{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:05:06Z","timestamp":1757621106169,"version":"3.44.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031966279"},{"type":"electronic","value":"9783031966286"}],"license":[{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-031-96628-6_1","type":"book-chapter","created":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T07:40:51Z","timestamp":1754120451000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SpectMamba: Integrating Frequency and\u00a0State Space Models for\u00a0Enhanced Medical Image Detection"],"prefix":"10.1007","author":[{"given":"Yao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liuzhi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"issue":"1","key":"1_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2017.117","volume":"4","author":"S Bakas","year":"2017","unstructured":"Bakas, S., et al.: Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci. Data 4(1), 1\u201313 (2017)","journal-title":"Sci. Data"},{"key":"1_CR2","unstructured":"Bakas, S., et\u00a0al.: Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the brats challenge. arXiv preprint arXiv:1811.02629 (2018)"},{"key":"1_CR3","volume-title":"The Fast Fourier Transform and Its Applications","author":"EO Brigham","year":"1988","unstructured":"Brigham, E.O.: The Fast Fourier Transform and Its Applications. Prentice-Hall Inc., Hoboken (1988)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Y., et al.: Remote sensing image segmentation using vision mamba and multi-scale multi-frequency feature fusion. arXiv preprint arXiv:2410.05624 (2024)","DOI":"10.3390\/rs17081390"},{"key":"1_CR6","doi-asserted-by":"publisher","first-page":"4609","DOI":"10.1109\/TIP.2022.3186532","volume":"31","author":"J Chen","year":"2022","unstructured":"Chen, J., Yu, L., Wang, W.: Hilbert space filling curve based scan-order for point cloud attribute compression. IEEE Trans. Image Process. 31, 4609\u20134621 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Drop an octave: reducing spatial redundancy in convolutional neural networks with octave convolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3435\u20133444 (2019)","DOI":"10.1109\/ICCV.2019.00353"},{"key":"1_CR8","unstructured":"Dao, T., Gu, A.: Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality. arXiv preprint arXiv:2405.21060 (2024)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Diwan, T., Anirudh, G., Tembhurne, J.V.: Object detection using YOLO: challenges, architectural successors, datasets and applications. Multimedia Tools Appl. 82(6), 9243\u20139275 (2023)","DOI":"10.1007\/s11042-022-13644-y"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Dong, W., et al.: Fusion-mamba for cross-modality object detection. arXiv preprint arXiv:2404.09146 (2024)","DOI":"10.1109\/TMM.2025.3599020"},{"key":"1_CR11","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Gabruseva, T., Poplavskiy, D., Kalinin, A.: Deep learning for automatic pneumonia detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 350\u2013351 (2020)","DOI":"10.1109\/CVPRW50498.2020.00183"},{"key":"1_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/978-3-030-87240-3_31","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"A Galdran","year":"2021","unstructured":"Galdran, A., Carneiro, G., Gonz\u00e1lez Ballester, M.A.: Balanced-mixup for highly imbalanced medical image classification. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 323\u2013333. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_31"},{"key":"1_CR14","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"1_CR15","unstructured":"Gu, A., Dao, T., Ermon, S., Rudra, A., R\u00e9, C.: Hippo: recurrent memory with optimal polynomial projections. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1474\u20131487 (2020)"},{"key":"1_CR16","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)"},{"key":"1_CR17","unstructured":"Gu, A., et al.: Combining recurrent, convolutional, and continuous-time models with linear state space layers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 572\u2013585 (2021)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"He, C., Li, R., Li, S., Zhang, L.: Voxel set transformer: a set-to-set approach to 3D object detection from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8417\u20138427 (2022)","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Hu, V.T., et al.: Zigma: a dit-style zigzag mamba diffusion model. In: European Conference on Computer Vision, pp. 148\u2013166. Springer, Cham (2025)","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Lee, M.: Gelu activation function in deep learning: a comprehensive mathematical analysis and performance. arXiv preprint arXiv:2305.12073 (2023)","DOI":"10.1155\/2023\/4229924"},{"key":"1_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3360456","volume":"62","author":"J Li","year":"2024","unstructured":"Li, J., Tian, P., Song, R., Xu, H., Li, Y., Du, Q.: PCViT: a pyramid convolutional vision transformer detector for object detection in remote-sensing imagery. IEEE Trans. Geosci. Remote Sens. 62, 1\u201315 (2024). https:\/\/doi.org\/10.1109\/TGRS.2024.3360456","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: European Conference on Computer Vision, pp. 280\u2013296. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1_CR24","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388 (2017)","journal-title":"Med. Image Anal."},{"key":"1_CR25","unstructured":"Liu, Y., et al.: Vmamba: visual state space model (2024). https:\/\/arxiv.org\/abs\/2401.10166"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR27","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"1_CR28","unstructured":"Mehta, H., Gupta, A., Cutkosky, A., Neyshabur, B.: Long range language modeling via gated state spaces. arXiv preprint arXiv:2206.13947 (2022)"},{"issue":"10","key":"1_CR29","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","volume":"34","author":"BH Menze","year":"2014","unstructured":"Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993\u20132024 (2014)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1_CR30","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1023\/A:1025196714293","volume":"7","author":"MF Mokbel","year":"2003","unstructured":"Mokbel, M.F., Aref, W.G., Kamel, I.: Analysis of multi-dimensional space-filling curves. GeoInformatica 7, 179\u2013209 (2003)","journal-title":"GeoInformatica"},{"issue":"1","key":"1_CR31","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1038\/s41597-022-01328-z","volume":"9","author":"E Nagy","year":"2022","unstructured":"Nagy, E., Janisch, M., Hr\u017ei\u0107, F., Sorantin, E., Tschauner, S.: A pediatric wrist trauma X-ray dataset (grazpedwri-dx) for machine learning. Sci. Data 9(1), 222 (2022)","journal-title":"Sci. Data"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Orenstein, J.A.: Spatial query processing in an object-oriented database system. In: Proceedings of the 1986 ACM SIGMOD International Conference on Management of Data, pp. 326\u2013336 (1986)","DOI":"10.1145\/16894.16886"},{"key":"1_CR33","unstructured":"Pan, Z., Cai, J., Zhuang, B.: Fast vision transformers with hilo attention. In: Advances in Neural Information Processing Systems, vol. 35, pp. 14541\u201314554 (2022)"},{"key":"1_CR34","unstructured":"Rahaman, N., et al.: On the spectral bias of neural networks. In: International Conference on Machine Learning, pp. 5301\u20135310. PMLR (2019)"},{"key":"1_CR35","unstructured":"Rao, Y., Zhao, W., Zhu, Z., Lu, J., Zhou, J.: Global filter networks for image classification. In: Advances in Neural Information Processing Systems, vol. 34, pp. 980\u2013993 (2021)"},{"key":"1_CR36","unstructured":"Ruan, J., Xiang, S.: VM-Unet: vision mamba Unet for medical image segmentation. arXiv preprint arXiv:2402.02491 (2024)"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Shi, D.: TransNext: robust foveal visual perception for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17773\u201317783 (2024)","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: RSN: range sparse net for efficient, accurate lidar 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5725\u20135734 (2021)","DOI":"10.1109\/CVPR46437.2021.00567"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Tang, Z., Jiang, C., Cui, Z., Shen, D.: HF-resdiff: high-frequency-guided residual diffusion for multi-dose PET reconstruction. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 372\u2013381. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72104-5_36"},{"key":"1_CR40","unstructured":"Tian, Z., Chu, X., Wang, X., Wei, X., Shen, C.: Fully convolutional one-stage 3D object detection on lidar range images. In: Advances in Neural Information Processing Systems, vol. 35, pp. 34899\u201334911 (2022)"},{"issue":"4","key":"1_CR41","first-page":"1922","volume":"44","author":"Z Tian","year":"2020","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: a simple and strong anchor-free object detector. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 1922\u20131933 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Selective structured state-spaces for long-form video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6387\u20136397 (2023)","DOI":"10.1109\/CVPR52729.2023.00618"},{"key":"1_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.107983","volume":"170","author":"K Wei","year":"2024","unstructured":"Wei, K., et al.: CT synthesis from MR images using frequency attention conditional generative adversarial network. Comput. Biol. Med. 170, 107983 (2024)","journal-title":"Comput. Biol. Med."},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Xu, Y., Shen, Y., Fernandez-Granda, C., Heacock, L., Geras, K.J.: Understanding differences in applying DETR to natural and medical images. arXiv preprint arXiv:2405.17677 (2024)","DOI":"10.59275\/j.melba.2025-g137"},{"key":"1_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107149","volume":"163","author":"Z Xu","year":"2023","unstructured":"Xu, Z., Zhang, X., Zhang, H., Liu, Y., Zhan, Y., Lukasiewicz, T.: EFPN: effective medical image detection using feature pyramid fusion enhancement. Comput. Biol. Med. 163, 107149 (2023)","journal-title":"Comput. Biol. Med."},{"key":"1_CR46","unstructured":"Yu, A., Lyu, D., Lim, S.H., Mahoney, M.W., Erichson, N.B.: Tuning frequency bias of state space models. arXiv preprint arXiv:2410.02035 (2024)"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 516\u2013520 (2016)","DOI":"10.1145\/2964284.2967274"},{"key":"1_CR48","unstructured":"Zhang, H., et al.: Dino: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al: Dense distinct query for end-to-end object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7329\u20137338 (2023)","DOI":"10.1109\/CVPR52729.2023.00708"},{"issue":"3","key":"1_CR50","doi-asserted-by":"publisher","first-page":"537","DOI":"10.3390\/electronics9030537","volume":"9","author":"L Zhao","year":"2020","unstructured":"Zhao, L., Li, S.: Object detection algorithm based on improved YOLOv3. Electronics 9(3), 537 (2020)","journal-title":"Electronics"},{"key":"1_CR51","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)"},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"Zhu, Q., et al.: Samba: semantic segmentation of remotely sensed images with state space model. Heliyon 10(19) (2024)","DOI":"10.1016\/j.heliyon.2024.e38495"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Zou, Z., Yu, H., Huang, J., Zhao, F.: Freqmamba: viewing mamba from a frequency perspective for image deraining. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 1905\u20131914 (2024)","DOI":"10.1145\/3664647.3680862"}],"container-title":["Lecture Notes in Computer Science","Information Processing in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-96628-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T11:59:47Z","timestamp":1757332787000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-96628-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"ISBN":["9783031966279","9783031966286"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-96628-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"3 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IPMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information Processing in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kos","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 May 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ipmi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ipmi2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}