{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:48:56Z","timestamp":1782838136372,"version":"3.54.5"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T00:00:00Z","timestamp":1761782400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Lung cancer remains as an important source of cancer-related mortality worldwide, demonstrating a substantial challenge to public health systems. The absence of evident symptoms in the early stages makes timely diagnosis of lung cancer challenging. Early identification and treatment will reduce the mortality rate caused by lung cancer. Abnormal growths identified as lung or pulmonary nodules can be found in the lungs and some of these could be malignant. A Computer-Aided Detection (CAD) framework can aid in identifying pulmonary nodules by investigating medical images. Automated CAD systems assist radiologists by reducing the diagnostic workload and increasing the possibility of early lung cancer identification. Finding and accurately outlining lung nodules is the specific task of lung nodule segmentation in medical image analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Multi-scale UNet, Feature Pyramid Network (FPN) with Linear Attention Mechanism and UNet with Asynchronous Convolution Blocks (ACB) and Channel Attention Mechanism were used to segment lung nodules. Multi-scale UNet improvises the traditional UNet architecture by incorporating multi-scale convolutional operations, which improves feature extraction and boosts segmentation accuracy. The UNet with ACB and Channel Attention Mechanism employs a cross-like receptive field that can reduce the impact of redundant information in obtaining representative characteristics. FPN with Linear Attention mechanism uses a multi-scale feature pyramid to identify nodules of different sizes and a linear attention mechanism is employed to improve feature extraction. FPN with Linear Attention mechanism attains a linear time and spatial complexity while effectively segmenting pulmonary nodules.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results and discussion<\/jats:title>\n                    <jats:p>Employing the FPN with Linear Attention mechanism yielded the highest performance in the experiments. The highest results in the study using FPN with Linear Attention were achieved using GELU on the LIDC-IDRI dataset with a DSC of 71.59% and IoU of 58.57%. The smooth, probabilistic weighting of GeLU complements the model's attention mechanisms.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1682171","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:22:02Z","timestamp":1761805322000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Leveraging multi-scale feature integration in UNet and FPN for semantic segmentation of lung nodules"],"prefix":"10.3389","volume":"8","author":[{"given":"Sarah","family":"Prithvika","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jani","family":"Anbarasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Modigari","family":"Narendra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3281135","DOI":"10.1155\/2021\/3281135","article-title":"Covid-19 and pneumonia diagnosis in x-ray images using convolutional neural networks","volume":"2021","author":"Abiyev","year":"2021","journal-title":"Mathem. Prob. Eng"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1007\/s11227-021-03845-x","article-title":"An efficient u-net framework for lung nodule detection using densely connected dilated convolutions","volume":"78","author":"Ali","year":"2022","journal-title":"J. Supercomput"},{"key":"B3","unstructured":"Lung Nodule, Patient Education\n          \n          2025"},{"key":"B4","doi-asserted-by":"publisher","first-page":"11591","DOI":"10.1038\/s41598-019-48004-8","article-title":"iw-net: an automatic and minimalistic interactive lung nodule segmentation deep network","volume":"9","author":"Aresta","year":"2019","journal-title":"Sci. Rep"},{"key":"B5","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1118\/1.3528204","article-title":"The lung image database consortium (LIDC) and image database resource initiative (idri): a completed reference database of lung nodules on ct scans","volume":"38","author":"Armato","year":"2011","journal-title":"Med. Phys"},{"key":"B6","doi-asserted-by":"publisher","first-page":"5245","DOI":"10.1007\/s00371-022-02657-1","article-title":"A bi-directional deep learning architecture for lung nodule semantic segmentation","volume":"39","author":"Bhattacharyya","year":"2023","journal-title":"Vis. Comput"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2006","DOI":"10.1109\/JBHI.2019.2963720","article-title":"A two-stage convolutional neural networks for lung nodule detection","volume":"24","author":"Cao","year":"2020","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B8","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1109\/TMI.2007.907555","article-title":"Segmentation of pulmonary nodules in thoracic ct scans: a region growing approach","volume":"27","author":"Dehmeshki","year":"2008","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B9","doi-asserted-by":"publisher","first-page":"3418","DOI":"10.1109\/TBME.2011.2167621","article-title":"Automated segmentation refinement of small lung nodules in ct scans by local shape analysis","volume":"58","author":"Diciotti","year":"2011","journal-title":"IEEE Trans. Biomed. Eng"},{"key":"B10","first-page":"1911","article-title":"\u201cACNet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Ding","year":"2019"},{"key":"B11","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1109\/APSIPAASC58517.2023.10317244","article-title":"\u201c1m parameters are enough? a lightweight cnn-based model for medical image segmentation,\u201d","volume-title":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Dinh","year":"2023"},{"key":"B12","doi-asserted-by":"publisher","first-page":"113017","DOI":"10.1016\/j.eswa.2019.113017","article-title":"Multi-view convolutional neural network for lung nodule false positive reduction","volume":"162","author":"El-Regaily","year":"2020","journal-title":"Expert Syst. Appl"},{"key":"B13","doi-asserted-by":"publisher","first-page":"5202","DOI":"10.1109\/TIP.2013.2282899","article-title":"A novel approach for lung nodules segmentation in chest ct using level sets","volume":"22","author":"Farag","year":"2013","journal-title":"IEEE Trans. Image Proc"},{"key":"B14","unstructured":"Ferlay\n              J.\n            \n            \n              Ervik\n              M.\n            \n            \n              Lam\n              F.\n            \n            \n              Laversanne\n              M.\n            \n            \n              Colombet\n              M.\n            \n            \n              Mery\n              L.\n            \n          \n          Global Cancer Observatory: Cancer Today\n          \n          2024"},{"key":"B15","first-page":"271","article-title":"\u201cLung ct image segmentation using double adaptive attention aided transunet,\u201d","volume-title":"International Conference on Computational Intelligence in Pattern Recognition","author":"Gautam","year":"2024"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.03191","article-title":"Level set image segmentation with velocity term learned from data with applications to lung nodule segmentation","author":"Hancock","year":"2019","journal-title":"arXiv"},{"key":"B17","first-page":"770","article-title":"\u201cDeep residual learning for image recognition,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1660","DOI":"10.1016\/j.procs.2023.01.144","article-title":"Covid-19 lung CT image segmentation using localization and enhancement methods with U-Net","volume":"218","author":"Ilhan","year":"2023","journal-title":"Procedia Comput. Sci"},{"key":"B19","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1109\/TMI.2018.2857800","article-title":"Multiple resolution residually connected feature streams for automatic lung tumor segmentation from ct images","volume":"38","author":"Jiang","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B20","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.compbiomed.2017.11.013","article-title":"Ground-glass nodule segmentation in chest ct images using asymmetric multi-phase deformable model and pulmonary vessel removal","volume":"92","author":"Jung","year":"2018","journal-title":"Comput. Biol. Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1109\/TMI.2006.871547","article-title":"Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic ct scans","volume":"25","author":"Kuhnigk","year":"2006","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1088\/0031-9155\/60\/3\/1307","article-title":"Robust semi-automatic segmentation of pulmonary subsolid nodules in chest computed tomography scans","volume":"60","author":"Lassen","year":"2015","journal-title":"Phys. Med. Biol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"8007205","DOI":"10.1109\/LGRS.2021.3052886","article-title":"Macu-net for semantic segmentation of fine-resolution remotely sensed images","volume":"19","author":"Li","year":"","journal-title":"IEEE Geosci. Remote Sens. Letters"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2007.14902","article-title":"Linear attention mechanism: An efficient attention for semantic segmentation","author":"Li","year":"2020","journal-title":"arXiv"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1080\/01431161.2022.2030071","article-title":"A2-fpn for semantic segmentation of fine-resolution remotely sensed images","volume":"43","author":"Li","year":"","journal-title":"Int. J. Remote Sens"},{"key":"B26","first-page":"2117","article-title":"\u201cFeature pyramid networks for object detection,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Lin","year":"2017"},{"key":"B27","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal"},{"key":"B28","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1109\/EIECS63941.2024.10800611","article-title":"\u201cA parallel fusion of cnn and transformer for ct lung nodule detection,\u201d","volume-title":"2024 4th International Conference on Electronic Information Engineering and Computer Science (EIECS)","author":"Liu","year":"2024"},{"key":"B29","first-page":"1205","article-title":"\u201cLung nodule segmentation using deep learned prior based graph cut,\u201d","volume-title":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI)","author":"Mukherjee","year":"2017"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2533","DOI":"10.1007\/s00034-023-02575-0","article-title":"Low-dose CT image denoising with a residual multi-scale feature fusion convolutional neural network and enhanced perceptual loss","volume":"43","author":"Niknejad Mazandarani","year":"2024","journal-title":"Circuits, Syst. Signal Proc"},{"key":"B31","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.lungcan.2008.07.003","article-title":"Design, recruitment and baseline results of the italung trial for lung cancer screening with low-dose CT","volume":"64","author":"Pegna","year":"2009","journal-title":"Lung Cancer"},{"key":"B32","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1109\/34.56205","article-title":"Scale-space and edge detection using anisotropic diffusion","volume":"12","author":"Perona","year":"1990","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B33","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/978-1-4757-6017-0_4","article-title":"\u201cMedian filters,\u201d","volume-title":"Nonlinear Digital Filters: Principles and Applications","author":"Pitas","year":"1990"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4065778","article-title":"Robustness of different loss functions and their impact on network's learning","author":"Rajput","year":"2022","journal-title":"SSRN Electron. J."},{"key":"B35","first-page":"234","article-title":"\u201cU-Net: Convolutional networks for biomedical image segmentation,\u201d","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015","author":"Ronneberger","year":"2015"},{"key":"B36","doi-asserted-by":"publisher","first-page":"5361","DOI":"10.1007\/s00371-024-03726-3","article-title":"Ct-uformer: an improved hybrid decoder for image segmentation","volume":"41","author":"Shen","year":"2025","journal-title":"Vis. Comput"},{"key":"B37","doi-asserted-by":"publisher","first-page":"106804","DOI":"10.1016\/j.bspc.2024.106804","article-title":"Mast-unet: More adaptive semantic texture for segmenting pulmonary nodules","volume":"99","author":"Shi","year":"2025","journal-title":"Biomed. Signal Process. Cont"},{"key":"B38","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/TMI.2015.2474119","article-title":"Lung lesion extraction using a toboggan based growing automatic segmentation approach","volume":"35","author":"Song","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B39","doi-asserted-by":"publisher","first-page":"639930","DOI":"10.3389\/fgene.2021.639930","article-title":"Msu-net: Multi-scale u-net for 2d medical image segmentation","volume":"12","author":"Su","year":"2021","journal-title":"Front. Genet"},{"key":"B40","doi-asserted-by":"publisher","first-page":"105866","DOI":"10.1016\/j.cmpb.2020.105866","article-title":"Lung nodule detection based on faster r-cnn framework","volume":"200","author":"Su","year":"2021","journal-title":"Comput. Methods Programs Biomed"},{"key":"B41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/CICT53865.2020.9672439","article-title":"\u201cComparing different deep learning backbones for segmentation of lung nodules,\u201d","volume-title":"2021 5th Conference on Information and Communication Technology (CICT)","author":"Suji","year":"2021"},{"key":"B42","doi-asserted-by":"publisher","first-page":"9685","DOI":"10.1007\/s11042-023-15871-3","article-title":"Exploring pretrained encoders for lung nodule segmentation task using LIDC-IDRI dataset","volume":"83","author":"Suji","year":"2024","journal-title":"Multimed. Tools Appl"},{"key":"B43","doi-asserted-by":"publisher","first-page":"129827","DOI":"10.1016\/j.neucom.2025.129827","article-title":"Ln-detr: An efficient transformer architecture for lung nodule detection with multi-scale feature fusion","volume":"633","author":"Tang","year":"2025","journal-title":"Neurocomputing"},{"key":"B44","doi-asserted-by":"publisher","first-page":"105781","DOI":"10.1016\/j.compbiomed.2022.105781","article-title":"CSE-GAN: A 3D conditional generative adversarial network with concurrent squeeze-and-excitation blocks for lung nodule segmentation","volume":"147","author":"Tyagi","year":"2022","journal-title":"Comput. Biol. Med"},{"key":"B45","doi-asserted-by":"publisher","first-page":"14291","DOI":"10.1007\/s11042-020-08618-x","article-title":"An effective neural network model for lung nodule detection in ct images with optimal fuzzy model","volume":"79","author":"Veronica","year":"2020","journal-title":"Multimed. Tools Appl"},{"key":"B46","doi-asserted-by":"publisher","first-page":"106330","DOI":"10.1016\/j.compbiomed.2022.106330","article-title":"DPBET: A dual-path lung nodules segmentation model based on boundary enhancement and hybrid transformer","volume":"151","author":"Wang","year":"2022","journal-title":"Comput. Biol. Med"},{"key":"B47","first-page":"3","article-title":"\u201cCBAM: convolutional block attention module,\u201d","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Woo","year":"2018"},{"key":"B48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-319-40389-2_1","article-title":"\u201cLung cancer screening,\u201d","volume-title":"Lung Cancer: Treatment and Research","author":"Wu","year":"2016"},{"key":"B49","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.cllc.2016.03.007","article-title":"Psychological burden associated with lung cancer screening: a systematic review","volume":"17","author":"Wu","year":"2016","journal-title":"Clin. Lung Cancer"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12938-020-00793-0","article-title":"Segmentation of small ground glass opacity pulmonary nodules based on markov random field energy and bayesian probability difference","volume":"19","author":"Zhang","year":"2020","journal-title":"Biomed. Eng. Online"},{"key":"B51","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1002\/ima.22527","article-title":"Automatic covid-19 ct segmentation using U-Net integrated spatial and channel attention mechanism","volume":"31","author":"Zhou","year":"2021","journal-title":"Int. J. Imaging Syst. Technol"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1682171\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:22:08Z","timestamp":1761805328000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1682171\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,30]]},"references-count":51,"alternative-id":["10.3389\/frai.2025.1682171"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1682171","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,30]]},"article-number":"1682171"}}