Differentiating age and sex in vertebral body CT scans – Texture analysis versus deep learning approach

• Autorzy: Nurzynska Karolina , Piórkowski Adam , Strzelecki Michał , Kociołek Marcin , Banyś Robert Paweł , Obuchowicz Rafał

Identyfikatory

DOI

10.1016/j.bbe.2023.11.002

• Języki publikacji: EN

Abstrakty

EN

The automated analysis of computed tomography (CT) scans of vertebrae, for the purpose of determining an individual’s age and sex constitutes a vital area of research. Accurate assessment of bone age in children facilitates the monitoring of their growth and development. Moreover, the determination of both age and sex has significant relevance in various legal contexts involving human remains. We have built a dataset comprising CT scans of vertebral bodies from 166 patients of diverse genders, acquired during routine cardiac examinations. These images were rescaled to 8-bit data, and textural features were computed using the qMaZda software. The results were analysed employing conventional machine learning techniques and deep convolutional networks. The regression model, developed for the automatic estimation of bone age, accurately determined patients’ ages, with a mean absolute error of 3.14 years and R2 = 0.79. In the context of classifying patient gender through textural analysis supported by machine learning, we achieved an accuracy of 69 %. However, the application of deep convolutional networks for this task yielded a slightly lower accuracy of 59 %.

Słowa kluczowe

EN

texture analysis; bone age assessment; sex differentiation; forensic medicine

PL

analiza tekstury; zróżnicowanie płciowe; medycyna sądowa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2024
• Tom: Vol. 44, no. 1
• Strony: 20--30
• Opis fizyczny: Bibliogr. 52 poz., rys., tab., wykr.

Twórcy

autor

Nurzynska Karolina

• Department of Algorithmics and Software, Silesian University of Technology, Gliwice, Poland

autor

Piórkowski Adam

• Department of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, Kraków, Poland

autor

Strzelecki Michał

• Institute of Electronics, Lodz University of Technology, Łódź, Poland

autor

Kociołek Marcin

• Institute of Electronics, Lodz University of Technology, Łódź, Poland

autor

Banyś Robert Paweł

• Department of Radiology and Diagnostic Imaging, John Paul II Hospital, Kraków, Poland

autor

Obuchowicz Rafał

• Department of Diagnostic Imaging, Jagiellonian University Medical College, Kraków, Poland

Bibliografia

• [1] Auger JD, Frings N, Wu Y, Marty AG, Morgan EF. Trabecular architecture and mechanical heterogeneity effects on vertebral body strength. Curr Osteoporos Rep 2020 Dec;18(6):716-26.
• [2] Kužma M, Killinger Z, Jackuliak P, Vaňuga P, Hans D, Binkley N, Payer J. Pathophysiology of growth hormone secretion disorders and their impact on bone microstructure as measured by trabecular bone score. Physiological Research 2019 Nov 30;68(Suppl 2):S121-S129.
• [3] Bragg S, Bain J, Ramsetty A. Endocrine conditions in older adults: osteoporosis. FP Essentials 2018 Nov;474:11-9.
• [4] Cozadd AJ, Schroder LK, Switzer JA. Fracture risk assessment: An update. J Bone Joint Surg Am 2021 Jul 7;103(13):1238-46.
• [5] Kaiser J, Allaire B, Fein PM, Lu D, Jarraya M, Guermazi A, et al. Correspondence between bone mineral density and intervertebral disc degeneration across age and sex. Arch Osteoporos 2018;13:123.
• [6] Kaiser J, Allaire B, Fein PM, Lu D, Adams A, Kiel DP, et al. Heterogeneity and spatial distribution of intravertebral trabecular bone mineral density in the lumbar spine is associated with prevalent vertebral fracture. J Bone Miner Res 2020;35: 641-8.
• [7] LeVasseur CM, Pitcairn S, Shaw DWF, Lee JY, Anderst WJ. The effects of age, pathology, and fusion on cervical neural foramen area. J Orthop Res 2020;39(3): 671-9.
• [8] Galbusera F, Bassani T. The spine: A strong, stable, and flexible structure with biomimetics potential. Biomimetics (Basel) 2019;30:4(3):60.
• [9] Ruiz Santiago F, Láinez Ramos-Bossini AJ, Wáng YXJ, López ZD. The role of radiography in the study of spinal disorders. Quant Imaging Med Surg 2020;10 (12):2322-55.
• [10] Nouh MR. Imaging of the spine: Where do we stand? World J Radiol 2019;11(4): 55-61.
• [11] Kim GU, Chang MC, Kim TU, Lee GW. Diagnostic modality in spine disease: A review. Asian Spine Journal 2020;14(6):910-20.
• [12] Hussein AI, Louzeiro DT, Unnikrishnan GU, Morgan EF. Differences in trabecular microarchitecture and simplified boundary conditions limit the accuracy of quantitative computed tomography-based finite element models of vertebral failure. J Biomech Eng 2018;140.
• [13] Doyle E, Marquez-Grant N, Field L, Holmes T, Arthurs O, van Rijn RR, et al. Guidelines for best practice: Imaging for age estimation in the living. J Forensic Radiol Imaging 2019;16:38-49.
• [14] Halabi SS, Prevedello LM, Kalpathy-Cramer J, Mamonov AB, Bilbily A, Cicero M, et al. The RSNA paediatric bone age machine learning challenge. Radiology 2019; 290(2):498-503.
• [15] Salim I, Hamza AB. Ridge regression neural network for pediatric bone age assessment. Multimed Tools Appl 2021;80:30461-78.
• [16] Hirasen D, Pillay V, Viriri S, Gwetu M. Skeletal age estimation from hand radiographs using ensemble deep learning. Lecture Notes on Computer Science 2021;12725:173-83.
• [17] Zulkifley MA, Mohamed NA, Abdani SR, Kamari NAM, Moubark AM, Ibrahim AA. Intelligent bone age assessment: An automated system to detect a bone growth problem using convolutional neural networks with attention mechanism. Diagnostics 2021;11:765.
• [18] Liu B, Zhang Y, Chu M, Bai X, Zhou F. Bone age assessment based on rank-monotonicity enhanced ranking CNN. IEEE Access 2019;7:120976-83.
• [19] Marouf M, Siddiqi R, Bashir F, Vohra B. Automated hand X-ray based sex classification and bone age assessment using convolutional neural network. In: Proc. 2020 3rd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET). 2020.
• [20] Nabilach A, Sigit R, Fariza A, Madyono M. Human bone age estimation of carpal bone X-ray using residual network with batch normalization classification. Int J Informat Visual 2023;7(1).
• [21] Kasani AA, Sajedi H. Hand bone age estimation using divide and conquer strategy and lightweight convolutional neural networks. Eng Appl Artif Intel 2023;120: 105935.
• [22] Akhade R, Dhanorkar A, Chawhan J, Khanapuri J. Bone age estimation system using deep learning. Proc. 5th IEEE International Conference on Advances in Science and Technology. 2022.
• [23] Yang Z, Cong C, Pagnucco M, Song Y. Multi-scale multi-reception attention network for bone age assessment in X-ray images. Neural Netw 2023;158:249-57.
• [24] Hu M, Wang Y, Wang X, Fan W, Yang J, An N. A primary and secondary feature interactive learning network for bone age assessment. Biomed Signal Process Control 2023;85:105083.
• [25] Karargyris A, Kashyap S, Wu JT, Sharma A, Moradi M, Syeda-Mahmood T. Age prediction using a large chest X-ray dataset. Proc Medical Imaging 2019: Computer-Aided Diagnosis. 2019.
• [26] Nguyen QH, Nguyen BP, Nguyen MT, Chua MCH, Do TTT, Nghiem N. Bone age assessment and sex determination using transfer learning. Expert Syst Appl 2022; 200:116926.
• [27] Wang Ch, Wu Y, Wang Ch, Zhou X, Niu Y, Zhu Y, et al. Attention-based multiple-instance learning for pediatric bone age assessment with efficient and interpretable. Biomed Signal Process Control 2023;79:104028.
• [28] Štepanovský M, Buk Z, Pilmann Kotěrová A, Brůžek J, Bejdová Š, Techataweewan N, et al. Automated age-at-death estimation from 3D surface scans of the facies auricularis of the pelvic bone. Forensic Sci Int 2023;349:111765.
• [29] Iglovikov VI, Rakhlin A, Kalinin AA, Shvets AA. Pediatric bone age assessment using deep convolutional neural networks. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support; Springer: Cham, Switzerland, 2018:300-308.
• [30] Janczyk K, Rumiński J, Neumann T, Głowacka N, Wiśniewski P. Age prediction from low resolution, dual-energy X-ray images using convolutional neural networks. Appl Sci 2022;12:6608.
• [31] Obuchowicz R, Nurzynska K, Pierzchała M, Piórkowski A, Strzelecki M. Texture analysis for the bone age assessment from MRI images of adolescent wrists in boys. J Clin Med 2023;12(8):2762.
• [32] Štern D, Payer C, Urschler M. Automated age estimation from MRI volumes of the hand. Med Image Anal 2019;58:101538.
• [33] Lopatin O, Barszcz M, Bolechala F, Wozniak KJ. The fusion of ossification centers – A comparative review of radiographic and other imaging modalities of age assessment in living groups of children, adolescents, and young adults. Leg Med 2023;61:102185.
• [34] Rüeger E, Hutmacher N, Eichelberger P, Locherbach C, Albrecht S, Romann M. Ultrasound imaging-based methods for assessing biological maturity during adolescence and possible application in youth sport: A scoping review. Children 2022;9(12):1985.
• [35] Navega D, Coelho JDO, Cunha E, Curate F. DXAGE: A new method for age at death estimation based on femoral bone mineral density and artificial neural networks. J Forensic Sci 2018;63:497-503.
• [36] Caloro E, Cè M, Gibelli D, Palamenghi A, Martinenghi C, Oliva G, et al. Artificial intelligence (AI)-based systems for automatic skeletal maturity assessment through bone and teeth analysis: A revolution in the radiological workflow? Appl Sci 2023; 13(6):3860.
• [37] Oura P, Junno J-A, Hunt D, Lehenkari P, Tuukkanen J, Maijanen H. Deep learning in sex estimation from knee radiographs – A proof-of-concept study utilizing the Terry Anatomical Collection. Leg Med 2023;61:102211.
• [38] Nonthasaen P, Mahikul W, Chobpenthai Th, Achararit P. Sex estimation from Thai hand radiographs using convolutional neural networks. Forens Sci Int: Reports 2023;8:100332.
• [39] Sakaran R, Alias A, Woon ChK, Ku Mohd Noor KM, Zaidun NH, Zulkiflee NDI, Lin NW, Chung E. Sex estimation on thoracic vertebrae: A systematic review. Transl Res Anatomy. 2023:31:100243.
• [40] Maalman RS-E, Korpisah JK, Ampong K, Darko ND, Ennin IE, Kpordzih EE, Kumi MB, Ali MA, Adatara P. Sex estimation using proximal femoral parameters of adult population in the Volta region of Ghana. Forens Sci Int: Reports, 2023:7:100323.
• [41] Kumar Battan S, Sharma M, Gakhar G, Garg M, Singh P, Jasuja OP. Cranio-facial bones evaluation based on clinical CT data for sex determination in Northwest Indian population. Leg Med 2023;64:102292.
• [42] Thornton R, Hutchinson EF, Edkins AL. PCR based method for sex estimation from bone samples of unidentified South African fetal remains. Forens Sci Int: Reports 2021;4:100248.
• [43] Szczypinski PM, Klepaczko A, Kociolek M. QMaZda - Software tools for image analysis and pattern recognition. Proc. signal processing - algorithms, architectures, arrangements. SPA: and applications; 2017.
• [44] Abbasian Ardakani A, Bureau NJ, Ciaccio EJ, Acharya UR. Interpretation of radiomics features-A pictorial review. Comput Methods Programs Biomed 2022 Mar;215:106609. https://doi.org/10.1016/j.cmpb.2021.106609.
• [45] Kociołek M, Strzelecki M, Obuchowicz R. Does image normalization and intensity resolution impact texture classification? Comput Med Imaging Graph 2020;81: 101716.
• [46] Zangpo D, Uehara K, Kondo K, Kato M, Yoshimiya M, Nakatome M, et al. Estimating age at death by Hausdorff distance analyses of the fourth lumbar vertebral bodies using 3D postmortem CT images. Forensic Sci Med Pathol 2023. https://doi.org/10.1007/s12024-023-00620-7.
• [47] Oura P, Karppinen J, Niinimäki J, Junno JA. Sex estimation from dimensions of the fourth lumbar vertebra in Northern Finns of 20, 30, and 46 years of age. Forensic Sci Int 2018;290:350-6.
• [48] Decker SJ, Foley R, Hazelton JM, Ford JM. 3D analysis of computed tomography (CT)-derived lumbar spine models for the estimation of sex. JM Int J Legal Med 2019;133:1497-506.
• [49] Bozdag M, Karaman G. Virtual morphometry of the first lumbar vertebrae for estimation of sex using computed tomography data in the Turkish population. Cureus 2021;13(7):e16597.
• [50] Nussi AD, de Castro P, Lopes SL, Simioni De Rosa C, Perez Gomes JP, Ogawa CM, et al. In vivo study of cone beam computed tomography texture analysis of mandibular condyle and its correlation with gender and age. Oral Radiol 2023;39 (1):191-7.
• [51] Ling H, Yang X, Li P, Megalooikonomou V, Xu Y, Yang J. Cross gender-age trabecular texture analysis in cone beam CT. Dentomaxillofac Radiol 2014;43(4): 20130324.
• [52] Dieckmeyer M, Sollmann N, El Husseini M, Sekuboyina A, Löffler MT, Zimmer C, et al. Gender-, age- and region-specific characterization of vertebral bone microstructure through automated segmentation and 3D texture analysis of routine abdominal CT. Frontiers in Endocrinology (Lausanne) 2022;12:792760.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).