{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T23:43:42Z","timestamp":1780098222760,"version":"3.54.0"},"reference-count":40,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Objectives: This study aimed to develop and validate a hybrid deep learning model combining Convolutional Neural Networks (CNN) and Vision Transformers (ViT) to automatically classify maxillary sinus membrane morphologies on Cone-Beam Computed Tomography (CBCT) images, distinguishing between Normal, Flat, Polypoid, and Obstruction types. Methods: A dataset of 959 CBCT images was collected and categorized into four morphological classes: Normal, Flat, Polypoid and Obstruction. A custom hybrid model was developed, integrating a lightweight residual CNN for local feature extraction, learnable weighted feature fusion with a bidirectional feature pyramid network and a Transformer encoder for global context modeling. The performance of proposed model was compared against six different architectures, including ResNet50, MobileNetV3L and standard ViT models, using accuracy, precision, recall and F1-score metrics. Results: The proposed hybrid model achieved the highest overall accuracy of 98.44%, outperforming six strong CNN and ViT models including ResNet50 (97.92%) and ViT-B16 (86.46%) models. In class-wise analysis, the model demonstrated superior diagnostic capability, particularly for the \u201cObstruction\u201d class, achieving 100% accuracy. High discrimination was also observed for \u201cFlat\u201d (98.21%) and \u201cPolypoid\u201d (98.04%) morphologies, confirming the model\u2019s sensitivity to shape-based features. Conclusions: The proposed hybrid CNN-ViT model successfully classifies maxillary sinus membrane morphologies with high accuracy, effectively overcoming the limitations of standard ViT models on limited datasets. Detection of membrane morphology is vital for predicting surgical risks like membrane perforation and post-operative sinusitis. This model serves as a reliable clinical decision support tool, enabling clinicians to objectively assess specific risk factors before implant surgery and sinus floor elevation.<\/jats:p>","DOI":"10.3390\/diagnostics16050777","type":"journal-article","created":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T13:11:22Z","timestamp":1772716282000},"page":"777","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluation of Maxillary Sinus Membrane Morphology Using a Novel Hybrid CNN-ViT-Based Deep Learning Model: An Automated Classification Study"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0625-3864","authenticated-orcid":false,"given":"Nurullah","family":"Duger","sequence":"first","affiliation":[{"name":"Department of Periodontology, Faculty of Dentistry, Firat University, Elazig 23119, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4891-7873","authenticated-orcid":false,"given":"Furkan","family":"Talo","sequence":"additional","affiliation":[{"name":"Digital Transformation and Software Office, Rectorate, Firat University, Elazig 23119, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gulucag Giray","family":"Tekin","sequence":"additional","affiliation":[{"name":"Department of Periodontology, Faculty of Dentistry, Batman University, Batman 72060, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1982-8225","authenticated-orcid":false,"given":"Burak","family":"Dagtekin","sequence":"additional","affiliation":[{"name":"Department of Periodontology, Faculty of Dentistry, Firat University, Elazig 23119, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8087-4044","authenticated-orcid":false,"given":"Mucahit","family":"Karaduman","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Malatya Turgut Ozal University, Malatya 44000, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1866-4721","authenticated-orcid":false,"given":"Muhammed","family":"Yildirim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence and Data Engineering, Firat University, Elazig 23119, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuba Talo","family":"Yildirim","sequence":"additional","affiliation":[{"name":"Department of Periodontology, Faculty of Dentistry, Firat University, Elazig 23119, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1097\/SCS.0000000000001725","article-title":"Maxillary sinus septa and anatomic correlation with the Schneiderian membrane","volume":"26","author":"Rancitelli","year":"2015","journal-title":"J. Craniofac. Surg."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Martu, C., Martu, M.A., Maftei, G.A., Diaconu-Popa, D.A., and Radulescu, L. (2022). Odontogenic sinusitis: From diagnosis to treatment possibilities\u2014A narrative review of recent data. Diagnostics, 12.","DOI":"10.3390\/diagnostics12071600"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e18050","DOI":"10.1016\/j.heliyon.2023.e18050","article-title":"Increased risks of maxillary sinus mucosal thickening in Chinese patients with periapical lesions","volume":"9","author":"Zhang","year":"2023","journal-title":"Heliyon"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1111\/clr.12646","article-title":"The influence of sinus membrane thickness upon membrane perforation during lateral window sinus augmentation","volume":"27","author":"Lin","year":"2016","journal-title":"Clin. Oral Implant. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"329","DOI":"10.4041\/kjod.2012.42.6.329","article-title":"Prevalence of incidental maxillary sinus findings in Italian orthodontic patients: A retrospective cone-beam computed tomography study","volume":"42","author":"Gracco","year":"2012","journal-title":"Korean J. Orthod."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1055\/s-0036-1593834","article-title":"Evaluation of the prevalence of maxillary sinuses abnormalities through spiral computed tomography (CT)","volume":"21","author":"Drumond","year":"2017","journal-title":"Int. Arch. Otorhinolaryngol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"15529","DOI":"10.1038\/s41598-024-66527-7","article-title":"Retrospective analysis of pathological changes in the maxillary sinus with CBCT","volume":"14","author":"Dogan","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1007\/s00784-017-2105-3","article-title":"Association of inflammatory status and maxillary sinus Schneiderian membrane thickness","volume":"22","author":"Insua","year":"2018","journal-title":"Clin. Oral Investig."},{"key":"ref_9","first-page":"115","article-title":"Sinus presurgical evaluation: A literature review and a new classification proposal","volume":"66","author":"Tavelli","year":"2017","journal-title":"Minerva Stomatol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1111\/clr.12168","article-title":"Cone-beam computed tomographic analysis of sinus membrane thickness, ostium patency, and residual ridge heights in the posterior maxilla: Implications for sinus floor elevation","volume":"25","author":"Shanbhag","year":"2014","journal-title":"Clin. Oral Implant. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1097\/RLI.0000000000000503","article-title":"Deep learning in diagnosis of maxillary sinusitis using conventional radiography","volume":"54","author":"Kim","year":"2019","journal-title":"Investig. Radiol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/s40729-018-0143-5","article-title":"Thickness of the Schneiderian membrane and its correlation with anatomical structures and demographic parameters using CBCT tomography: A retrospective study","volume":"4","author":"Kalyvas","year":"2018","journal-title":"Int. J. Implant. Dent."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1007\/s11282-018-0363-7","article-title":"Deep-learning classification using convolutional neural network for evaluation of maxillary sinusitis on panoramic radiography","volume":"35","author":"Murata","year":"2019","journal-title":"Oral Radiol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Schiller, L.A., Barbu, H.M., Iancu, S.A., and Brad, S. (2022). Incidence, size and orientation of maxillary sinus septa\u2014A retrospective clinical study. J. Clin. Med., 11.","DOI":"10.3390\/jcm11092393"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1093\/dmfr\/twae031","article-title":"Deep learning in the diagnosis of maxillary sinus diseases: A systematic review","volume":"53","author":"Wu","year":"2024","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"14009","DOI":"10.1038\/s41598-022-18436-w","article-title":"Deep learning-based fully automatic segmentation of the maxillary sinus on cone-beam computed tomographic images","volume":"12","author":"Choi","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1055\/s-0034-1371550","article-title":"A diagnosis of maxillary sinus fracture with cone-beam CT: Case report and literature review","volume":"7","author":"Yilmaz","year":"2014","journal-title":"Craniomaxillofac. Trauma Reconstr."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ravesh, M.N., Ameli, N., Vich, M.L., and Lai, H. (2025). Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scans. Front. Dent. Med., 6.","DOI":"10.3389\/fdmed.2025.1583455"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Shujaat, S. (2025). Automated Machine Learning in Dentistry: A Narrative Review of Applications, Challenges, and Future Directions. Diagnostics, 15.","DOI":"10.3390\/diagnostics15030273"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"187","DOI":"10.5624\/isd.20210263","article-title":"Evaluation of maxillary sinusitis from panoramic radiographs and cone-beam computed tomographic images using a convolutional neural network","volume":"52","author":"Serindere","year":"2022","journal-title":"Imaging Sci. Dent."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2734","DOI":"10.1038\/s41598-023-29890-5","article-title":"Automatic diagnosis of retention pseudocyst in the maxillary sinus on panoramic radiographs using a convolutional neural network algorithm","volume":"13","author":"Ha","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Altun, O., Ozen, D.C., Duman, S.B., Dedeoglu, N., Bayrakdar, I.S., Eser, G., Celik, O., Sumbullu, M.A., and Syed, A.Z. (2024). Automatic maxillary sinus segmentation and pathology classification on cone-beam computed tomographic images using deep learning. BMC Oral Health, 24.","DOI":"10.1186\/s12903-024-04924-0"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"6111","DOI":"10.1007\/s00405-024-08870-z","article-title":"Automatic segmentation of the maxillary sinus on cone beam computed tomographic images with U-Net deep learning model","volume":"281","author":"Ozturk","year":"2024","journal-title":"Eur. Arch. Otorhinolaryngol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.1111\/joor.13585","article-title":"Abnormal maxillary sinus diagnosing on CBCT images via object detection and \u201cstraight-forward\u201d classification deep learning strategy","volume":"50","author":"Zeng","year":"2023","journal-title":"J. Oral Rehabil."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Szab\u00f3, V., Orhan, K., Dob\u00f3-Nagy, C., Veres, D.S., Manulis, D., Ezhov, M., Sanders, A., and Szab\u00f3, B.T. (2025). Deep learning-based periapical lesion detection on panoramic radiographs. Diagnostics, 15.","DOI":"10.3390\/diagnostics15040510"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Butnaru, O.M., Tatarciuc, M., Luchian, I., Tudorici, T., Balcos, C., Budala, D.G., Sirghe, A., Virvescu, D.I., and Haba, D. (2025). AI efficiency in dentistry: Comparing artificial intelligence systems with human practitioners in assessing several periodontal parameters. Medicina, 61.","DOI":"10.3390\/medicina61040572"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ibraheem, W.I., Jain, S., Ayoub, M.N., Namazi, M.A., Alfaqih, A.I., Aggarwal, A., Meshni, A.A., Almarghlani, A., and Alhumaidan, A.A. (2025). Assessment of the diagnostic accuracy of artificial intelligence software in identifying common periodontal and restorative dental conditions (marginal bone loss, periapical lesion, crown, restoration, dental caries) in intraoral periapical radiographs. Diagnostics, 15.","DOI":"10.3390\/diagnostics15111432"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ardila, C.M., Pineda-V\u00e9lez, E., and Vivares-Builes, A.M. (2025). Artificial intelligence in endodontic education: A systematic review with frequentist and Bayesian meta-analysis of student-based evidence. Dent. J., 13.","DOI":"10.3390\/dj13110489"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020). EfficientDet: Scalable and efficient object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1007\/978-3-030-01231-1_8","article-title":"Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection","volume":"Volume 11210","author":"Zhu","year":"2018","journal-title":"Computer Vision\u2014ECCV 2018"},{"key":"ref_31","first-page":"5998","article-title":"Attention is all you need","volume":"Volume 30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref_32","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021). An image is worth 16\u00d716 words: Transformers for image recognition at scale. International Conference on Learning Representations (ICLR), ICLR."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2017). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A convnet for the 2020s. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (2019). Searching for MobileNetV3. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3987","DOI":"10.1007\/s00784-021-04365-x","article-title":"Automatic detection and segmentation of morphological changes of the maxillary sinus mucosa on cone-beam computed tomography images using a three-dimensional convolutional neural network","volume":"26","author":"Hung","year":"2022","journal-title":"Clin. Oral Investig."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1007\/s00784-025-06191-x","article-title":"A platform combining automatic segmentation and automatic measurement of the maxillary sinus and adjacent structures","volume":"29","author":"He","year":"2025","journal-title":"Clin. Oral Investig."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Alhumaid, M., and Fayoumi, A.G. (2025). Hybrid CNN\u2014Swin transformer model to advance the diagnosis of maxillary sinus abnormalities on CT images using explainable AI. Computers, 14.","DOI":"10.3390\/computers14100419"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1902\/jop.2011.110376","article-title":"Cone-beam computed tomographic evidence of the association between periodontal bone loss and mucosal thickening of the maxillary sinus","volume":"83","author":"Phothikhun","year":"2012","journal-title":"J. Periodontol."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/5\/777\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T13:29:09Z","timestamp":1772717349000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/5\/777"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,5]]},"references-count":40,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["diagnostics16050777"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16050777","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,5]]}}}