{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:59:55Z","timestamp":1790312395300,"version":"4.1.0"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"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. Med."],"abstract":"<jats:p>Accurate delineation of the maxillary sinuses in CT images is a relevant step supporting preoperative planning and the evaluation of sinonasal disease within otolaryngology. Manual contouring of these paranasal sinus structures is difficult and error-prone, since the surrounding anatomy is complex, bony structures are thin, and inter-patient variability is large. This paper proposes an instance segmentation framework that extends the YOLO11n-Seg architecture through the integration of Coordinate Attention (CoordAtt) modules and Deformable Convolutional Networks v2 (DCNv2), to improve spatial feature representation and boundary precision for the right and left maxillary sinuses in CT images. CoordAtt encodes directional spatial context along horizontal and vertical axes to enhance anatomical localisation, while DCNv2 replaces selected fixed-kernel convolution layers with adaptive deformable sampling to better capture irregular and thin-walled sinus boundaries. The proposed model was trained and evaluated on the publicly available NasalSeg dataset, using all axial CT slices containing either maxillary sinus from 130 patients (3,620 slices; 104\/13\/13 patients across training\/validation\/test), and compared against three YOLO-family baselines (YOLOv8n-Seg, YOLO11n-Seg, and YOLO26n-Seg). On the 382-slice test set (13 patients), the proposed model achieved a mask mAP50 of 93.07% and mask mAP50-95 of 74.49%, outperforming the three baselines by up to +4.60 and +3.30 percentage points, respectively, and a box mAP50 of 91.00% and mAP50-95 of 75.83%. A component-wise ablation study confirmed that this improvement arises from the joint use of CoordAtt and DCNv2 rather than from either mechanism alone, and patient-level bootstrap confidence intervals and paired significance testing confirmed the statistical robustness of the observed gains. These results represent proof-of-concept evidence that coordinate-aware attention and deformable convolution can be effectively integrated into a YOLO-based instance segmentation pipeline for bilateral maxillary sinus delineation from CT.<\/jats:p>","DOI":"10.3389\/fmed.2026.1945669","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:26:51Z","timestamp":1790310411000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Coordinate attention and deformable convolution-enhanced YOLO for bilateral maxillary sinus segmentation, a paranasal sinus structure, in CT images"],"prefix":"10.3389","volume":"13","author":[{"given":"Ameera","family":"Jaradat","sequence":"first","affiliation":[{"name":"Computer Science Department, Faculty of Information Technology and Computer Sciences, Yarmouk University","place":["Irbid, Jordan"]},{"name":"Computer Science & Engineering, College of Engineering, American University of Sharjah","place":["Sharjah, United Arab Emirates"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salem","family":"Alhatamleh","sequence":"additional","affiliation":[{"name":"Computer Science Department, Faculty of Information Technology and Computer Sciences, Yarmouk University","place":["Irbid, Jordan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Amin","sequence":"additional","affiliation":[{"name":"Computer Science Department, Faculty of Information Technology and Computer Sciences, Yarmouk University","place":["Irbid, Jordan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abrar","family":"Omari","sequence":"additional","affiliation":[{"name":"Prince Hamzah Hospital","place":["Amman, Jordan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amal","family":"Alishwait","sequence":"additional","affiliation":[{"name":"Computer Science Department, Faculty of Information Technology and Computer Sciences, Yarmouk University","place":["Irbid, Jordan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rabia Emhamed","family":"Al Mamlook","sequence":"additional","affiliation":[{"name":"Department of Business Administration, Trine University","place":["Angola, IN, United States"]},{"name":"Department of Artificial Intelligence, Center of Advanced Research for Complementary Medicine, University of Zawia","place":["Zawia, Libya"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdullah Mohammed","family":"Al Fatais","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, College of Engineering, King Khalid University","place":["Abha, Saudi Arabia"]},{"name":"Center for Engineering and Technology Innovations, King Khalid University","place":["Abha, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4193\/Rhin20.401","article-title":"European position paper on rhinosinusitis and nasal polyps 2020","volume":"58","author":"Fokkens","year":"2020","journal-title":"Rhinology"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1216","DOI":"10.1111\/j.1398-9995.2011.02646.x","article-title":"Chronic rhinosinusitis in Europe - an underestimated disease: a GA2LEN study","volume":"66","author":"Hastan","year":"2011","journal-title":"Allergy"},{"key":"B3","doi-asserted-by":"publisher","first-page":"134","DOI":"10.2500\/ajra.2016.30.4297","article-title":"Chronic rhinosinusitis: epidemiology and burden of disease","volume":"30","author":"DeConde","year":"2016","journal-title":"Am J Rhinol Allergy"},{"key":"B4","author":"Harnsberger","year":""},{"key":"B5","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.ejrad.2018.02.033","article-title":"Imaging sinonasal disease with MRI: providing insight over and above CT","volume":"102","author":"Pulickal","year":"2018","journal-title":"Eur J Radiol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1007\/s11548-014-1134-5","article-title":"Automatic segmentation of the nasal cavity and paranasal sinuses from cone-beam CT images","volume":"10","author":"Bui","year":"2015","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"B7","doi-asserted-by":"publisher","first-page":"4125","DOI":"10.1002\/lary.32292","article-title":"Development of an open-source algorithm for automated segmentation in clinician-led paranasal sinus radiologic research","volume":"135","author":"Darbari Kaul","year":"2025","journal-title":"Laryngoscope"},{"key":"B8","doi-asserted-by":"publisher","first-page":"148","DOI":"10.3390\/jimaging11050148","article-title":"3D-NASE: a novel 3D CT nasal attention-based segmentation ensemble","volume":"11","author":"Pani","year":"2025","journal-title":"J Imaging"},{"key":"B9","doi-asserted-by":"publisher","first-page":"68720","DOI":"10.1109\/ACCESS.2026.3689347","article-title":"Adaptive frequency-spatial dual-stream network (AFS-DSN) for nasal and paranasal sinus CT segmentation","volume":"14","author":"Wan","year":"2026","journal-title":"IEEE Access"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.1038\/s41597-024-04176-1","article-title":"Nasalseg: a dataset for automatic segmentation of nasal cavity and paranasal sinuses from 3D CT images","volume":"11","author":"Zhang","year":"2024","journal-title":"Sci Data"},{"key":"B11","doi-asserted-by":"publisher","first-page":"46737","DOI":"10.1109\/ACCESS.2026.3673705","article-title":"UHCT-Net: a unified hybrid CNN\u2013transformer network for nasal CT segmentation and tumor analysis","volume":"14","author":"Alam","year":"2026","journal-title":"IEEE Access"},{"key":"B12","doi-asserted-by":"publisher","first-page":"111511","DOI":"10.1016\/j.compbiomed.2026.111511","article-title":"PARASIDE: an automatic paranasal sinus segmentation and structure analysis tool for magnetic resonance imaging","volume":"204","author":"M\u00f6ller","year":"2026","journal-title":"Comput Biol Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1778260","DOI":"10.3389\/fncom.2026.1778260","article-title":"Explainable hybrid CNN-transformer with self-supervised learning for structural analysis of paranasal sinus CT","volume":"20","author":"Ullah","year":"2026","journal-title":"Front Comput Neurosci"},{"key":"B14","doi-asserted-by":"publisher","first-page":"102541","DOI":"10.1016\/j.compmedimag.2025.102541","article-title":"Automatic semantic segmentation of the osseous structures of the paranasal sinuses","volume":"123","author":"Sun","year":"2025","journal-title":"Comput Med Imaging Graph"},{"key":"B15","doi-asserted-by":"publisher","first-page":"11653","DOI":"10.1038\/s41598-023-38273-9","article-title":"SinusC-Net for automatic classification of surgical plans for maxillary sinus augmentation using a 3D distance-guided network","volume":"13","author":"Hwang","year":"2023","journal-title":"Sci Rep"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1186\/s12903-024-04924-0","article-title":"Automatic maxillary sinus segmentation and pathology classification on cone-beam computed tomographic images using deep learning","volume":"24","author":"Altun","year":"2024","journal-title":"BMC Oral Health"},{"key":"B17","doi-asserted-by":"publisher","first-page":"120578","DOI":"10.1016\/j.ins.2024.120578","article-title":"CAT-Unet: an enhanced U-net architecture with coordinate attention and skip-neighborhood attention transformer for medical image segmentation","volume":"670","author":"Ding","year":"2024","journal-title":"Inf Sci"},{"key":"B18","doi-asserted-by":"publisher","first-page":"3820","DOI":"10.3390\/s22103820","article-title":"Multiresolution aggregation transformer UNet based on multiscale input and coordinate attention for medical image segmentation","volume":"22","author":"Chen","year":"2022","journal-title":"Sensors"},{"key":"B19","doi-asserted-by":"publisher","first-page":"86710","DOI":"10.1109\/ACCESS.2022.3199419","article-title":"Convolution neural network with coordinate attention for the automatic detection of pulmonary tuberculosis images on chest x-rays","volume":"10","author":"Xu","year":"2022","journal-title":"IEEE Access"},{"key":"B20","author":"Zhang","year":""},{"key":"B21","first-page":"301","article-title":"Hybrid deformable and basic convolution network for fine retinal vessel segmentation","author":"Yi","year":"2026"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e70416","DOI":"10.1002\/mp.70416","article-title":"Megavoltage CT enhancement for cervical cancer tomotherapy using a generative adversarial network with deformable convolution and self-attention","volume":"53","author":"Jian","year":"2026","journal-title":"Med Phys"},{"key":"B23","doi-asserted-by":"publisher","first-page":"336","DOI":"10.3390\/computers13120336","article-title":"The YOLO framework: a comprehensive review of evolution, applications, and benchmarks in object detection","volume":"13","author":"Ali","year":"2024","journal-title":"Computers"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.14569\/IJACSA.2025.01604111","article-title":"Optimizing medical image analysis: a performance evaluation of YOLO-based segmentation models.","volume":"16","author":"Alanazi","year":"2025","journal-title":"Int J Adv Comput Sci Appl"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1219","DOI":"10.3390\/diagnostics13071219","article-title":"Computer-aided diagnoses for sore throat based on dynamic uncertain causality graph","volume":"13","author":"Bu","year":"2023","journal-title":"Diagnostics"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1945669\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:26:52Z","timestamp":1790310412000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1945669\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"references-count":25,"alternative-id":["10.3389\/fmed.2026.1945669"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1945669","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"article-number":"1945669"}}