biomedical image segmentation. Comput. Biol. Med.136:104699, 2021.","journal-title":"Comput. Biol. Med."},{"key":"4032_CR19","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.ins.2019.06.011","volume":"501","author":"T Li","year":"2019","unstructured":"Li, T., Y. Gao, K. Wang, S. Guo, H. Liu, and H. Kang. Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening. Inf. Sci. 501:511\u2013522, 2019. https:\/\/doi.org\/10.1016\/j.ins.2019.06.011.","journal-title":"Inf. Sci."},{"key":"4032_CR20","doi-asserted-by":"publisher","DOI":"10.3390\/data3030025","author":"P Porwal","year":"2018","unstructured":"Porwal, P., S. Pachade, R. Kamble, M. Kokare, G. Deshmukh, V. Sahasrabuddhe, and F. Meriaudeau. Indian diabetic retinopathy image dataset (IDRiD): a database for diabetic retinopathy screening research. Data. 2018. https:\/\/doi.org\/10.3390\/data3030025.","journal-title":"Data"},{"key":"4032_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108160","volume":"249","author":"R Romero-Ora\u00e1","year":"2024","unstructured":"Romero-Ora\u00e1, R., M. Herrero-Tudela, M. I. L\u00f3pez, R. Hornero, and M. Garc\u00eda. Attention-based deep learning framework for automatic fundus image processing to aid in diabetic retinopathy grading. Comput. Methods Programs Biomed.249:108160, 2024. https:\/\/doi.org\/10.1016\/j.cmpb.2024.108160.","journal-title":"Comput. Methods Programs Biomed."},{"key":"4032_CR22","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1007\/978-3-031-61625-9_10","volume-title":"9th European Medical and Biological Engineering Conference","author":"M Herrero-Tudela","year":"2024","unstructured":"Herrero-Tudela, M., R. Romero-Ora\u00e1, R. Hornero, G. C. Guti\u00e9rrez-Tobal, M. I. Lopez, and M. Garc\u00eda. An explainable deep-learning model to aid in the diagnosis of age related macular degeneration. In: 9th European Medical and Biological Engineering Conference, edited by T. Jarm, R. \u0160merc, and S. Mahni\u010d-Kalamiza. Cham: Springer, 2024, pp. 85\u201394."},{"key":"4032_CR23","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Y. Bengio, and A. Courville. Deep Learning. MIT Press, 2016."},{"key":"4032_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107328","volume":"102","author":"M Herrero-Tudela","year":"2025","unstructured":"Herrero-Tudela, M., R. Romero-Ora\u00e1, R. Hornero, G. C. Guti\u00e9rrez-Tobal, M. I. L\u00f3pez, and M. Garc\u00eda. An explainable deep-learning model reveals clinical clues in diabetic retinopathy through SHAP. Biomed. Signal Process. Control.102:107328, 2025. https:\/\/doi.org\/10.1016\/j.bspc.2024.107328.","journal-title":"Biomed. Signal Process. Control"},{"key":"4032_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120987","volume":"234","author":"Y Fu","year":"2023","unstructured":"Fu, Y., G. Zhang, X. Lu, H. Wu, and D. Zhang. RMCA U-net: Hard exudates segmentation for retinal fundus images. Exp. Syst. Appl.234:120987, 2023. https:\/\/doi.org\/10.1016\/j.eswa.2023.120987.","journal-title":"Exp. Syst. Appl."},{"key":"4032_CR26","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-11726-9_28","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","author":"A Myronenko","year":"2019","unstructured":"Myronenko, A. 3d MRI brain tumor segmentation using autoencoder regularization. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, edited by A. Crimi, S. Bakas, H. Kuijf, F. Keyvan, M. Reyes, and T. Walsum. Cham: Springer, 2019, pp. 311\u2013320."},{"key":"4032_CR27","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-031-09002-8_16","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Virtual Event, September 27, 2021, Revised Selected Papers, Part II","author":"HM Luu","year":"2021","unstructured":"Luu, H. M., and S. H. Park. Extending nn-UNet for brain tumor segmentation. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Virtual Event, September 27, 2021, Revised Selected Papers, Part II, Berlin: Springer, 2021, pp. 173\u2013186. https:\/\/doi.org\/10.1007\/978-3-031-09002-8_16."},{"key":"4032_CR28","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, S., M. Drozdzal, D. Vazquez, A. Romero, and Y. Bengio. The one hundred layers tiramisu: fully convolutional DenseNets for semantic segmentation. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops, 2017.","DOI":"10.1109\/CVPRW.2017.156"},{"issue":"5","key":"4032_CR29","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.11.5.054004","volume":"11","author":"V Loos","year":"2024","unstructured":"Loos, V., R. Pardasani, and N. Awasthi. Demystifying the effect of receptive field size in U-Net models for medical image segmentation. J. Med. Imaging.11(5):054004, 2024.","journal-title":"J. Med. Imaging"},{"key":"4032_CR30","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems. NIPS \u201923","author":"C Williams","year":"2023","unstructured":"Williams, C., F. Falck, G. Deligiannidis, C. Holmes, A. Doucet, and S. Syed. A unified framework for U-net design and analysis. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. NIPS \u201923,Red Hook, NY, USA: Curran Associates Inc., 2023."},{"issue":"5","key":"4032_CR31","doi-asserted-by":"publisher","first-page":"874","DOI":"10.3934\/mfc.2024040","volume":"8","author":"X-C Tai","year":"2025","unstructured":"Tai, X.-C., H. Liu, R. H. Chan, and L. Li. A mathematical explanation of UNet. Math. Found. Comput. 8(5):874\u2013889, 2025. https:\/\/doi.org\/10.3934\/mfc.2024040.","journal-title":"Math. Found. Comput."},{"key":"4032_CR32","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3054719","author":"S Vandenhende","year":"2021","unstructured":"Vandenhende, S., S. Georgoulis, W. Van Gansbeke, M. Proesmans, D. Dai, and L. Van Gool. Multi-task learning for dense prediction tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 2021. https:\/\/doi.org\/10.1109\/tpami.2021.3054719.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4032_CR33","unstructured":"Ruder, S. An overview of multi-task learning in deep neural networks, 2017. http:\/\/arxiv.org\/abs\/1706.05098."},{"key":"4032_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102035","volume":"71","author":"J Ma","year":"2021","unstructured":"Ma, J., J. Chen, M. Ng, R. Huang, Y. Li, C. Li, X. Yang, and A. L. Martel. Loss odyssey in medical image segmentation. Med. Image Anal.71:102035, 2021. https:\/\/doi.org\/10.1016\/j.media.2021.102035.","journal-title":"Med. Image Anal."},{"issue":"2","key":"4032_CR35","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/S1076-6332(03)00671-8","volume":"11","author":"KH Zou","year":"2004","unstructured":"Zou, K. H., S. K. Warfield, A. Bharatha, C. M. C. Tempany, M. R. Kaus, S. J. Haker, W. M. Wells 3rd., F. A. Jolesz, and R. Kikinis. Statistical validation of image segmentation quality based on a spatial overlap index. Acad. Radiol. 11(2):178\u2013189, 2004.","journal-title":"Acad. Radiol."},{"key":"4032_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075","author":"H Rezatofighi","year":"2019","unstructured":"Rezatofighi, H., N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese. Generalized intersection over union: a metric and a loss for bounding box regression. CVPR. 2019. https:\/\/doi.org\/10.1109\/CVPR.2019.00075.","journal-title":"CVPR"},{"key":"4032_CR37","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-642-40994-3_29","volume-title":"Proceedings of the 2013th European Conference on Machine Learning and Knowledge Discovery in Databases. ECMLPKDD\u201913","author":"K Boyd","year":"2013","unstructured":"Boyd, K., K. H. Eng, and C. D. Page. Area under the precision-recall curve: point estimates and confidence intervals. In: Proceedings of the 2013th European Conference on Machine Learning and Knowledge Discovery in Databases. ECMLPKDD\u201913, Berlin: Springer, 2013, pp. 451\u2013466. https:\/\/doi.org\/10.1007\/978-3-642-40994-3_29."},{"key":"4032_CR38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76917-0","volume-title":"Advanced Data Mining Techniques","author":"DL Olson","year":"2008","unstructured":"Olson, D. L., and D. Delen. Advanced Data Mining Techniques. Cham: Springer, 2008. https:\/\/doi.org\/10.1007\/978-3-540-76917-0."},{"key":"4032_CR39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.02483","author":"L Gao","year":"2023","unstructured":"Gao, L., C. Khamesra, U. Kumbhar, and A. Aglawe. Multi-Task Self-Supervised Learning for Image Segmentation Task. Comput. Sci. 2023. https:\/\/doi.org\/10.48550\/arXiv.2302.02483.","journal-title":"Comput. Sci."},{"issue":"3","key":"4032_CR40","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1109\/JBHI.2021.3108169","volume":"26","author":"Q Liu","year":"2022","unstructured":"Liu, Q., H. Liu, Y. Zhao, and Y. Liang. Dual-branch network with dual-sampling modulated dice loss for hard exudate segmentation in color fundus images. IEEE J. Biomed. Health Inform. 26(3):1091\u20131102, 2022. https:\/\/doi.org\/10.1109\/JBHI.2021.3108169.","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"4032_CR41","doi-asserted-by":"publisher","unstructured":"Xie, S., and Z. Tu. Holistically-nested edge detection. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1395\u20131403, 2015. https:\/\/doi.org\/10.1109\/ICCV.2015.164.","DOI":"10.1109\/ICCV.2015.164"},{"key":"4032_CR42","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-030-58555-6_12","volume-title":"Computer Vision-ECCV 2020","author":"M Yin","year":"2020","unstructured":"Yin, M., Z. Yao, Y. Cao, X. Li, Z. Zhang, S. Lin, and H. Hu. Disentangled non-local neural networks. In: Computer Vision-ECCV 2020, edited by A. Vedaldi, H. Bischof, T. Brox, and J.-M. Frahm. Cham: Springer, 2020, pp. 191\u2013207."},{"key":"4032_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, H., J. Shi, X. Qi, X. Wang, and J. Jia. Pyramid scene parsing network. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017.","DOI":"10.1109\/CVPR.2017.660"},{"key":"4032_CR44","doi-asserted-by":"crossref","unstructured":"Hou, Q., L. Zhang, M.-M. Cheng, and J. Feng. Strip pooling: Rethinking spatial pooling for scene parsing. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020.","DOI":"10.1109\/CVPR42600.2020.00406"},{"issue":"10","key":"4032_CR45","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2021","unstructured":"Wang, J., K. Sun, T. Cheng, B. Jiang, C. Deng, Y. Zhao, D. Liu, Y. Mu, M. Tan, X. Wang, W. Liu, and B. Xiao. Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10):3349\u20133364, 2021. https:\/\/doi.org\/10.1109\/TPAMI.2020.2983686.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4032_CR46","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., Z. Tian, Y. Wang, B. Zhang, H. Ren, X. Wei, H. Xia, and C. Shen. Twins: Revisiting the design of spatial attention in vision transformers. Adv. Neural. Inf. Process. Syst. 34:9355\u20139366, 2021.","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"4032_CR47","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1109\/TMI.2004.825627","volume":"23","author":"J Staal","year":"2004","unstructured":"Staal, J., M. D. Abr\u00e0moff, M. Niemeijer, M. A. Viergever, and B. Van Ginneken. Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging. 23(4):501\u2013509, 2004.","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"3","key":"4032_CR48","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1109\/42.845178","volume":"19","author":"AD Hoover","year":"2000","unstructured":"Hoover, A. D., V. Kouznetsova, and M. Goldbaum. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Med. Imaging. 19(3):203\u2013210, 2000.","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Annals of Biomedical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10439-026-04032-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10439-026-04032-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10439-026-04032-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T13:42:47Z","timestamp":1787838167000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10439-026-04032-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,12]]},"references-count":48,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["4032"],"URL":"https:\/\/doi.org\/10.1007\/s10439-026-04032-w","relation":{},"ISSN":["0090-6964","1573-9686"],"issn-type":[{"value":"0090-6964","type":"print"},{"value":"1573-9686","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,12]]},"assertion":[{"value":"24 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no conflict of interest to declare.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}