{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T11:51:03Z","timestamp":1777722663073,"version":"3.51.4"},"reference-count":44,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T00:00:00Z","timestamp":1742515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Vertebral fracture (VF) may induce spinal cord injury that can lead to serious consequences which eventually may paralyze the entire or some parts of the body depending on the location and severity of the injury. Diagnosis of VFs is crucial at the initial stage, which may be challenging because of the subtle features, noise, and homogeneity present in the computed tomography (CT) images. In this study, Wide ResNet-40, DenseNet-121, and EfficientNet-B7 are chosen, fine-tuned, and used as base models, and a Bayesian-based probabilistic ensemble learning method is proposed for fracture detection in cervical spine CT images. The proposed method considers the prediction\u2019s uncertainty of the base models and combines the predictions obtained from them, to improve the overall performance significantly. This method assigns weights to the base learners, based on their performance and confidence about the prediction. To increase the robustness of the proposed model, custom data augmentation techniques are performed in the preprocessing step. This work utilizes 15,123 CT images from the RSNA-2022 C-spine fracture detection challenge and demonstrates superior performance compared to the individual base learners, and the other existing conventional ensemble methods. The proposed model also outperforms the best state-of-the-art (SOTA) model by 1.62%, 0.51%, and 1.29% in terms of accuracy, specificity, and sensitivity, respectively; furthermore, the AUC score of the best SOTA model is lagging by 5%. The overall accuracy, specificity, sensitivity, and F1-score of the proposed model are 94.62%, 93.51%, 95.29%, and 93.16%, respectively.<\/jats:p>","DOI":"10.3390\/a18040181","type":"journal-article","created":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T06:21:38Z","timestamp":1742797298000},"page":"181","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Improving Vertebral Fracture Detection in C-Spine CT Images Using Bayesian Probability-Based Ensemble Learning"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3952-9785","authenticated-orcid":false,"given":"Abhishek Kumar","family":"Pandey","sequence":"first","affiliation":[{"name":"Department of Mathematical and Computational Sciences, National Institute of Technology Karnataka, Surathkal, Mangalore 575025, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1562-2756","authenticated-orcid":false,"given":"Kedarnath","family":"Senapati","sequence":"additional","affiliation":[{"name":"Department of Mathematical and Computational Sciences, National Institute of Technology Karnataka, Surathkal, Mangalore 575025, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9189-9298","authenticated-orcid":false,"given":"Ioannis K.","family":"Argyros","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, Cameron University, Lawton, OK 73505, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2418-2336","authenticated-orcid":false,"given":"G. P.","family":"Pateel","sequence":"additional","affiliation":[{"name":"Department of Mathematical and Computational Sciences, National Institute of Technology Karnataka, Surathkal, Mangalore 575025, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1653","DOI":"10.3174\/ajnr.A5228","article-title":"Percutaneous spinal ablation in a sheep model: Protective capacity of an intact cortex, correlation of ablation parameters with ablation zone size, and correlation of postablation MRI and pathologic findings","volume":"38","author":"Wallace","year":"2017","journal-title":"Am. J. Neuroradiol."},{"key":"ref_2","first-page":"103","article-title":"Cervical spine injury: Clinical and medico-legal overview","volume":"128","author":"Zanza","year":"2023","journal-title":"Radiol. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1842","DOI":"10.1148\/rg.347130094","article-title":"Multidetector CT of blunt cervical spine trauma in adults","volume":"34","author":"Dreizin","year":"2014","journal-title":"Radiographics"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0079-6123(05)52034-X","article-title":"Overview: Autonomic dysfunction in spinal cord injury: Clinical presentation of symptoms and signs","volume":"152","author":"Karlsson","year":"2006","journal-title":"Prog. Brain Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.1007\/s00345-018-2301-z","article-title":"Epidemiology and pathophysiology of neurogenic bladder after spinal cord injury","volume":"36","author":"Hamid","year":"2018","journal-title":"World J. Urol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.ejrad.2018.10.025","article-title":"Basics of iterative reconstruction methods in computed tomography: A vendor-independent overview","volume":"109","author":"Stiller","year":"2018","journal-title":"Eur. J. Radiol."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Argyros, I.K. (2022). The Theory and Applications of Iteration Methods, CRC Press.","DOI":"10.1201\/9781003128915"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bate, I., Murugan, M., George, S., Senapati, K., Argyros, I.K., and Regmi, S. (2024). On Extending the Applicability of Iterative Methods for Solving Systems of Nonlinear Equations. Axioms, 13.","DOI":"10.3390\/axioms13090601"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1007\/s10958-020-04789-y","article-title":"Gauss\u2013Newton\u2013Kurchatov method for the solution of nonlinear least-squares problems","volume":"247","author":"Shakhno","year":"2020","journal-title":"J. Math. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e427","DOI":"10.1016\/j.wneu.2017.11.011","article-title":"Traumatic fractures of the cervical spine: Analysis of changes in incidence, cause, concurrent injuries, and complications among 488,262 patients from 2005 to 2013","volume":"110","author":"Passias","year":"2018","journal-title":"World Neurosurg."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Bhavya, M.B.S., Pujitha, M.V., and Supraja, G.L. (2022, January 2\u20133). Cervical Spine Fracture Detection Using Pytorch. Proceedings of the 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC), Tumkur, Karnataka.","DOI":"10.1109\/ICMNWC56175.2022.10031629"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1016\/j.acra.2018.02.018","article-title":"Deep learning in radiology","volume":"25","author":"McBee","year":"2018","journal-title":"Acad. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1002\/acm2.13001","article-title":"Faster RCNN-based detection of cervical spinal cord injury and disc degeneration","volume":"21","author":"Ma","year":"2020","journal-title":"J. Appl. Clin. Med Phys."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.3174\/ajnr.A7094","article-title":"CT cervical spine fracture detection using a convolutional neural network","volume":"42","author":"Small","year":"2021","journal-title":"Am. J. Neuroradiol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Paik, S., Park, J., Hong, J.Y., and Han, S.W. (2024). Deep learning application of vertebral compression fracture detection using mask R-CNN. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-67017-6"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"101238","DOI":"10.1016\/j.imu.2023.101238","article-title":"Vertebral compression fracture detection using imitation learning, patch based convolutional neural networks and majority voting","volume":"38","author":"Iyer","year":"2023","journal-title":"Informatics Med. Unlocked"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xu, F., Xiong, Y., Ye, G., Liang, Y., Guo, W., Deng, Q., Wu, L., Jia, W., Wu, D., and Chen, S. (2023). Deep learning-based artificial intelligence model for classification of vertebral compression fractures: A multicenter diagnostic study. Front. Endocrinol., 14.","DOI":"10.3389\/fendo.2023.1025749"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chen, H.Y., Hsu, B.W.Y., Yin, Y.K., Lin, F.H., Yang, T.H., Yang, R.S., Lee, C.K., and Tseng, V.S. (2021). Application of deep learning algorithm to detect and visualize vertebral fractures on plain frontal radiographs. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0245992"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1496","DOI":"10.1007\/s00330-021-08247-4","article-title":"A deep-learning model for identifying fresh vertebral compression fractures on digital radiography","volume":"32","author":"Chen","year":"2022","journal-title":"Eur. Radiol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ono, Y., Suzuki, N., Sakano, R., Kikuchi, Y., Kimura, T., Sutherland, K., and Kamishima, T. (2023). A deep learning-based model for classifying osteoporotic lumbar vertebral fractures on radiographs: A retrospective model development and validation study. J. Imaging, 9.","DOI":"10.3390\/jimaging9090187"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/s00198-023-06903-7","article-title":"External validation of a convolutional neural network algorithm for opportunistically detecting vertebral fractures in routine CT scans","volume":"35","author":"Nicolaes","year":"2024","journal-title":"Osteoporos. Int."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"El Kojok, Z., Al Khansa, H., Trad, F., and Chehab, A. (2025). Augmenting a spine CT scans dataset using VAEs, GANs, and transfer learning for improved detection of vertebral compression fractures. Comput. Biol. Med., 184.","DOI":"10.1016\/j.compbiomed.2024.109446"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"106831","DOI":"10.1016\/j.crad.2025.106831","article-title":"Automated vertebral compression fracture detection and quantification on opportunistic CT scans: A performance evaluation","volume":"83","author":"Guenoun","year":"2025","journal-title":"Clin. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"126946","DOI":"10.1016\/j.neucom.2023.126946","article-title":"Automated detection of vertebral fractures from X-ray images: A novel machine learning model and survey of the field","volume":"566","author":"Cheng","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e230034","DOI":"10.1148\/ryai.230034","article-title":"The RSNA cervical spine fracture CT dataset","volume":"5","author":"Lin","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1007\/s10278-017-9941-1","article-title":"Clinical applications of a CT window blending algorithm: RADIO (relative attenuation-dependent image overlay)","volume":"30","author":"Mandell","year":"2017","journal-title":"J. Digit. Imaging"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1002\/widm.1143","article-title":"Generating ensembles of heterogeneous classifiers using stacked generalization","volume":"5","author":"Sesmero","year":"2015","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S. (2016). Wide residual networks. arXiv.","DOI":"10.5244\/C.30.87"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_30","unstructured":"Tan, M., and Le, Q. (2019, January 9\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_32","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11\u201314). Identity mappings in deep residual networks. Proceedings of the Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part IV 14."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_34","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"105151","DOI":"10.1016\/j.engappai.2022.105151","article-title":"Ensemble deep learning: A review","volume":"115","author":"Ganaie","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1109\/ICNNB.2005.1614650","article-title":"A survey of neural network ensembles","volume":"Volume 1","author":"Zhao","year":"2005","journal-title":"Proceedings of the 2005 International Conference on Neural Networks and Brain"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/S0893-6080(05)80023-1","article-title":"Stacked generalization","volume":"5","author":"Wolpert","year":"1992","journal-title":"Neural Networks"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"46093","DOI":"10.1109\/ACCESS.2024.3382212","article-title":"A Novel Decision Level Class-Wise Ensemble Method in Deep Learning for Automatic Multi-Class Classification of HER2 Breast Cancer Hematoxylin-Eosin Images","volume":"12","author":"Pateel","year":"2024","journal-title":"IEEE Access"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Agapitos, A., O\u2019Neill, M., and Brabazon, A. (2014, January 6\u201311). Ensemble Bayesian model averaging in genetic programming. Proceedings of the 2014 IEEE Congress on Evolutionary Computation (CEC), Beijing, China.","DOI":"10.1109\/CEC.2014.6900567"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/S0022-2496(02)00028-7","article-title":"Tutorial on maximum likelihood estimation","volume":"47","author":"Myung","year":"2003","journal-title":"J. Math. Psychol."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Polikar, R. (2012). Ensemble learning. Ensemble Machine Learning: Methods and Applications, Springer.","DOI":"10.1007\/978-1-4419-9326-7_1"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Dietterich, T.G. (2000, January 21\u201323). Ensemble methods in machine learning. Proceedings of the International Workshop on Multiple Classifier Systems, Cagliari, Italy.","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Caruana, R., Niculescu-Mizil, A., Crew, G., and Ksikes, A. (2004, January 4\u20138). Ensemble selection from libraries of models. Proceedings of the Twenty-First International Conference on Machine Learning, Banff, AB, Canada.","DOI":"10.1145\/1015330.1015432"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/4\/181\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:58:16Z","timestamp":1760029096000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/4\/181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,21]]},"references-count":44,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["a18040181"],"URL":"https:\/\/doi.org\/10.3390\/a18040181","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,21]]}}}