{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T14:26:02Z","timestamp":1780928762288,"version":"3.54.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:00:00Z","timestamp":1775174400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:00:00Z","timestamp":1775174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2023J01429"],"award-info":[{"award-number":["2023J01429"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Surg Endosc"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00464-026-12758-w","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T16:17:15Z","timestamp":1775233035000},"page":"4883-4899","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Crohn\u2019s disease lesion detection in capsule endoscopy with an advanced feature pyramid network"],"prefix":"10.1007","volume":"40","author":[{"given":"Jiwei","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3725-3461","authenticated-orcid":false,"given":"Shu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengli","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,3]]},"reference":[{"issue":"1","key":"12758_CR1","doi-asserted-by":"publisher","DOI":"10.1186\/s13062-020-00280-5","volume":"15","author":"L Petagna","year":"2020","unstructured":"Petagna L, Antonelli A, Ganini C et al (2020) Pathophysiology of Crohn\u2019s disease inflammation and recurrence. Biol Direct 15(1):23. https:\/\/doi.org\/10.1186\/s13062-020-00280-5","journal-title":"Biol Direct"},{"issue":"10","key":"12758_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04146-3","volume":"53","author":"D Marin-Santos","year":"2023","unstructured":"Marin-Santos D, Contreras-Fernandez J, Perez-Borrero I et al (2023) Automatic detection of Crohn disease in wireless capsule endoscopic images using a deep convolutional neural network. Appl Intell 53(10):12632-12646. https:\/\/doi.org\/10.1007\/s10489-022-04146-3","journal-title":"Appl Intell"},{"key":"12758_CR3","unstructured":"Ren S, He K, Girshick R, et al (2015) Faster R-CNN: Towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28"},{"key":"12758_CR4","unstructured":"Zhu X, Su W, Lu L, et al (2020) Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:201004159"},{"key":"12758_CR5","doi-asserted-by":"crossref","unstructured":"Lin TY, Dollar P, Girshick R, et al (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"12758_CR6","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, et al (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"12758_CR7","unstructured":"Ma X, Dai X, Yang J, et al (2024) Efficient modulation for vision networks. In: The twelfth international conference on learning representations. https:\/\/openreview.net\/forum?id=ip5LHJs6QX"},{"key":"12758_CR8","unstructured":"Ma J, Chen B (2020) Dual refinement feature pyramid networks for object detection. arXiv preprint arXiv:2012.01733"},{"key":"12758_CR9","doi-asserted-by":"crossref","unstructured":"Xu W, Wan Y (2024) Ela: Efficient local attention for deep convolutional neural networks. arXiv preprint arXiv:240301123","DOI":"10.1007\/s11554-025-01719-6"},{"key":"12758_CR10","unstructured":"Liu S, Huang D, Wang Y (2019) Learning spatial fusion for single-shot object detection. arXiv preprint arXiv:191109516"},{"key":"12758_CR11","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin TY, Le QV (2019) Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7036\u20137045","DOI":"10.1109\/CVPR.2019.00720"},{"key":"12758_CR12","doi-asserted-by":"crossref","unstructured":"Yang G, Lei J, Zhu Z, et al (2023) Afpn: asymptotic feature pyramid network for object detection. In: IEEE transactions on systems, man, and cybernetics, pp 2184\u20132189","DOI":"10.1109\/SMC53992.2023.10394415"},{"key":"12758_CR13","first-page":"1","volume-title":"ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"D Ouyang","year":"2023","unstructured":"Ouyang D, He S, Zhang G et al (2023) Efficient multi-scale attention module with cross-spatial learning. ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 1\u20135"},{"key":"12758_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"12758_CR15","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, et al (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"12758_CR16","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu CY, et al (2022) A convnet for the 2020s. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11976\u201311986","DOI":"10.1109\/CVPR52688.2022.01167"},{"issue":"4","key":"12758_CR17","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","volume":"9","author":"MH Guo","year":"2023","unstructured":"Guo MH, Lu CZ, Liu ZN et al (2023) Visual attention network. Comput Vis Media 9(4):733\u2013752","journal-title":"Comput Vis Media"},{"key":"12758_CR18","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, et al (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"12758_CR19","first-page":"11963","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"X Ding","year":"2022","unstructured":"Ding X, Zhang X, Han J et al (2022) Scaling up your kernels to 31x31: Revisiting large kernel design in CNNs. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 11963\u201311975"},{"key":"12758_CR20","doi-asserted-by":"crossref","unstructured":"Liu S, Chen T, Chen X, et al (2023) More convnets in the 2020s: scaling up kernels beyond 51\u00a0\u00d7\u00a051 using sparsity. In: Proceedings of the International Conference on Learning Representations (ICLR)","DOI":"10.1109\/ICIP49359.2023.10222130"},{"key":"12758_CR21","unstructured":"Lou M, Zhou HY, Yang S, et al (2023) Transxnet: learning both global and local dynamics with a dual dynamic token mixer for visual recognition. arXiv preprint arXiv:231019380"},{"key":"12758_CR22","doi-asserted-by":"crossref","unstructured":"Ma X, Dai X, Bai Y, et al (2024) Rewrite the stars. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 5694\u20135703","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"12758_CR23","doi-asserted-by":"crossref","unstructured":"Hou Q, Zhou D, Feng J (2021) Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13713\u201313722","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"12758_CR24","doi-asserted-by":"crossref","unstructured":"Wang CY, Liao HYM, Wu YH, et al (2020) Cspnet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 390\u2013391","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"12758_CR25","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"key":"12758_CR26","first-page":"12021","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"J Chen","year":"2023","unstructured":"Chen J, Kao S, He H et al (2023) Run, don\u2019t walk: Chasing higher flops for faster neural networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 12021\u201312031"},{"key":"12758_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, et al (2017) Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"12758_CR28","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, et al (2014) Microsoft coco: common objects in context. In: Computer vision-ECCV 2014: 13th European conference, Zurich, Sept 6\u201312, 2014, Proceedings, Part V 13, Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"12758_CR29","unstructured":"Paszke A, Gross S, Massa F, et al (2019) Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"12758_CR30","unstructured":"Chen K, Wang J, Pang J, et al (2019) MMDetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:190607155"},{"key":"12758_CR31","unstructured":"Loshchilov I (2017) Decoupled weight decay regularization. arXiv preprint arXiv:171105101"},{"key":"12758_CR32","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","volume-title":"2009 IEEE conference on computer vision and pattern recognition","author":"J Deng","year":"2009","unstructured":"Deng J, Dong W, Socher R et al (2009) Imagenet: a large-scale hierarchical image database. 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248\u2013255"},{"key":"12758_CR33","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"12758_CR34","doi-asserted-by":"crossref","unstructured":"Sun P, Zhang R, Jiang Y, et al (2021) Sparse R-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14454\u201314463","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"12758_CR35","first-page":"1","volume":"60","author":"Y Peng","year":"2022","unstructured":"Peng Y, Zhang Y, Tu B et al (2022) Spatial-spectral transformer with cross-attention for hyperspectral image classification. IEEE Trans Geosci Remote Sens 60:1\u201315","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"12758_CR36","doi-asserted-by":"crossref","unstructured":"Zhang H, Chang H, Ma B, et al (2020) Dynamic R-CNN: Towards high quality object detection via dynamic training. In: Computer vision-ECCV 2020: 16th European conference, Glasgow, Aug 23\u201328, 2020, Proceedings, Part XV 16, Springer, pp 260\u2013275","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"12758_CR37","unstructured":"Liu S, Li F, Zhang H, et al (2022) Dab-detr: dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:220112329"},{"key":"12758_CR38","doi-asserted-by":"crossref","unstructured":"Meng D, Chen X, Fan Z, et al (2021) Conditional detr for fast training convergence. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3651\u20133660","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"12758_CR39","unstructured":"Zhang H, Li F, Liu S, et al (2022) Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:220303605"},{"key":"12758_CR40","doi-asserted-by":"crossref","unstructured":"Zhang S, Wang X, Wang J, et al (2023) 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","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"12758_CR41","doi-asserted-by":"crossref","unstructured":"Pang J, Chen K, Shi J, et al (2019) Libra R-CNN: towards balanced learning for object detection. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 821\u2013830","DOI":"10.1109\/CVPR.2019.00091"},{"key":"12758_CR42","doi-asserted-by":"crossref","unstructured":"Wang J, Chen K, Xu R, et al (2019) Carafe: content-aware reassembly of features. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3007\u20133016","DOI":"10.1109\/ICCV.2019.00310"},{"key":"12758_CR43","unstructured":"Chen K, Cao Y, Loy CC, et al (2020) Feature pyramid grids. arXiv preprint arXiv:2004.03580"}],"container-title":["Surgical Endoscopy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00464-026-12758-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00464-026-12758-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00464-026-12758-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T13:52:44Z","timestamp":1780926764000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00464-026-12758-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,3]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["12758"],"URL":"https:\/\/doi.org\/10.1007\/s00464-026-12758-w","relation":{},"ISSN":["0930-2794","1432-2218"],"issn-type":[{"value":"0930-2794","type":"print"},{"value":"1432-2218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,3]]},"assertion":[{"value":"31 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors involved in this manuscript are Jiwei Wu, Shu Zhang, Weiwei Zheng, Mengli Xue. All the above authors have no conflicts of interest or financial ties to any pharmaceutical or device companies. Specifically, there are no relevant relationships including but not limited to consultancies, honoraria, stock ownership, gifts, reimbursed travel, equity interests, patent arrangements, or other vested interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosures"}}]}}