Ortopedik Cerrahide Derin Öğrenme
Özet
Yapay zekânın II. Dünya Savaşı sonrasında Alan Turing ile başlayan ve günümüzde derin öğrenme ile evrişimsel sinir ağlarına (CNN) uzanan gelişim süreci, ortopedik cerrahide tanısal, prognostik ve klinik süreçlerin optimize edilmesinde kritik bir rol oynamaktadır. Ortopedi ve travmatoloji disiplininde derin öğrenme algoritmaları; manuel olarak sınıflandırılmış röntgen, BT ve MRG gibi geniş tıbbi görüntüleme veri tabanlarını işleyerek insan hata payını azaltmayı hedeflemektedir. Literatür incelendiğinde bu sistemlerin; ASA ve mFI-5 gibi geleneksel risk modellerinden daha yüksek doğrulukla postoperatif komplikasyonları öngörebildiği, kalça kırığı risk analizleri ile ekstremite kurtarma tahminlerinde üstün başarı sergilediği gösterilmiştir. Ayrıca ortopedik onkolojide sağkalım sürelerinin tahmini, hastanede kalış süreleri, tedavi maliyetlerinin hesaplanması ve hasta odaklı sonuç ölçütlerinin (PROM) analizinde etkin olarak kullanılmaktadır. Travma ve eklem cerrahisinde ise el, bilek, kalça ve gözden kaçabilecek skafoid kırıklarının tespitinde, osteoartrit evrelendirmesinde, yüksek tibial osteotomi için hasta seçiminde ve omurga cerrahisinde vertebra etiketleme ile dejeneratif değişikliklerin derecelendirilmesinde konunun uzmanı hekimlerle kıyaslanabilir veya daha üstün performans sergilemektedir. Sonuç olarak derin öğrenme, ortopedik cerrahide tanı ve tedavi planlamasını geliştirerek kaynakların verimli kullanılmasına olanak tanımakta ve gelecekte cerrahların bu teknolojik dönüşüme yönelik eğitim alması gerekliliğini ortaya koymaktadır.
The developmental process of artificial intelligence, which began with Alan Turing after World War II and has extended to deep learning and convolutional neural networks (CNN) today, plays a critical role in optimizing diagnostic, prognostic, and clinical processes in orthopedic surgery. In the discipline of orthopedics and traumatology, deep learning algorithms aim to reduce human error by processing large medical imaging databases such as manually classified X-rays, CT, and MRI. When the literature is reviewed, it is shown that these systems can predict postoperative complications with higher accuracy than traditional risk models like ASA and mFI-5, and display superior success in hip fracture risk analysis and limb salvage predictions. Additionally, they are effectively utilized in orthopedic oncology for predicting survival times, length of hospital stays, calculating treatment costs, and analyzing patient-reported outcome measures (PROM). In trauma and joint surgery, they exhibit performance comparable to or superior to expert physicians in detecting bone fractures that might be missed, such as in the hand, wrist, hip, and scaphoid, as well as in osteoarthritis grading, patient selection for high tibial osteotomy, and vertebra labeling and grading of degenerative changes in spine surgery. Consequently, deep learning improves diagnosis and treatment planning in orthopedic surgery, enabling efficient use of resources and revealing the necessity for surgeons to receive training on this technological transformation in the future.
Referanslar
Tappert, C. C. (2019, December). Who is the father of deep learning? In 2019 International Conference on Computational Science and Computational Intelligence (CSCI) (pp. 343-348). IEEE.
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., ... & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical image analysis, 42, 60-88.
Borjali A, Monson K, Raeymaekers B. Predicting the polyethylene wear rate in pin-on-disc experiments in the context of prosthetic hip implants: deriving a data-driven model using machine learning methods. Tribol Int. 2019; 133:101–110
Samuel, A. L. (1967). Some studies in machine learning using the game of checkers. II—Recent progress. IBM Journal of research and development, 11(6), 601-617.
Kijowski, R., Liu, F., Caliva, F. (2020). Deep learning for lesion detection, progression, and prediction of musculoskeletal disease. Journal of Magnetic Resonance Imaging, 52(6), 1607-1619.
Lu, Z., Pu, H., Wang, F., Hu, Z. (2017). The expressive power of neural networks: A view from the width. Advances in neural information processing systems, 6231-6239
Deng, L., & Yu, D. (2014). Deep learning: methods and applications. Foundations and trends® in signal processing, 7(3–4), 197-387.(dx.doi.org/10.1561/2000000039)
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444. (doı: 10.1038/nature14539)
Borjali A, Chen AF, Muratoglu OK, Learning in Orthopedics: How Do We Build Trust in the Machine? Healthcare Transformat 2020(doı: 10.1089/heat.2019.0006)
Salih B , Şahika B.Y , Uğur D. Derin öğrenme ile otomatik kalça kırığı tanısı. TOTBİD Dergisi 2022;21:32-39 (doi.org/10.5578/ totbid .dergisi.2022.07)
Berg, Hans E. Will Intelligent Machine Learning Revolutionmize Orthopedic Imaging? ActaOrthopaedica. 2017;88(6), 577–577. (doı: 10.1080/17453674.2017.1387732.)
Miller DD, Brown EW. Artificial Intelligence in Medical Practice: The Question to the Answer? Am J Med 2018; 131: 129-133 [PMID: 29126825 (doı: 10.1016/j.amjmed.2017.10.035)
Lalehzarian, S. P., Gowd, A. K., & Liu, J. N. (2021). Machine learning in orthopaedic surgery. World Journal of Orthopedics, 12(9), 685. (doı: 10.5312/wjo.v12.i9.685)
Irlbeck, T., Zwissler, B., & Bauer, A. ASA classification: Transition in the course of time and depiction in the literature. Anaesthesist [Internet]. 2017 [cited 2019 Dec 9]; 66 (1): 5-10. (doı: 10.1007/s00101-016-0246-4.)
Subramaniam, S., Aalberg, J. J., Soriano, R. P., & Divino, C. M. (2018). New 5-factor modified frailty index using American College of Surgeons NSQIP data. Journal of the American College of Surgeons, 226(2), 173-181.( doı: 10.1016/j.jamcollsurg.2017.11.005)
Harris AHS, Kuo AC, Weng Y, Trickey AW, Bowe T, Giori NJ. Can Machine Learning Methods Produce Accurate and Easy-to-use Prediction Models of 30-day Complications and Mortality After Knee or Hip Arthroplasty? Clin Orthop Relat Res 2019; 477: 452-460 (doi: 10.1097/CORR.0000000000000601)
Arvind, V., Kim, J. S., Oermann, E. K., Kaji, D., & Cho, S. K. (2018). Predicting surgical complications in adult patients undergoing anterior cervical discectomy and fusion using machine learning. Neurospine, 15(4), 329. ( doi: 10.14245/ns.1836248.124)
Kim, J. S., Arvind, V., Oermann, E (2018). Predicting surgical complications in patients undergoing elective adult spinal deformity procedures using machine learning. Spine deformity, 6(6), 762-770. (doi: 10.1016/j.jspd.2018.03.003)
Galassi, A., Martín-Guerrero, J. D., Villamor, E., Monserrat, C., & Rupérez, M. J. (2020). Risk assessment of hip fracture based on machine learning. Applied Bionics and Biomechanics, 2020. (doi: 10.1155/2020/8880786)
Devana, S. K., Shah, A. A., Lee, C., Roney, A. R., van der Schaar, M., & SooHoo, N. F. (2021). A novel, potentially universal machine learning algorithm to predict complications in total knee arthroplasty. Arthroplasty today, 10, 135-143.(doi: 10.1016/j.artd. 2021.06.020)
Gowd AK, Agarwalla A, Amin NH,. Construct validation of machine learning in the prediction of short-term postoperative complications following total shoulder arthroplasty. J Shoulder Elbow Surg 2019; 28: e410-e421 (doı: 10.1016/j.jse.2019.05.017)
Bevevino AJ, Dickens JF, Potter BK, Dworak T, Gordon W, Forsberg JA. A model to predict limb salvage in severe combat-related open calcaneus fractures. Clin Orthop Relat Res 2014; 472: 3002- 3009 (doı: 10.1007/s11999-013-3382-z)
Merrill, R. K., Ferrandino, R. M., Hoffman, R., Shaffer, G. W., & Ndu, A. (2019). Machine learning accurately predicts short-term outcomes following open reduction and internal fixation of ankle fractures. The Journal of Foot and Ankle Surgery, 58(3), 410-416.(DOI: 10.1053/j.jfas.2018.09.004)
Fontana MA, Lyman S, Sarker GK Can Machine Learning Algorithms Predict Which Patients Will Achieve Minimally Clinically Important Differences From Total Joint Arthroplasty? Clin Orthop Relat Res 2019; 477: 1267-1279 [doi: 10.1097/CORR.0000000000000687]
Menendez ME, Shaker J, Lawler SM, Ring D, Jawa A. Negative Patient-Experience Comments After Total Shoulder Arthroplasty. J Bone Joint Surg Am 2019; 101: 330-337 (DOI: 10.2106/JBJS.18.00695)
Thio QCBS, Karhade AV, Ogink PT, Raskin KA, De Amorim Bernstein K, Lozano Calderon SA, Schwab JH. Can Machine-learning Techniques Be Used for 5-year Survival Prediction of Patients With Chondrosarcoma? Clin Orthop Relat Res 2018; 476: 2040-2048 doi: 10.1097/CORR.0000000000000433]
Navarro SM, Wang EY, Haeberle HS, Mont MA, Krebs VE, Patterson BM, Ramkumar PN. Machine Learning and Primary Total Knee Arthroplasty: Patient Forecasting for a Patient-Specific Payment Model. J Arthroplasty 2018; 33: 3617-3623 (DOI: 10.1016/j.arth.2018.08.028)
Lalehzarian, S. P., Gowd, A. K., & Liu, J. N. (2021). Machine learning in orthopaedic surgery. World Journal of Orthopedics, 12(9), 685. (doı: 10.5312/wjo. v12.i9.685)
Olczak J, Fahlberg N, Maki A, Razavian AS, Jilert A, Stark A, Sköldenberg O, Gordon M. Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop 2017; 88: 581-586 [DOI: 10.1080/17453674.2017.1344459]
Mutasa, S., Varada, S., Goel, A., Wong, T. T., & Rasiej, M. J. (2020). Advanced deep learning techniques applied to automated femoral neck fracture detection and classification. Journal of Digital Imaging, 33(5), 1209-1217. (DOI: 10.1007/s10278-020-00364-8)
Yoon, A. P., Lee, Y. L., Kane, R. L., Kuo, C. F., Lin, C., & Chung, K. C. (2021). Development and validation of a deep learning model using convolutional neural networks to identify scaphoid fractures in radiographs. JAMA network open, 4(5), e216096-e216096.( DOI: 10.1001/jamanetworkopen.2021.6096)
Üreten, K., Sevinç, H. F., İğdeli, U., Onay, A., & Maraş, Y. (2022). Use of deep learning methods for hand fracture detection from plain hand radiographs. Turkish Journal of Trauma and Emergency Surgery, 28(2), 196-201.( DOI: 10.14744/tjtes.2020.06944)
Braun HJ, Gold GE. Diagnosis of osteoarthritis: imaging. Bone 2012; 51: 278-288 (DOI: 10.1016/j.bone.2011.11.019)
Xue Y, Zhang R, Deng Y, Chen K, Jiang T. A preliminary examination of the diagnostic value of deep learning in hip osteoarthritis. PLoS One 2017; 12: e0178992 ( DOI: 10.1371/journal.pone.0178992)
Ashinsky BG, Bouhrara M, Coletta CE, Lehallier B, Urish KL, Lin PC, Goldberg IG, Spencer RG. Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative. J Orthop Res 2017; 35: 2243-2250 (DOI: 10.1002/jor.23519)
Bayramoglu, N., Nieminen, M. T., & Saarakkala, S. (2021). Automated detection of patellofemoral osteoarthritis from knee lateral view radiographs using deep learning: data from the Multicenter Osteoarthritis Study (MOST). Osteoarthritis and Cartilage, 29(10), 1432-1447.( doi: 10.1016/j.joca.2021.06.011.)
Huang, Y., Liu, J., Wang, X. S., & Xu, H. J. (2020). Deep learning indications for high tibial osteotomy. Zhonghua wai ke za zhi [Chinese Journal of Surgery], 58(6), 420-424.(DOI: 10.3760/cma.j.cn112139-20200228-00149)
Oh E, Seo SW, Yoon YC, Kim DW, Kwon S, Yoon S. Prediction of pathologic femoral fractures in patients with lung cancer using machine learning algorithms: Comparison of computed tomographybased radiological features with clinical features vs without clinical features. J Orthop Surg (Hong Kong) 2017; 25: 2309499017716243 ( DOI: 10.1177/2309499017716243]
Zhao, Z., Pi, Y., Jiang, L., Xiang, Y., Wei, J., Yang, P., ... & Cai, H. (2020). Deep neural network based artificial intelligence assisted diagnosis of bone scintigraphy for cancer bone metastasis. Scientific reports, 10(1), 1-9.( DOI: 10.1038/s41598-020-74135-4)
Forsberg D, Sjöblom E, Sunshine JL. Detection and Labeling of Vertebrae in MR Images Using Deep Learning with Clinical Annotations as Training Data. J Digit Imaging 2017; 30: 406-412 (DOI: 10.1007/s10278-017-9945-x)
Pesteie M, Abolmaesumi P, Ashab HA, Lessoway VA, Massey S, Gunka V, Rohling RN. Real-time ultrasound image classification for spine anesthesia using local directional Hadamard features. Int J Comput Assist Radiol Surg 2015; 10: 901-912 (DOI: 10.1007/s11548-015-1202-59
Al-Helo S, Alomari RS, Ghosh S, Chaudhary V, Dhillon G, Al-Zoubi MB, Hiary H, Hamtini TM. Compression fracture diagnosis in lumbar: a clinical CAD system. Int J Comput Assist Radiol Surg 2013; 8: 461-469 (DOI: 10.1007/s11548-012-0796-0)
Jamaludin A, Lootus M, Kadir T, Zisserman A, Urban J, Battié MC, Fairbank J, McCall I; Genodisc Consortium. ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist. Eur Spine J 2017; 26: 1374-1383 (DOI: 10.1007/s00586-017-4956-3)
