Evaluation of a deep learning software for automated measurements on full‑leg standing radiographs
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Background. Precise lower limb measurements are crucial for assessing musculoskeletal health; fully automated solutions have the potential to enhance standardization and reproducibility of these measurements. This study compared the measurements performed by BoneMetrics (Gleamer, Paris, France), a commercial AI-based software, to expert manual measurements on anteroposterior full leg standing radiographs. Methods. A retrospective analysis was conducted on a dataset comprising consecutive anteroposterior full leg standing radiographs obtained from 4 imaging institutions. Key anatomical landmarks to define the hip-knee-ankle angle, pelvic obliquity, leg length, femoral length, and tibial length were annotated independently by two expert musculoskeletal radiologists and served as the ground truth. The performance of the AI was compared against these reference measurements using the mean absolute error, Bland-Altman analyses, and intraclass correlation coefficients. Results. A total of 175 anteroposterior full leg standing radiographs from 167 patients were included in the final dataset (mean age = 49.9 ± 23.6 years old; 103 women, 64 men). Mean absolute error values were 0.30° (95% CI: [0.28, 0.32]) for the hip-knee-ankle angle, 0.75 mm (95% CI: [0.60, 0.88]) for pelvic obliquity, 1.03 mm (95% CI: [0.91,1.14]) for leg length from the top of the femoral head, 1.45 mm (95% CI: [1.33, 1.60]) for leg length from the center of the femoral head, 0.95 mm (95% CI: [0.85, 1.04]) for femoral length from the top of the femoral head, 1.23 mm (95% CI: [1.12, 1.32]) for femoral length from the center of the femoral head, and 1.38 mm (95% CI: [1.21, 1.52]) for tibial length. The Bland-Altman analyses revealed no systematic bias across all measurements. Additionally, the software exhibited excellent agreement with the gold standard measurements with ICC values above 0.97 for all parameters. Conclusions. Automated measurements on anteroposterior full leg standing radiographs offer a reliable alternative to manual assessments. Use of AI in musculoskeletal radiology has the potential to support physicians in their daily practice without compromising patient care standards.
Abstract
Background. Precise lower limb measurements are crucial for assessing musculoskeletal health; fully automated solutions have the potential to enhance standardization and reproducibility of these measurements. This study compared the measurements performed by BoneMetrics (Gleamer, Paris, France), a commercial AI-based software, to expert manual measurements on anteroposterior full leg standing radiographs. Methods. A retrospective analysis was conducted on a dataset comprising consecutive anteroposterior full leg standing radiographs obtained from 4 imaging institutions. Key anatomical landmarks to define the hip-knee-ankle angle, pelvic obliquity, leg length, femoral length, and tibial length were annotated independently by two expert musculoskeletal radiologists and served as the ground truth. The performance of the AI was compared against these reference measurements using the mean absolute error, Bland-Altman analyses, and intraclass correlation coefficients. Results. A total of 175 anteroposterior full leg standing radiographs from 167 patients were included in the final dataset (mean age = 49.9 ± 23.6 years old; 103 women, 64 men). Mean absolute error values were 0.30° (95% CI: [0.28, 0.32]) for the hip-knee-ankle angle, 0.75 mm (95% CI: [0.60, 0.88]) for pelvic obliquity, 1.03 mm (95% CI: [0.91,1.14]) for leg length from the top of the femoral head, 1.45 mm (95% CI: [1.33, 1.60]) for leg length from the center of the femoral head, 0.95 mm (95% CI: [0.85, 1.04]) for femoral length from the top of the femoral head, 1.23 mm (95% CI: [1.12, 1.32]) for femoral length from the center of the femoral head, and 1.38 mm (95% CI: [1.21, 1.52]) for tibial length. The Bland-Altman analyses revealed no systematic bias across all measurements. Additionally, the software exhibited excellent agreement with the gold standard measurements with ICC values above 0.97 for all parameters. Conclusions. Automated measurements on anteroposterior full leg standing radiographs offer a reliable alternative to manual assessments. Use of AI in musculoskeletal radiology has the potential to support physicians in their daily practice without compromising patient care standards.
참고문헌 (51)
- Felson DT, "Valgus malalignment is a risk factor for lateral knee osteoarthritis incidence and progression : findings from MOST and the osteoarthritis initiative", Arthritis Rheum, 65(2), pp.355~362 (2013)
- Sharma L, "Varus and valgus alignment and incident and progressive knee osteoarthritis", Ann Rheum Dis, 69(11), pp.1940~1945 (2010)
- Sharma L, "The role of varus and valgus alignment in the initial development of knee cartilage damage by MRI : the MOST study", Ann Rheum Dis, 72(2), pp.235~240 (2013)
- Applebaum A, "Overview and spinal implications of leg length discrepancy : narrative review", Clin Orthop Surg, 13(2), pp.127~134 (2021)
- Kumar N, "How to interpret postoperative X-rays after total knee arthroplasty", Orthop Surg, 6(3), pp.179~186 (2014)
- van de Pol GJ, "The value of the intra-operative clinical mechanical axis measurement in open-wedge valgus high tibial osteotomies", Knee, 19(6), pp.933~938 (2012)
- Kim SH, "Reliability and validity of the femorotibial mechanical axis angle in primary total knee arthroplasty : navigation versus weight bearing or supine whole leg radiographs", Knee Surg Relat Res, 30(4), pp.326~333 (2018)
- Lin Y-H, "Mismatch between femur and tibia coronal alignment in the knee joint : classification of five lower limb types according to femoral and tibial mechanical alignment", BMC Musculoskelet Disord, 19(1), pp.411~ (2018)
- Sheehy L, "Does measurement of the anatomic axis consistently predict hip-knee-ankle angle (HKA) for knee alignment studies in osteoarthritis? Analysis of long limb radiographs from the multicenter osteoarthritis (MOST) study", Osteoarthritis Cartilage, 19(1), pp.58~64 (2011)
- Khalifa AA, "A protocol to systematic radiographic assessment of primary total knee arthroplasty", Orthop Res Rev, 13, pp.95~106 (2021)
- Tipton SC, "The assessment of limb length discrepancy before total hip arthroplasty", J Arthroplasty, 31(4), pp.888~892 (2016)
- Heaver C, "Measuring limb length discrepancy using pelvic radiographs : the most reproducible method", HIP Int, 23(4), pp.391~394 (2013)
- Vaishya R, "Inter-observer variability and its correlation to experience in measurement of lower limb mechanical axis on long leg radiographs", J Clin Orthop Trauma, 7(4), pp.260~264 (2016)
- "Define-AI Use Case Directory"[URL]
- Chen K, "Artificial intelligence in orthopedic radiography analysis : a narrative review", Diagnostics, 12(9), pp.2235~ (2022)
- Kijowski R, "Deep learning for lesion detection, progression, and prediction of musculoskeletal disease", J Magn Reson Imaging, 52(6), pp.1607~1619 (2020)
- Gyftopoulos S, "Artificial intelligence in musculoskeletal imaging : current status and future directions", Am J Roentgenol, 213(3), pp.506~513 (2019)
- Regnard N-E, "Assessment of performances of a deep learning algorithm for the detection of limbs and pelvic fractures, dislocations, focal bone lesions, and elbow effusions on trauma X-rays", Eur J Radiol, 154, pp.110447~ (2022)
- Guermazi A, "Improving radiographic fracture recognition performance and efficiency using artificial intelligence", Radiology, 302(3), pp.627~636 (2022)
- Canoni-Meynet L, "Added value of an artificial intelligence solution for fracture detection in the radiologist’s daily trauma emergencies workflow", Diagn Interv Imaging, 103(12), pp.594~600 (2022)
- Dallora AL, "Bone age assessment with various machine learning techniques : a systematic literature review and meta-analysis", PLoS ONE, 14(7), pp.e0220242~ (2019)
- Nguyen T, "High performance for bone age estimation with an artificial intelligence solution", Diagn Interv Imaging, 104(7), pp.330~336 (2023)
- Lee LS, "Artificial intelligence in diagnosis of knee osteoarthritis and prediction of arthroplasty outcomes : a review", Arthroplasty, 4(1), pp.16~ (2022)
- Ahmed SM, "A comprehensive survey on bone segmentation techniques in knee osteoarthritis research : from conventional methods to deep learning", Diagnostics, 12(3), pp.611~ (2022)
- Pan Y, "Evaluation of a computer-aided method for measuring the Cobb angle on chest X-rays", Eur Spine J, 28(12), pp.3035~3043 (2019)
- Korez R, "A deep learning tool for fully automated measurements of sagittal spinopelvic balance from X-ray images : performance evaluation", Eur Spine J, 29(9), pp.2295~2305 (2020)
- Jensen J, "A deep learning algorithm for radiographic measurements of the hip in adults—a reliability and agreement study", Diagnostics, 12(11), pp.2597~ (2022)
- Schwarz GM, "Can an artificial intelligence powered software reliably assess pelvic radiographs?", Int Orthop, 47(4), pp.945~953 (2023)
- Day J, "Evaluation of a Weightbearing CT artificial intelligence-based automatic measurement for the M1–M2 intermetatarsal angle in hallux valgus", Foot Ankle Int, 42(11), pp.1502~1509 (2021)
- Li T, "Feasibility study of hallux valgus measurement with a deep convolutional neural network based on landmark detection", Skeletal Radiol, 51(6), pp.1235~1247 (2022)
- Simon S, "Fully automated deep learning for knee alignment assessment in lower extremity radiographs : a cross-sectional diagnostic study", Skeletal Radiol, 51(6), pp.1249~1259 (2022)
- Archer H, "Deep learning generated lower extremity radiographic measurements are adequate for quick assessment of knee angular alignment and leg length determination", Skeletal Radiol, 53, pp.923~933 (2023)
- Stotter C, "Artificial intelligence-based analyses of varus leg alignment and after high tibial osteotomy show high accuracy and reproducibility", Knee Surg Sports Traumatol Arthrosc, 31, pp.5885~5895 (2023)
- Hau MYT, "Two-dimensional", three-dimensional EOS™ imaging is reliable and comparable to traditional X-ray imaging assessment of knee osteoarthritis aiding surgical management, 2020, pp.27(3), 970~979
- Simone Waldt KW, "Measurements and classifications in musculoskeletal radiology" (2013), Georg Thieme Verlag
- Birkenmaier C, "Distances and angles in standing long-leg radiographs : comparing conventional radiography, digital radiography, and EOS", Skeletal Radiol, 53(8), pp.1517~1528 (2024)
- Lu M-J, "Sample size for assessing agreement between two methods of measurement by bland-altman method", Int J Biostat, 12(2), pp.1~8 (2016)
- Ramazanian T, "Distribution and correlates of hip-knee-ankle angle in early osteoarthritis and preoperative total knee arthroplasty patients", J Arthroplasty, 37(6), pp.S170~S175 (2022)
- Thienpont E, "Bone morphotypes of the varus and valgus knee", Arch Orthop Trauma Surg, 137(3), pp.393~400 (2017)
- Koo TK, "A guideline of selecting and reporting intraclass correlation coefficients for reliability research", J Chiropr Med, 15(2), pp.155~163 (2016)
- Pagano S, "The role and efficiency of an AI-powered software in the evaluation of lower limb radiographs before and after total knee arthroplasty", J Clin Med, 12(17), pp.5498~ (2023)
- Schwarz GM, "Artificial intelligence enables reliable and standardized measurements of implant alignment in long leg radiographs with total knee arthroplasties", Knee Surg Sports Traumatol Arthrosc, 30(8), pp.2538~2547 (2022)
- Knutson GA, "Anatomic and functional leg-length inequality: a review and recommendation for clinical decision-making. Part I, anatomic leg-length inequality: prevalence, magnitude, effects and clinical significance", Chiropr Osteopat, 13(1), pp.11~ (2005)
- Mitterer JA, "Fully automated assessment of the knee alignment on long leg radiographs following corrective knee osteotomies in patients with valgus or varus deformities", Arch Orthop Trauma Surg, 144(3), pp.1029~1038 (2023)
- Rerucha CM, "Lower extremity abnormalities in children", Am Fam Physician, 96(4), pp.226~233 (2017)
- León HO, "Intercondylar notch stenosis in degenerative arthritis of the knee", Arthroscopy, 21(3), pp.294~302 (2005)
- Wada M, "Femoral intercondylar notch measurements in osteoarthritic knees", Rheumatology, 38(6), pp.554~558 (1999)
- Dubousset J, "A new 2D and 3D imaging approach to musculoskeletal physiology and pathology with low-dose radiation and the standing position : the EOS system", Bull Acad Natl Med, 189(2), pp.287~297 (2005)
- Schock J, "Automated analysis of alignment in long-leg radiographs by using a fully automated support system based on artificial intelligence", Radiol Artif Intell, 3(2), pp.e200198~ (2020)
- Erne F, "Automated artificial intelligence-based assessment of lower limb alignment validated on weight-bearing pre-and postoperative full-leg radiographs", Diagnostics, 12(11), pp.2679~ (2022)
- Kim SE, "Enhanced deep learning model enables accurate alignment measurement across diverse institutional imaging protocols", Knee Surg Relat Res, 36(1), pp.4~ (2024)