深度学习算法能够高精度地自动测量Cobb角。
Deep learning algorithm enables automated Cobb angle measurements with high accuracy.
作者信息
Hayashi Daichi, Regnard Nor-Eddine, Ventre Jeanne, Marty Vincent, Clovis Lauryane, Lim Ludovic, Nitche Nicolas, Zhang Zekun, Tournier Antoine, Ducarouge Alexis, Kompel Andrew J, Tannoury Chadi, Guermazi Ali
机构信息
Department of Radiology, Chobanian and Avedisian School of Medicine, Boston University, Boston, MA, USA.
Department of Radiology, Tufts Medical Center, Tufts University School of Medicine, 800 Washington Street, #299, Boston, MA, 02111, USA.
出版信息
Skeletal Radiol. 2025 Jul;54(7):1469-1478. doi: 10.1007/s00256-024-04853-7. Epub 2024 Dec 17.
OBJECTIVE
To determine the accuracy of automatic Cobb angle measurements by deep learning (DL) on full spine radiographs.
MATERIALS AND METHODS
Full spine radiographs of patients aged > 2 years were screened using the radiology reports to identify radiographs for performing Cobb angle measurements. Two senior musculoskeletal radiologists and one senior orthopedic surgeon independently annotated Cobb angles exceeding 7° indicating the angle location as either proximal thoracic (apices between T3 and T5), main thoracic (apices between T6 and T11), or thoraco-lumbar (apices between T12 and L4). If at least two readers agreed on the number of angles, location of the angles, and difference between comparable angles was < 8°, then the ground truth was defined as the mean of their measurements. Otherwise, the radiographs were reviewed by the three annotators in consensus. The DL software (BoneMetrics, Gleamer) was evaluated against the manual annotation in terms of mean absolute error (MAE).
RESULTS
A total of 345 patients were included in the study (age 33 ± 24 years, 221 women): 179 pediatric patients (< 22 years old) and 166 adult patients (22 to 85 years old). Fifty-three cases were reviewed in consensus. The MAE of the DL algorithm for the main curvature was 2.6° (95% CI [2.0; 3.3]). For the subgroup of pediatric patients, the MAE was 1.9° (95% CI [1.6; 2.2]) versus 3.3° (95% CI [2.2; 4.8]) for adults.
CONCLUSION
The DL algorithm predicted the Cobb angle of scoliotic patients with high accuracy.
目的
确定深度学习（DL）在全脊柱X光片上自动测量Cobb角的准确性。
材料与方法
使用放射学报告筛选年龄大于2岁患者的全脊柱X光片，以确定用于进行Cobb角测量的X光片。两名资深肌肉骨骼放射科医生和一名资深骨科医生独立标注超过7°的Cobb角，并将角的位置标注为近端胸椎（顶点在T3和T5之间）、主胸椎（顶点在T6和T11之间）或胸腰段（顶点在T12和L4之间）。如果至少两名读者在角的数量、角的位置以及可比角之间的差异<8°方面达成一致，则将真实值定义为他们测量值的平均值。否则，由三名注释者共同重新审查X光片。根据平均绝对误差（MAE）对DL软件（BoneMetrics，Gleamer）与手动标注进行评估。
结果
本研究共纳入345例患者（年龄33±24岁，女性221例）：179例儿科患者（<22岁）和166例成年患者（22至85岁）。53例病例进行了共同审查。DL算法对主曲率的MAE为2.6°（95%CI[2.0；3.3]）。对于儿科患者亚组，MAE为1.9°（95%CI[1.6；2.2]），而成人患者为3.3°（95%CI[2.2；4.8]）。
结论
DL算法能够高精度地预测脊柱侧弯患者的Cobb角。
Zotero 插件