Tipik Servikal Omurlar Makine Öğrenimi Algoritmaları Kullanılarak Birbirinden Ayırt Edilebilir mi? Radyoanatomik Yeni Belirteçler

Year 2023, Volume: 15 Issue: 2, 210 - 218, 22.06.2023

Deniz Şenol , Yusuf Seçgin , Şeyma Toy , Serkan Öner , Zülal Öner

https://doi.org/10.18521/ktd.1177279

Cited By: 1

Abstract

Amaç: Bu çalışmanın amacı, bilgisayarlı tomografi (BT) görüntülerinde yapılan ölçümlerle makine algoritmaları (ML) kullanılarak çıplak gözle birbirinden ayrılamayan tipik servikal omurları ayırt etmek ve bu omurların farklılıklarını göstermektir.
Metod: Bu çalışma 134 (20-55 yaş arası) bireyin 536 tipik servikal vertebra BT görüntüleri incelenerek yapılmıştır. Servikal vertebraların koronal, aksiyal ve sagital kesitlerinde ölçümleri yapıldı. Parametrelerle 6 farklı kombinasyon (Grup 1: C3 – C4, Grup 2: C3 – C5, Grup 3: C3 – C6, Grup 4: C4 – C5, Grup 5: C4 – C6, Grup 6: C5 – C6) oluşturulmuştur. her bir omurun ve ML algoritmalarında analiz edildi. Analiz sonucunda Doğruluk (Acc), Matthews korelasyon katsayısı (Mcc), Özgüllük (Spe), Duyarlılık (Sen) değerleri elde edilmiştir.
Bulgular: Bu çalışma sonucunda en yüksek başarı Linear Discriminant Analysis (LDA) ve Logistic Regresyon (LR) algoritmaları ile elde edilmiştir. Grup 3 ve Grup 4'te en yüksek Acc oranı LDA ve LR algoritması ile 0.94, en yüksek Spe değeri Grup 5'te LDA ve LR algoritması ile 0.95, en yüksek Mcc değeri LDA ve LR algoritması ile 0.90 olarak bulundu. Grup 5'te en yüksek Sen değeri, Grup 3 ve 5'te LDA ve LR algoritması ile 0.94 olarak bulundu.
Sonuç: Sonuç olarak, tipik servikal vertebraların ML algoritmaları kullanılarak birbirinden net bir şekilde ayırt edilebildiği bulundu.

Keywords

Tipik servikal omurga, makine öğrenimi algoritmaları, bilgisayarlı tomografi

Can Typical Cervical Vertebrae Be Distinguished From One Another By Using Machine Learning Algorithms? Radioanatomic New Markers

Abstract

Objective: The aim of this study is to distinguish the typical cervical vertebrae that cannot be separated from one another with the naked eye by using machine algorithms (ML) with measurements made on computerized tomography (CT) images and to show the differences of these vertebrae.
Method: This study was conducted by examining the 536 typical cervical vertebrae CT images of 134 (between the ages of 20 and 55) individuals. Measurements of cervical vertebrae were made on coronal, axial and sagittal section. 6 different combinations (Group 1: C3 – C4, Group 2: C3 – C5, Group 3: C3 – C6, Group 4: C4 – C5, Group 5: C4 – C6, Group 6: C5 – C6) were formed with parameters of each vertebrae and they were analyzed in ML algorithms. Accuracy (Acc), Matthews correlation coefficient (Mcc), Specificity (Spe), Sensitivity (Sen) values were obtained as a result of the analysis.
Results: As a result of this study, the highest success was obtained with Linear Discriminant Analysis (LDA) and Logistic Regression (LR) algorithms. The highest Acc rate was found as 0.94 with LDA and LR algorithm in Groups 3 and Group 4, the highest Spe value was found as 0.95 with LDA and LR algorithm in Group 5, the highest Mcc value was found as 0.90 with LDA and LR algorithm in Group 5 and the highest Sen value was found as 0.94 with LDA and LR algorithm in Groups 3 and 5.
Conclusion: As a conclusion, it was found that typical cervical vertebrae can be clearly distinguished from one another by using ML algorithms.

Keywords

Typical cervical vertebrae, machine learning algorithms, computerized tomography

References

• 1. Saluja S, Patil S, Vasudeva N. Morphometric Analysis of Sub-axial Cervical Vertebrae and Its Surgical Implications. J Clin Diagn Res. 2015;9(11):AC01-4.
• 2. Desdicioglu K, Öztürk K, Çizmeci G, Malas M. Morphometric investigation of anatomic structures of vertebras and clinical evaluation: an anatomical study. SDU Saglık Bilimleri Dergisi. 2017;8(1):16-20.
• 3. Dweik A, Van den Brande E, Kossmann T, Maas AI. History of cervical spine surgery: from nihilism to advanced reconstructive surgery. Spinal Cord. 2013;51(11):809-14.
• 4. Wang T, Wang H, Liu S, Ding WY. Incidence of C5 nerve root palsy after cervical surgery: A meta-analysis for last decade. Medicine (Baltimore). 2017;96(45):e8560.
• 5. Neo M, Fujibayashi S, Miyata M, Takemoto M, Nakamura T. Vertebral artery injury during cervical spine surgery: a survey of more than 5600 operations. Spine (Phila Pa 1976). 2008;33(7):779-85.
• 6. Nottmeier EW, Pirris SM, Edwards S, Kimes S, Bowman C, Nelson KL. Operating room radiation exposure in cone beam computed tomography-based, image-guided spinal surgery: clinical article. J Neurosurg Spine. 2013;19(2):226-31.
• 7. Kothe R, Ruther W, Schneider E, Linke B. Biomechanical analysis of transpedicular screw fixation in the subaxial cervical spine. Spine (Phila Pa 1976). 2004;29(17):1869-75.
• 8. Ebraheim NA, Xu R, Knight T, Yeasting RA. Morphometric evaluation of lower cervical pedicle and its projection. Spine (Phila Pa 1976). 1997;22(1):1-6.
• 9. Bailey AS, Stanescu S, Yeasting RA, Ebraheim NA, Jackson WT. Anatomic relationships of the cervicothoracic junction. Spine (Phila Pa 1976). 1995;20(13):1431-9.
• 10. Bozbuga M, Ozturk A, Ari Z, Sahinoglu K, Bayraktar B, Cecen A. Morphometric evaluation of subaxial cervical vertebrae for surgical application of transpedicular screw fixation. Spine (Phila Pa 1976). 2004;29(17):1876-80.
• 11. Kayalioglu G, Erturk M, Varol T, Cezayirli E. Morphometry of the cervical vertebral pedicles as a guide for transpedicular screw fixation. Neurol Med Chir (Tokyo). 2007;47(3):102-7; discussion 7-8.
• 12. Sakamoto T, Neo M, Nakamura T. Transpedicular screw placement evaluated by axial computed tomography of the cervical pedicle. Spine (Phila Pa 1976). 2004;29(22):2510-4; discussion 5.
• 13. Shin EK, Panjabi MM, Chen NC, Wang JL. The anatomic variability of human cervical pedicles: considerations for transpedicular screw fixation in the middle and lower cervical spine. Eur Spine J. 2000;9(1):61-6.
• 14. Vara CS, Thompson GH. A cadaveric examination of pediatric cervical pedicle morphology. Spine (Phila Pa 1976). 2006;31(10):1107-12. 15. Yusof MI, Ming LK, Abdullah MS, Yusof AH. Computerized tomographic measurement of the cervical pedicles diameter in a Malaysian population and the feasibility for transpedicular fixation. Spine (Phila Pa 1976). 2006;31(8):E221-4.
• 16. Kirnaz S, Gebhard H, Wong T, Nangunoori R, Schmidt FA, Sato K, et al. Intraoperative image guidance for cervical spine surgery. Ann Transl Med. 2021;9(1):93.
• 17. Secgin Y, Oner Z, Turan MK, Oner S. Gender prediction with parameters obtained from pelvis computed tomography images and decision tree algorithm. Medicine Science International Medical Journal. 2021;10(2):356-61.
• 18. Serkan Ö, TURAN M, Zülal Ö. Estimation of gender by using decision tree, a machine learning algorithm, with patellar measurements obtained from MDCT images. Medical Records. 2021;3(1):1-9.
• 19. Deo RC. Machine Learning in Medicine. Circulation. 2015;132(20):1920-30.
• 20. Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine Learning for Medical Imaging. Radiographics. 2017;37(2):505-15.
• 21. Senol D, Bodur F, Seçgin Y, Bakıcı R, Sahin N, Toy S, et al. Sex prediction with morphometric measurements of first and fifth metatarsal and phalanx obtained from X-ray images by using machine learning algorithms. Folia Morphologica. 2022.
• 22. Reges O, Krefman AE, Hardy ST, Yano Y, Muntner P, Lloyd-Jones DM, et al. Decision Tree-Based Classification for Maintaining Normal Blood Pressure Throughout Early Adulthood and Middle Age: Findings From the Coronary Artery Risk Development in Young Adults (CARDIA) Study. American journal of hypertension. 2021;34(10):1037-41.
• 23. Sarica A, Cerasa A, Quattrone A. Random forest algorithm for the classification of neuroimaging data in Alzheimer's disease: a systematic review. Frontiers in aging neuroscience. 2017;9:329.
• 24. DeGregory K, Kuiper P, DeSilvio T, Pleuss J, Miller R, Roginski J, et al. A review of machine learning in obesity. Obesity reviews. 2018;19(5):668-85.
• 25. Perfecto-Avalos Y, Garcia-Gonzalez A, Hernandez-Reynoso A, Sánchez-Ante G, Ortiz-Hidalgo C, Scott S-P, et al. Discriminant analysis and machine learning approach for evaluating and improving the performance of immunohistochemical algorithms for COO classification of DLBCL. Journal of translational medicine. 2019;17(1):1-12.
• 26. Toy S, Secgin Y, Oner Z, Turan MK, Oner S, Senol D. A study on sex estimation by using machine learning algorithms with parameters obtained from computerized tomography images of the cranium. Scientific Reports. 2022;12(1):1-11.
• 27. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: Machine learning in Python. the Journal of machine Learning research. 2011;12:2825-30.
• 28. Jeanneret B, Gebhard JS, Magerl F. Transpedicular screw fixation of articular mass fracture-separation: results of an anatomical study and operative technique. J Spinal Disord. 1994;7(3):222-9.
• 29. Xu R, Kang A, Ebraheim NA, Yeasting RA. Anatomic relation between the cervical pedicle and the adjacent neural structures. Spine (Phila Pa 1976). 1999;24(5):451-4.
• 30. Jones EL, Heller JG, Silcox DH, Hutton WC. Cervical pedicle screws versus lateral mass screws. Anatomic feasibility and biomechanical comparison. Spine (Phila Pa 1976). 1997;22(9):977-82.
• 31. Kotani Y, Cunningham BW, Abumi K, McAfee PC. Biomechanical analysis of cervical stabilization systems. An assessment of transpedicular screw fixation in the cervical spine. Spine (Phila Pa 1976). 1994;19(22):2529-39.
• 32. Prameela M, Prabhu LV, Murlimanju B, Pai MM, Rai R-l, Kumar CG. Anatomical dimensions of the typical cervical vertebrae and their clinical implications. Eur j anat. 2020:9-15.
• 33. Gupta R, Kapoor K, Sharma A, Kochhar S, Garg R. Morphometry of typical cervical vertebrae on dry bones and CT scan and its implications in transpedicular screw placement surgery. Surg Radiol Anat. 2013;35(3):181-9.
• 34. Ugur HC, Attar A, Uz A, Tekdemir I, Egemen N, Caglar S, et al. Surgical anatomic evaluation of the cervical pedicle and adjacent neural structures. Neurosurgery. 2000;47(5):1162-8; discussion 8-9.
• 35. Evangelopoulos D, Kontovazenitis P, Kouris S, Zlatidou X, Benneker L, Vlamis J, et al. Computerized tomographic morphometric analysis of the cervical spine. Open Orthop J. 2012;6:250-4.
• 36. Ludwisiak K, Podgorski M, Biernacka K, Stefanczyk L, Olewnik L, Majos A, et al. Variation in the morphology of spinous processes in the cervical spine - An objective and parametric assessment based on CT study. PLoS One. 2019;14(6):e0218885.