{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T18:58:17Z","timestamp":1782932297297,"version":"3.54.5"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Medical image segmentation is critical for accurate diagnosis, treatment planning, and surgical navigation. In recent years, large multitask segmentation models have often struggled due to the limited size of datasets and significant variability in target structures, image resolutions, and annotation standards. These variations can introduce task competitions during multitask model training, which hinder effective feature learning. To address these challenges, we propose PatchMoE, a unified framework designed to compensate for resolution discrepancies across datasets and feature conflicts arising in mixed-dataset training. PatchMoE is the first to introduce patch-based contrastive learning into medical image segmentation tasks, which divides images into equal-sized patches represented in 3D coordinate space. This novel approach ensures that mixed datasets with varying resolutions can be trained in a unified manner, preserving spatial relationships and enhancing contextual understanding. PatchMoE also incorporates a mixture of experts (MoE) mechanism into the decoder, which dynamically selects dataset-specific expert combinations. This design mitigates parameter conflicts through network sparsification, effectively resolving optimization conflicts in multitask datasets. The effectiveness of the proposed method was demonstrated in four independent segmentation tasks: retinal vessel (DRIVE), near-infrared blurred vessel (HVNIR), abdominal multiorgan (Synapse), and polyp segmentation (Kvasir-SEG). We compared performance using multiple metrics, including Dice score, Intersection over Union (IoU), and Hausdorff distance (HD). Compared with the state-of-the-art (SOTA) GCASCADE model, PatchMoE achieved an improvement of 3.04% in the mean Dice score across all tasks. The proposed method also achieved an average Dice score improvement of 0.88% compared to four independently trained SOTA models for each individual task. In summary, PatchMoE combines patch-based contrastive learning with dataset-informed expert gating to provide promising solutions for dataset conflicts in large transformer-based medical segmentation models.<\/jats:p>","DOI":"10.1007\/s00521-025-11234-1","type":"journal-article","created":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T17:45:49Z","timestamp":1746726349000},"page":"14189-14216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Conducting patch contrastive learning with mixture of experts on mixed datasets for medical image segmentation"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4542-3202","authenticated-orcid":false,"given":"Jiazhe","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osamu","family":"Yoshie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuya","family":"Ieiri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,8]]},"reference":[{"key":"11234_CR1","doi-asserted-by":"publisher","first-page":"154860","DOI":"10.1155\/2013\/154860","volume":"1","author":"A Budai","year":"2013","unstructured":"Budai A, Bock R, Maier A et al (2013) Robust vessel segmentation in fundus images. Int J Biomed Imaging 1:154860. https:\/\/doi.org\/10.1155\/2013\/154860","journal-title":"Int J Biomed Imaging"},{"key":"11234_CR2","doi-asserted-by":"publisher","unstructured":"Cao H, Wang Y, Chen J et\u00a0al (2023) Swin-unet: Unet-like pure transformer for medical image segmentation. In: Karlinsky L, Michaeli T, Nishino K (eds) Computer Vision \u2013 ECCV 2022 Workshops. Springer Nature Switzerland, Cham, pp 205\u2013218, https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"11234_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.bspc.2018.06.007","volume":"46","author":"A Carballal","year":"2018","unstructured":"Carballal A, Novoa FJ, Fernandez-Lozano C et al (2018) Automatic multiscale vascular image segmentation algorithm for coronary angiography. Biomed Signal Process Control 46:1\u20139. https:\/\/doi.org\/10.1016\/j.bspc.2018.06.007","journal-title":"Biomed Signal Process Control"},{"key":"11234_CR4","doi-asserted-by":"publisher","unstructured":"Chen J, Lu Y, Yu Q et\u00a0al (2021) Transunet: Transformers make strong encoders for medical image segmentation. https:\/\/doi.org\/10.48550\/arXiv.2102.04306, preprint at https:\/\/arxiv.org\/abs\/2102.04306","DOI":"10.48550\/arXiv.2102.04306"},{"key":"11234_CR5","doi-asserted-by":"publisher","unstructured":"Cheng B, Schwing A, Kirillov A (2021) Per-pixel classification is not all you need for semantic segmentation. In: Ranzato M, Beygelzimer A, Dauphin Y, et\u00a0al (eds) Advances in Neural Information Processing Systems, vol\u00a034. Curran Associates, Inc., Virtual, pp 17864\u201317875, https:\/\/doi.org\/10.5555\/3540261.3541628","DOI":"10.5555\/3540261.3541628"},{"key":"11234_CR6","doi-asserted-by":"publisher","unstructured":"Cheng B, Misra I, Schwing AG et\u00a0al (2022) Masked-attention mask transformer for universal image segmentation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE\/CVF, New Orleans, LA, USA, pp 1280\u20131289, https:\/\/doi.org\/10.1109\/CVPR52688.2022.00135","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"11234_CR7","doi-asserted-by":"publisher","unstructured":"Cheng D, Qin Z, Jiang Z et\u00a0al (2023) Sam on medical images: A comprehensive study on three prompt modes. https:\/\/doi.org\/10.48550\/arXiv.2305.00035, preprint at https:\/\/arxiv.org\/abs\/2305.00035","DOI":"10.48550\/arXiv.2305.00035"},{"key":"11234_CR8","unstructured":"Chung MK, Bryan N (2015) Multi-organ segmentation dataset. Accessed: 2024-01-17 at https:\/\/www.synapse.org\/#!Synapse:syn3193805\/wiki\/217789"},{"issue":"1","key":"11234_CR9","doi-asserted-by":"publisher","first-page":"9380","DOI":"10.1038\/s41598-024-59813-x","volume":"14","author":"BK Das","year":"2024","unstructured":"Das BK, Zhao G, Islam S et al (2024) Co-ordinate-based positional embedding that captures resolution to enhance transformer\u2019s performance in medical image analysis. Sci Rep 14(1):9380. https:\/\/doi.org\/10.1038\/s41598-024-59813-x","journal-title":"Sci Rep"},{"key":"11234_CR10","doi-asserted-by":"publisher","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A et\u00a0al (2021) An image is worth 16x16 words: Transformers for image recognition at scale. https:\/\/doi.org\/10.48550\/arXiv.2010.11929, preprint at https:\/\/arxiv.org\/abs\/2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"11234_CR11","doi-asserted-by":"publisher","DOI":"10.2352\/J.ImagingSci.Technol.2020.64.2.020508","author":"G Du","year":"2020","unstructured":"Du G, Cao X, Liang J et al (2020) Medical image segmentation based on u-net: A review. J Imaging Sci Technol. https:\/\/doi.org\/10.2352\/J.ImagingSci.Technol.2020.64.2.020508","journal-title":"J Imaging Sci Technol"},{"issue":"8","key":"11234_CR12","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T (2006) An introduction to roc analysis. Pattern Recognit Lett 27(8):861\u2013874. https:\/\/doi.org\/10.1016\/j.patrec.2005.10.010","journal-title":"Pattern Recognit Lett"},{"issue":"9","key":"11234_CR13","doi-asserted-by":"publisher","first-page":"2538","DOI":"10.1109\/TBME.2012.2205687","volume":"59","author":"MM Fraz","year":"2012","unstructured":"Fraz MM, Remagnino P, Hoppe A et al (2012) An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Trans Biomed Eng 59(9):2538\u20132548. https:\/\/doi.org\/10.1109\/TBME.2012.2205687","journal-title":"IEEE Trans Biomed Eng"},{"issue":"1","key":"11234_CR14","doi-asserted-by":"publisher","first-page":"6174","DOI":"10.1038\/s41598-022-09675-y","volume":"12","author":"A Galdran","year":"2022","unstructured":"Galdran A, Anjos A, Dolz J et al (2022) State-of-the-art retinal vessel segmentation with minimalistic models. Sci Rep 12(1):6174. https:\/\/doi.org\/10.1038\/s41598-022-09675-y","journal-title":"Sci Rep"},{"key":"11234_CR15","doi-asserted-by":"publisher","unstructured":"Ge C, Chen J, Xie E et\u00a0al (2023) Metabev: Solving sensor failures for 3d detection and map segmentation. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE\/CVF, Paris, France, pp 8687\u20138697, https:\/\/doi.org\/10.1109\/ICCV51070.2023.00801","DOI":"10.1109\/ICCV51070.2023.00801"},{"key":"11234_CR16","doi-asserted-by":"publisher","first-page":"102685","DOI":"10.1016\/j.media.2022.102685","volume":"83","author":"S Graham","year":"2023","unstructured":"Graham S, Vu QD, Jahanifar M et al (2023) One model is all you need: Multi-task learning enables simultaneous histology image segmentation and classification. Med Image Anal 83:102685. https:\/\/doi.org\/10.1016\/j.media.2022.102685","journal-title":"Med Image Anal"},{"key":"11234_CR17","doi-asserted-by":"publisher","unstructured":"Guo C, Szemenyei M, Yi Y et\u00a0al (2021) Sa-unet: Spatial attention u-net for retinal vessel segmentation. In: 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, Milan, Italy, pp 1236\u20131242, https:\/\/doi.org\/10.1109\/ICPR48806.2021.9413346","DOI":"10.1109\/ICPR48806.2021.9413346"},{"key":"11234_CR18","doi-asserted-by":"publisher","unstructured":"Han K, Xiao A, Wu E et\u00a0al (2021) Transformer in transformer. In: Ranzato M, Beygelzimer A, Dauphin Y, et\u00a0al (eds) Advances in Neural Information Processing Systems, vol\u00a034. Curran Associates, Inc., Virtual, pp 15908\u201315919, https:\/\/doi.org\/10.48550\/arXiv.2103.00112","DOI":"10.48550\/arXiv.2103.00112"},{"key":"11234_CR19","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S et\u00a0al (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Las Vegas, NV, USA, pp 770\u2013778, https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"11234_CR20","doi-asserted-by":"publisher","unstructured":"He K, Chen X, Xie S et\u00a0al (2022) Masked autoencoders are scalable vision learners. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE\/CVF, New Orleans, LA, USA, pp 15979\u201315988, https:\/\/doi.org\/10.1109\/CVPR52688.2022.01553","DOI":"10.1109\/CVPR52688.2022.01553"},{"issue":"3","key":"11234_CR21","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1109\/42.845178","volume":"19","author":"A Hoover","year":"2000","unstructured":"Hoover A, Kouznetsova V, Goldbaum M (2000) Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans Med Imaging 19(3):203\u2013210. https:\/\/doi.org\/10.1109\/42.845178","journal-title":"IEEE Trans Med Imaging"},{"key":"11234_CR22","doi-asserted-by":"publisher","first-page":"103061","DOI":"10.1016\/j.media.2023.103061","volume":"92","author":"Y Huang","year":"2024","unstructured":"Huang Y, Yang X, Liu L et al (2024) Segment anything model for medical images? Med Image Anal 92:103061. https:\/\/doi.org\/10.1016\/j.media.2023.103061","journal-title":"Med Image Anal"},{"issue":"9","key":"11234_CR23","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1109\/34.232073","volume":"15","author":"D Huttenlocher","year":"1993","unstructured":"Huttenlocher D, Klanderman G, Rucklidge W (1993) Comparing images using the hausdorff distance. IEEE Trans Pattern Anal Mach Intell 15(9):850\u2013863. https:\/\/doi.org\/10.1109\/34.232073","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"11234_CR24","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1007\/s00158-020-02581-9","volume":"62","author":"H Jafaryeganeh","year":"2020","unstructured":"Jafaryeganeh H, Ventura M, Guedes Soares C (2020) Effect of normalization techniques in multi-criteria decision making methods for the design of ship internal layout from a pareto optimal set. Struct Multidiscip Optimization 62(4):1849\u20131863. https:\/\/doi.org\/10.1007\/s00158-020-02581-9","journal-title":"Struct Multidiscip Optimization"},{"issue":"1","key":"11234_CR25","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1038\/s42003-023-04848-5","volume":"6","author":"Y Jain","year":"2023","unstructured":"Jain Y, Godwin LL, Ju Y et al (2023) Segmentation of human functional tissue units in support of a human reference atlas. Commun Biol 6(1):717. https:\/\/doi.org\/10.1038\/s42003-023-04848-5","journal-title":"Commun Biol"},{"key":"11234_CR26","doi-asserted-by":"publisher","unstructured":"Jha D, Smedsrud PH, Riegler MA, et\u00a0al (2020) Kvasir-seg: A segmented polyp dataset. In: Ro YM, Cheng WH, Kim J, et\u00a0al (eds) MultiMedia Modeling. Springer International Publishing, Cham, pp 451\u2013462, https:\/\/doi.org\/10.1007\/978-3-030-37734-2_37","DOI":"10.1007\/978-3-030-37734-2_37"},{"key":"11234_CR27","doi-asserted-by":"publisher","unstructured":"Jha D, Tomar NK, Sharma V, et\u00a0al (2024) Transnetr: Transformer-based residual network for polyp segmentation with multi-center out-of-distribution testing. In: Oguz I, Noble J, Li X, et\u00a0al (eds) Medical Imaging with Deep Learning, vol 227. PMLR, New York, NY, USA, pp 1372\u20131384, https:\/\/doi.org\/10.48550\/arXiv.2303.07428","DOI":"10.48550\/arXiv.2303.07428"},{"key":"11234_CR28","doi-asserted-by":"publisher","unstructured":"Jung C, Kwon G, Ye JC (2022) Exploring patch-wise semantic relation for contrastive learning in image-to-image translation tasks. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE\/CVF, New Orleans, LA, USA, pp 18239\u201318248, https:\/\/doi.org\/10.1109\/CVPR52688.2022.01772","DOI":"10.1109\/CVPR52688.2022.01772"},{"key":"11234_CR29","doi-asserted-by":"publisher","unstructured":"Kamran SA, Hossain KF, Tavakkoli A, et\u00a0al (2021) Rv-gan: Segmenting retinal vascular structure in fundus photographs using a novel multi-scale generative adversarial network. In: de\u00a0Bruijne M, Cattin PC, Cotin S, et\u00a0al (eds) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021. Springer International Publishing, Cham, pp 34\u201344, https:\/\/doi.org\/10.1007\/978-3-030-87237-3_4","DOI":"10.1007\/978-3-030-87237-3_4"},{"key":"11234_CR30","doi-asserted-by":"publisher","unstructured":"Kirillov A, Mintun E, Ravi N, et\u00a0al (2023) Segment anything. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE\/CVF, Paris, France, pp 3992\u20134003, https:\/\/doi.org\/10.1109\/ICCV51070.2023.00371","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"8","key":"11234_CR31","doi-asserted-by":"publisher","first-page":"1975","DOI":"10.3390\/diagnostics12081975","volume":"12","author":"SG Kobat","year":"2022","unstructured":"Kobat SG, Baygin N, Yusufoglu E et al (2022) Automated diabetic retinopathy detection using horizontal and vertical patch division-based pre-trained densenet with digital fundus images. Diagnostics 12(8):1975. https:\/\/doi.org\/10.3390\/diagnostics12081975","journal-title":"Diagnostics"},{"issue":"2","key":"11234_CR32","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"TY Lin","year":"2020","unstructured":"Lin TY, Goyal P, Girshick R et al (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42(2):318\u2013327. https:\/\/doi.org\/10.1109\/TPAMI.2018.2858826","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"11234_CR33","doi-asserted-by":"publisher","first-page":"4623","DOI":"10.1109\/JBHI.2022.3188710","volume":"26","author":"W Liu","year":"2022","unstructured":"Liu W, Yang H, Tian T et al (2022) Full-resolution network and dual-threshold iteration for retinal vessel and coronary angiograph segmentation. IEEE J Biomed Health Inform 26(9):4623\u20134634. https:\/\/doi.org\/10.1109\/JBHI.2022.3188710","journal-title":"IEEE J Biomed Health Inform"},{"issue":"3","key":"11234_CR34","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.3390\/su13031224","volume":"13","author":"X Liu","year":"2021","unstructured":"Liu X, Song L, Liu S et al (2021) A review of deep-learning-based medical image segmentation methods. Sustainability 13(3):1224. https:\/\/doi.org\/10.3390\/su13031224","journal-title":"Sustainability"},{"key":"11234_CR35","doi-asserted-by":"publisher","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, New Orleans, LA, USA, https:\/\/doi.org\/10.48550\/arXiv.1711.05101","DOI":"10.48550\/arXiv.1711.05101"},{"key":"11234_CR36","doi-asserted-by":"publisher","unstructured":"Ma P, Du T, Matusik W (2020) Efficient continuous pareto exploration in multi-task learning. In: III HD, Singh A (eds) Proceedings of the 37th International Conference on Machine Learning, vol 119. PMLR, Virtual, pp 6522\u20136531, https:\/\/doi.org\/10.48550\/arXiv.2006.16434","DOI":"10.48550\/arXiv.2006.16434"},{"key":"11234_CR37","doi-asserted-by":"publisher","unstructured":"Ma Y, Xu G, Sun X, et\u00a0al (2022) X-clip: End-to-end multi-grained contrastive learning for video-text retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia, vol\u00a010. Association for Computing Machinery, New York, NY, USA, pp 638\u2013647, https:\/\/doi.org\/10.1145\/3503161.3547910","DOI":"10.1145\/3503161.3547910"},{"key":"11234_CR38","doi-asserted-by":"publisher","first-page":"102918","DOI":"10.1016\/j.media.2023.102918","volume":"89","author":"MA Mazurowski","year":"2023","unstructured":"Mazurowski MA, Dong H, Gu H et al (2023) Segment anything model for medical image analysis: an experimental study. Med Image Anal 89:102918. https:\/\/doi.org\/10.1016\/j.media.2023.102918","journal-title":"Med Image Anal"},{"key":"11234_CR39","doi-asserted-by":"publisher","unstructured":"Oktay O, Schlemper J, Folgoc LL et\u00a0al (2018) Attention u-net: Learning where to look for the pancreas. https:\/\/doi.org\/10.48550\/arXiv.1804.03999, preprint at https:\/\/arxiv.org\/abs\/1804.03999","DOI":"10.48550\/arXiv.1804.03999"},{"key":"11234_CR40","doi-asserted-by":"publisher","unstructured":"Ou Y, Yuan Y, Huang X et\u00a0al (2022) Patcher: Patch transformers with mixture of experts for precise medical image segmentation. In: Wang L, Dou Q, Fletcher PT, et\u00a0al (eds) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022. Springer Nature Switzerland, Cham, pp 475\u2013484, https:\/\/doi.org\/10.1007\/978-3-031-16443-9_46","DOI":"10.1007\/978-3-031-16443-9_46"},{"key":"11234_CR41","doi-asserted-by":"publisher","unstructured":"Park T, Efros AA, Zhang R et\u00a0al (2020) Contrastive learning for unpaired image-to-image translation. In: Vedaldi A, Bischof H, Brox T, et\u00a0al (eds) Computer Vision \u2013 ECCV 2020. Springer International Publishing, Cham, pp 319\u2013345, https:\/\/doi.org\/10.1007\/978-3-030-58545-7_19","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"11234_CR42","doi-asserted-by":"publisher","unstructured":"Radford A, Kim JW, Hallacy C et\u00a0al (2021) Learning transferable visual models from natural language supervision. https:\/\/doi.org\/10.48550\/arXiv.2103.00020, preprint at https:\/\/arxiv.org\/abs\/2103.00020","DOI":"10.48550\/arXiv.2103.00020"},{"key":"11234_CR43","doi-asserted-by":"publisher","unstructured":"Rahman MM, Marculescu R (2023) Medical image segmentation via cascaded attention decoding. In: 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE\/CVF, Waikoloa, HI, USA, pp 6211\u20136220, https:\/\/doi.org\/10.1109\/WACV56688.2023.00616","DOI":"10.1109\/WACV56688.2023.00616"},{"key":"11234_CR44","doi-asserted-by":"publisher","unstructured":"Rahman MM, Marculescu R (2024) G-cascade: Efficient cascaded graph convolutional decoding for 2d medical image segmentation. In: 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE\/CVF, Waikoloa, HI, USA, pp 7713\u20137722, https:\/\/doi.org\/10.1109\/WACV57701.2024.00755","DOI":"10.1109\/WACV57701.2024.00755"},{"key":"11234_CR45","doi-asserted-by":"publisher","unstructured":"Riquelme C, Puigcerver J, Mustafa B, et\u00a0al (2021) Scaling vision with sparse mixture of experts. In: Ranzato M, Beygelzimer A, Dauphin Y, et\u00a0al (eds) Advances in Neural Information Processing Systems, vol\u00a034. Curran Associates, Inc., Virtual, pp 8583\u20138595, https:\/\/doi.org\/10.48550\/arXiv.2106.05974","DOI":"10.48550\/arXiv.2106.05974"},{"key":"11234_CR46","doi-asserted-by":"publisher","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, et\u00a0al (eds) Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. Springer International Publishing, Cham, pp 234\u2013241, https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11234_CR47","doi-asserted-by":"publisher","unstructured":"Sabottke CF, Spieler BM (2020) The effect of image resolution on deep learning in radiography. Radiology: Artificial Intelligence 2(1):e190015. https:\/\/doi.org\/10.1148\/ryai.2019190015","DOI":"10.1148\/ryai.2019190015"},{"key":"11234_CR48","doi-asserted-by":"publisher","unstructured":"Sener O, Koltun V (2018) Multi-task learning as multi-objective optimization. In: Bengio S, Wallach H, Larochelle H et\u00a0al (eds) Advances in Neural Information Processing Systems, vol\u00a031. Curran Associates, Inc., Montreal, Canada, https:\/\/doi.org\/10.48550\/arXiv.1810.04650","DOI":"10.48550\/arXiv.1810.04650"},{"key":"11234_CR49","doi-asserted-by":"publisher","first-page":"16621","DOI":"10.1109\/ACCESS.2023.3244197","volume":"11","author":"T Shen","year":"2023","unstructured":"Shen T, Xu H (2023) Medical image segmentation based on transformer and hardnet structures. IEEE Access 11:16621\u201316630. https:\/\/doi.org\/10.1109\/ACCESS.2023.3244197","journal-title":"IEEE Access"},{"issue":"4","key":"11234_CR50","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1109\/TMI.2004.825627","volume":"23","author":"J Staal","year":"2004","unstructured":"Staal J, Abramoff M, Niemeijer M et al (2004) Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 23(4):501\u2013509. https:\/\/doi.org\/10.1109\/TMI.2004.825627","journal-title":"IEEE Trans Med Imaging"},{"key":"11234_CR51","doi-asserted-by":"publisher","unstructured":"Tancik M, Srinivasan P, Mildenhall B et\u00a0al (2020) Fourier features let networks learn high frequency functions in low dimensional domains. In: Larochelle H, Ranzato M, Hadsell R, et\u00a0al (eds) Advances in Neural Information Processing Systems, vol\u00a033. Curran Associates, Inc., Virtual, pp 7537\u20137547, https:\/\/doi.org\/10.48550\/arXiv.2006.10739","DOI":"10.48550\/arXiv.2006.10739"},{"issue":"8","key":"11234_CR52","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu AJ, Ting DSJ, Elangovan K et al (2023) Large language models in medicine. Nature Med 29(8):1930\u20131940. https:\/\/doi.org\/10.1038\/s41591-023-02448-8","journal-title":"Nature Med"},{"key":"11234_CR53","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N et\u00a0al (2023) Attention is all you need. https:\/\/doi.org\/10.48550\/arXiv.1706.03762, preprint at https:\/\/arxiv.org\/abs\/1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"11234_CR54","doi-asserted-by":"publisher","unstructured":"Wang J, Huang Q, Tang F et\u00a0al (2022a) Stepwise feature fusion: Local guides global. In: Wang L, Dou Q, Fletcher PT, et\u00a0al (eds) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022. Springer Nature Switzerland, Cham, pp 110\u2013120, https:\/\/doi.org\/10.1007\/978-3-031-16437-8_11","DOI":"10.1007\/978-3-031-16437-8_11"},{"key":"11234_CR55","doi-asserted-by":"publisher","unstructured":"Wang J, Osamu Y, Shimizu K (2022b) Trc-unet: Transformer connections for near-infrared blurred image segmentation. In: 2022 26th International Conference on Pattern Recognition (ICPR). IEEE, Montreal, QC, Canada, pp 4211\u20134218, https:\/\/doi.org\/10.1109\/ICPR56361.2022.9956727","DOI":"10.1109\/ICPR56361.2022.9956727"},{"issue":"11","key":"11234_CR56","doi-asserted-by":"publisher","first-page":"1828","DOI":"10.1002\/tee.24146","volume":"19","author":"J Wang","year":"2024","unstructured":"Wang J, Shimizu K, Yoshie O (2024) Transformer connections: Improving segmentation in blurred near-infrared blood vessel image in different depth. IEEJ Trans Electric Electron Eng 19(11):1828\u20131841. https:\/\/doi.org\/10.1002\/tee.24146","journal-title":"IEEJ Trans Electric Electron Eng"},{"key":"11234_CR57","doi-asserted-by":"publisher","unstructured":"Wu J, Ji W, Liu Y et\u00a0al (2023) Medical sam adapter: Adapting segment anything model for medical image segmentation. https:\/\/doi.org\/10.48550\/arXiv.2304.12620, preprint at https:\/\/arxiv.org\/abs\/2304.12620","DOI":"10.48550\/arXiv.2304.12620"},{"key":"11234_CR58","doi-asserted-by":"publisher","unstructured":"Xie CW, Sun S, Xiong X et\u00a0al (2023) Ra-clip: Retrieval augmented contrastive language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE\/CVF, Vancouver, BC, Canada, pp 19265\u201319274, https:\/\/doi.org\/10.1109\/CVPR52729.2023.01846","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"11234_CR59","doi-asserted-by":"publisher","first-page":"5984","DOI":"10.1109\/TIP.2021.3089942","volume":"30","author":"CB Zhang","year":"2021","unstructured":"Zhang CB, Jiang PT, Hou Q et al (2021) Delving deep into label smoothing. IEEE Trans Image Process 30:5984\u20135996. https:\/\/doi.org\/10.1109\/TIP.2021.3089942","journal-title":"IEEE Trans Image Process"},{"key":"11234_CR60","doi-asserted-by":"publisher","unstructured":"Zhao R, Qian B, Zhang X et\u00a0al (2020) Rethinking dice loss for medical image segmentation. In: 2020 IEEE International Conference on Data Mining (ICDM). IEEE, Sorrento, Italy, pp 851\u2013860, https:\/\/doi.org\/10.1109\/ICDM50108.2020.00094","DOI":"10.1109\/ICDM50108.2020.00094"},{"key":"11234_CR61","doi-asserted-by":"publisher","unstructured":"Zhao WX, Zhou K, Li J et\u00a0al (2024) A survey of large language models. https:\/\/doi.org\/10.48550\/arXiv.2303.18223, preprint at https:\/\/arxiv.org\/abs\/2303.18223","DOI":"10.48550\/arXiv.2303.18223"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11234-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11234-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11234-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T08:28:46Z","timestamp":1751012926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11234-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":61,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["11234"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11234-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"23 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 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":"The authors of this study declare that they did not receive any support or funding from any organization for the submitted work. They also declare that they have no financial interests that could have influenced the outcome of this study. Additionally, the authors declare that they have no conflict of interest that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}