{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:29:44Z","timestamp":1781533784460,"version":"3.54.5"},"reference-count":46,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T00:00:00Z","timestamp":1777075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771359"],"award-info":[{"award-number":["2025M771359"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"award":["2025M771359"],"award-info":[{"award-number":["2025M771359"]}],"id":[{"id":"https:\/\/ror.org\/0426zh255","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["JJ2025QC0495"],"award-info":[{"award-number":["JJ2025QC0495"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Fund Project of the Ministry of Education Key Laboratory","award":["VCAME202502"],"award-info":[{"award-number":["VCAME202502"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2572025BR11"],"award-info":[{"award-number":["2572025BR11"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computation"],"abstract":"<jats:p>Aero-engine defects often exhibit micro-scale and high-frequency characteristics under complex metallic textures, which makes precise segmentation difficult. Most existing pixel-level methods rely on spatial-domain modeling and lack frequency-domain decoupling. As a result, high-frequency details are easily hidden by low-frequency background information. In addition, repeated downsampling weakens the representation of fine-grained structures, leading to inaccurate boundary localization and limited robustness. To address these issues, a spectrum-driven hierarchical learning network is proposed for aero-engine defect segmentation. First, a dual-band spectral module is constructed using the discrete cosine transform to separate high-frequency and low-frequency components, providing stable and physically meaningful frequency-domain priors for the network. Second, a detail-guided module is designed where high-frequency features adaptively guide skip connections, compensating information loss during encoding and improving boundary recovery. Furthermore, a low-frequency-driven region-aware modeling module is developed. The internal defect regions, boundary areas, and background regions are modeled hierarchically. A dynamic hyper-kernel generation mechanism performs region-sensitive convolutional modeling, improving adaptation to complex structural variations. Extensive experiments on the Turbo19 and NEU-Seg datasets demonstrate that the proposed method produces accurate defect boundaries and achieves mIoU scores of 89.82% and 91.44%, improving over the second-best method by 5.22% and 4.42%, respectively.<\/jats:p>","DOI":"10.3390\/computation14050099","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T08:46:26Z","timestamp":1777538786000},"page":"99","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Spectrum-Driven Hierarchical Learning Network for Aero-Engine Defect Segmentation"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0435-4012","authenticated-orcid":false,"given":"Yining","family":"Xie","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4240-5940","authenticated-orcid":false,"given":"Aoqi","family":"Shen","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9648-2141","authenticated-orcid":false,"given":"Haochen","family":"Qi","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Northeast Forestry University, Harbin 150040, China"},{"name":"Key Laboratory of Vibration and Control of Aero-Propulsion System, Ministry of Education, Northeastern University, Shenyang 110819, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8464-3227","authenticated-orcid":false,"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1756-4341","authenticated-orcid":false,"given":"Jianpeng","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4766-7388","authenticated-orcid":false,"given":"Xichun","family":"Pan","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7890-0677","authenticated-orcid":false,"given":"Anlong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/TII.2023.3261889","article-title":"WDLS: Deep level set learning for weakly supervised aeroengine defect segmentation","volume":"20","author":"Qi","year":"2023","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_2","first-page":"5016514","article-title":"Multi-scale adaptive prototype transformer network for few-shot strip steel surface defect segmentation","volume":"74","author":"Huang","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"111681","DOI":"10.1109\/ACCESS.2025.3583752","article-title":"RSM-YOLOv11: Lightweight steel surface defect segmentation algorithm based on YOLOv11 improvement","volume":"13","author":"Shan","year":"2025","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103449","DOI":"10.1016\/j.media.2024.103449","article-title":"Dynamic spectrum-driven hierarchical learning network for polyp segmentation","volume":"101","author":"Wang","year":"2025","journal-title":"Med. Image Anal."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107717","DOI":"10.1016\/j.engappai.2023.107717","article-title":"A systematic review of deep learning approaches for surface defect detection in industrial applications","volume":"130","author":"Ameri","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"118377","DOI":"10.1016\/j.measurement.2025.118377","article-title":"A survey on industrial image anomaly detection: Methods, benchmarks and rethinks","volume":"256","author":"Mao","year":"2025","journal-title":"Measurement"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wen, G., Cheng, L., Yuan, H., and Li, X. (2025). Surface defect detection based on adaptive multi-scale feature fusion. Sensors, 25.","DOI":"10.3390\/s25061720"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.patrec.2024.11.024","article-title":"Enhanced multiscale attentional feature fusion model for defect detection on steel surfaces","volume":"188","author":"Xia","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1007\/s10462-024-10956-3","article-title":"Surface defect inspection of industrial products with object detection deep networks: A systematic review","volume":"57","author":"Ma","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"016222","DOI":"10.1088\/1361-6501\/ad9856","article-title":"Edge-aware interactive refinement network for strip steel surface defects detection","volume":"36","author":"Dong","year":"2025","journal-title":"Meas. Sci. Technol."},{"key":"ref_11","first-page":"40","article-title":"Steel Surface Defect Detection via the Multiscale Edge Enhancement Method","volume":"86","author":"Wang","year":"2026","journal-title":"Comput. Mater. Contin."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.jmsy.2025.11.022","article-title":"A comprehensive survey for real-world industrial surface defect detection: Challenges, approaches, and prospects","volume":"84","author":"Cheng","year":"2026","journal-title":"J. Manuf. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"108864","DOI":"10.1016\/j.rineng.2025.108864","article-title":"U-Net driven semantic segmentation for detection and quantification of cracks on gas turbine blade tips","volume":"29","author":"Kim","year":"2025","journal-title":"Results Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"116639","DOI":"10.1016\/j.measurement.2024.116639","article-title":"PIndNet: A pixel-wise industrial defect inspection network using multiple pyramid feature aggregation","volume":"245","author":"Zhou","year":"2025","journal-title":"Measurement"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"12131","DOI":"10.1007\/s10462-023-10475-7","article-title":"A survey of real-time surface defect inspection methods based on deep learning","volume":"56","author":"Liu","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"104067","DOI":"10.1016\/j.aei.2025.104067","article-title":"AI-enabled defect detection in industrial products: A comprehensive survey, key insights and future research challenges","volume":"69","author":"Nahar","year":"2026","journal-title":"Adv. Eng. Inform."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"He, Y., Li, S., Wen, X., and Xu, J. (2024). A survey on surface defect inspection based on generative models in manufacturing. Appl. Sci., 14.","DOI":"10.3390\/app14156774"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"103007","DOI":"10.1016\/j.inffus.2025.103007","article-title":"Deep learning based infrared small object segmentation: Challenges and future directions","volume":"118","author":"Yang","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"103225","DOI":"10.1016\/j.displa.2025.103225","article-title":"Review of deep learning-based segmentation methods: Popular approaches, literature gaps, and opportunities","volume":"91","author":"Celik","year":"2025","journal-title":"Displays"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Montello, F., G\u00fcldenring, R., Scardapane, S., and Nalpantidis, L. (2026). A survey on dynamic neural networks: From computer vision to multi-modal sensor fusion. Image Vis. Comput., 105980.","DOI":"10.1016\/j.imavis.2026.105980"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lee, D.H., Park, H.Y., and Lee, J. (2024). A review on recent deep learning-based semantic segmentation for urban greenness measurement. Sensors, 24.","DOI":"10.3390\/s24072245"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"108338","DOI":"10.1016\/j.knosys.2022.108338","article-title":"A nondestructive automatic defect detection method with pixelwise segmentation","volume":"242","author":"Yang","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5011410","DOI":"10.1109\/TIM.2021.3087826","article-title":"Auto-annotated deep segmentation for surface defect detection","volume":"70","author":"Tsai","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"110569","DOI":"10.1016\/j.measurement.2021.110569","article-title":"Defect detection in welding radiographic images based on semantic segmentation methods","volume":"188","author":"Xu","year":"2022","journal-title":"Measurement"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"110974","DOI":"10.1016\/j.engappai.2025.110974","article-title":"An edge-guided defect segmentation network for in-service aerospace engine blades","volume":"154","author":"Yang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1007\/s11760-024-03645-9","article-title":"Aviation-engine blade surface anomaly detection based on the deformable neural network","volume":"19","author":"Song","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Utomo, S., Sulistyaningrum, D.R., Setiyono, B., and Mubarok, M.K.N. (2025). Recurrent Residual U-Net for borescope crack segmentation in aero-engine. International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), IEEE.","DOI":"10.1109\/ICIMCIS68501.2025.11327414"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, J., Xu, Y., Fu, Q., Qian, J., and Wang, X. (2025). Aero-engine ablation defect detection with improved CLR-YOLOv11 algorithm. Sensors, 25.","DOI":"10.3390\/s25216574"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"6475","DOI":"10.1080\/00207543.2025.2473069","article-title":"Defect detection in impeller parts utilising local geometric feature analysis","volume":"63","author":"Wang","year":"2025","journal-title":"Int. J. Prod. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"119388","DOI":"10.1016\/j.eswa.2022.119388","article-title":"A pixel-level deep segmentation network for automatic defect detection","volume":"215","author":"Yang","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"5029510","DOI":"10.1109\/TIM.2023.3323004","article-title":"A pixel-level segmentation convolutional neural network based on global and local feature fusion for surface defect detection","volume":"72","author":"Zuo","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"125093","DOI":"10.1016\/j.eswa.2024.125093","article-title":"AeroClick: An advanced single-click interactive framework for aeroengine defect segmentation","volume":"257","author":"Qi","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1016\/j.cja.2022.05.002","article-title":"Visual inspection of aircraft skin: Automated pixel-level defect detection by instance segmentation","volume":"35","author":"Meng","year":"2022","journal-title":"Chin. J. Aeronaut."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"10463","DOI":"10.1109\/TII.2024.3396550","article-title":"SAIT: Harnessing sparse annotations and intrinsic tasks for semi-supervised aeroengine defect segmentation","volume":"20","author":"Qi","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"016197","DOI":"10.1088\/1361-6501\/ad9cb0","article-title":"An adaptive feature refinement network for pixel-level segmentation of surface defect","volume":"36","author":"Zhang","year":"2024","journal-title":"Meas. Sci. Technol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2724","DOI":"10.1109\/TASE.2024.3383451","article-title":"SPDP-Net: A semantic prior guided defect perception network for automated aero-engine blades surface visual inspection","volume":"22","author":"Ma","year":"2024","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"085405","DOI":"10.1088\/1361-6501\/acd5f2","article-title":"Automatic pixel-level detection of tire defects based on a lightweight Transformer architecture","volume":"34","author":"Sun","year":"2023","journal-title":"Meas. Sci. Technol."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Pham, H.C., Ta, Q.-B., Kim, J.-T., Ho, D.-D., Tran, X.-L., and Huynh, T.-C. (2020). Bolt-loosening monitoring framework using an image-based deep learning and graphical model. Sensors, 20.","DOI":"10.3390\/s20123382"},{"key":"ref_39","first-page":"17","article-title":"Semantic crack-image identification framework for steel structures using atrous convolution-based Deeplabv3+ Network","volume":"30","author":"Kim","year":"2022","journal-title":"Smart Struct. Syst. Int. J."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_41","unstructured":"Huang, C.-H., Wu, H.-Y., and Lin, Y.-L. (2021). HarDNet-MSEG: A simple encoder-decoder polyp segmentation neural network that achieves over 0.9 mean dice and 86 FPS. arXiv."},{"key":"ref_42","unstructured":"Dong, B., Wang, W., Fan, D.-P., Li, J., Fu, H., and Shao, L. (2021). Polyp-PVT: Polyp segmentation with pyramid vision transformers. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Fan, D.-P., Ji, G.-P., Zhou, T., Chen, G., Fu, H., Shen, J., and Shao, L. (2020). PraNet: Parallel reverse attention network for polyp segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer.","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Wei, J., Hu, Y., Zhang, R., Li, Z., Zhou, S.K., and Cui, S. (2021). Shallow attention network for polyp segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer.","DOI":"10.1007\/978-3-030-87193-2_66"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"109555","DOI":"10.1016\/j.patcog.2023.109555","article-title":"Cross-level feature aggregation network for polyp segmentation","volume":"140","author":"Zhou","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"102110","DOI":"10.1016\/j.compmedimag.2022.102110","article-title":"Boosting medical image segmentation via conditional-synergistic convolution and lesion decoupling","volume":"101","author":"Yang","year":"2022","journal-title":"Comput. Med. Imaging Graph."}],"container-title":["Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-3197\/14\/5\/99\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T09:01:11Z","timestamp":1777539671000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-3197\/14\/5\/99"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,25]]},"references-count":46,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["computation14050099"],"URL":"https:\/\/doi.org\/10.3390\/computation14050099","relation":{},"ISSN":["2079-3197"],"issn-type":[{"value":"2079-3197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,25]]}}}