PDF(Pubmed)
Abstract：
OBJECTIVE: This study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise.
METHODS: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics-compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)-from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model.
RESULTS: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees.
CONCLUSIONS: The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.
METHODS: Using the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics-compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)-from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model.
RESULTS: The DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees.
CONCLUSIONS: The DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.
摘要：
目的：本研究旨在开发和验证一种用于定量测量胸腰椎（TL）骨折特征的深度学习（DL）算法，并评估其在不同临床专业知识水平上的疗效。
方法：使用预训练的基于掩码区域的卷积神经网络模型，最初开发用于椎体分割和骨折检测，我们对模型进行了微调，并增加了一个新的测量骨折指标的模块——压缩率(CR)，Cobb角(CA),加德纳角(GA),和矢状指数（SI）-来自腰椎侧位X光片。这些指标来自3名放射科医生的六点标记，形成地面真相（GT）。培训使用了1,000张非骨折和318张骨折X光片，而验证使用了213个内部和200个外部断裂的射线照片。使用组内相关系数针对GT评估了DL算法量化断裂特征的准确性。此外,4位具有不同专业知识水平的读者，包括受训人员和一名脊柱主治医生，在有和没有DL辅助的情况下进行测量，并将其结果与GT和DL模型进行了比较。
结果：对于CR，DL算法与GT表现出良好的一致性，CA,GA,和SI在内部（分别为0.860、0.944、0.932和0.779）和外部（分别为0.836、0.940、0.916和0.815）验证中。DL辅助测量显着改善了大多数测量值，特别是对于学员。
结论：DL算法已被验证为使用射线照片定量TL断裂特征的准确工具。DL辅助测量有望加快诊断过程并增强可靠性，特别是受益于经验较少的临床医生。
方法：使用预训练的基于掩码区域的卷积神经网络模型，最初开发用于椎体分割和骨折检测，我们对模型进行了微调，并增加了一个新的测量骨折指标的模块——压缩率(CR)，Cobb角(CA),加德纳角(GA),和矢状指数（SI）-来自腰椎侧位X光片。这些指标来自3名放射科医生的六点标记，形成地面真相（GT）。培训使用了1,000张非骨折和318张骨折X光片，而验证使用了213个内部和200个外部断裂的射线照片。使用组内相关系数针对GT评估了DL算法量化断裂特征的准确性。此外,4位具有不同专业知识水平的读者，包括受训人员和一名脊柱主治医生，在有和没有DL辅助的情况下进行测量，并将其结果与GT和DL模型进行了比较。
结果：对于CR，DL算法与GT表现出良好的一致性，CA,GA,和SI在内部（分别为0.860、0.944、0.932和0.779）和外部（分别为0.836、0.940、0.916和0.815）验证中。DL辅助测量显着改善了大多数测量值，特别是对于学员。
结论：DL算法已被验证为使用射线照片定量TL断裂特征的准确工具。DL辅助测量有望加快诊断过程并增强可靠性，特别是受益于经验较少的临床医生。
