From the Departments of Biomedical Informatics and Medical Education (B.C.C., Q.D., G.L.), University of Washington, Seattle, Washington.
Keck School of Medicine (J.R.), University of Southern California, Los Angeles, California.
AJNR Am J Neuroradiol. 2024 Oct 3;45(10):1512-1520. doi: 10.3174/ajnr.A8343.
Vertebral compression fractures may indicate osteoporosis but are underdiagnosed and underreported by radiologists. We have developed an ensemble of vertebral body (VB) segmentation models for lateral radiographs as a critical component of an automated, opportunistic screening tool. Our goal is to detect the approximate location of thoracic and lumbar VBs, including fractured vertebra, on lateral radiographs.
The Osteoporotic Fractures in Men Study (MrOS) data set includes spine radiographs of 5994 men aged ≥65 years from 6 clinical centers. Two segmentation models, U-Net and Mask-RCNN (Region-based Convolutional Neural Network), were independently trained on the MrOS data set retrospectively, and an ensemble was created by combining them. Primary performance metrics for VB detection success included precision, recall, and F1 score for object detection on a held-out test set. Intersection over union (IoU) and Dice coefficient were also calculated as secondary metrics of performance for the test set. A separate external data set from a quaternary health care enterprise was acquired to test generalizability, comprising diagnostic clinical radiographs from men and women aged ≥65 years.
The trained models achieved F1 score of U-Net = 83.42%, Mask-RCNN = 86.30%, and ensemble = 88.34% in detecting all VBs, and F1 score of U-Net = 87.88%, Mask-RCNN = 92.31%, and ensemble = 97.14% in detecting severely fractured vertebrae. The trained models achieved an average IoU per VB of 0.759 for U-Net and 0.709 for Mask-RCNN. The trained models achieved F1 score of U-Net = 81.11%, Mask-RCNN = 79.24%, and ensemble = 87.72% in detecting all VBs in the external data set.
An ensemble model combining predictions from U-Net and Mask-RCNN resulted in the best performance in detecting VBs on lateral radiographs and generalized well to an external data set. This model could be a key component of a pipeline to detect fractures on all vertebrae in a radiograph in an automated, opportunistic screening tool under development.
椎体压缩性骨折可能表明患有骨质疏松症，但放射科医生对此诊断不足且报告不足。我们已经开发了一个用于侧位 X 光片的椎体（VB）分割模型的集合，作为自动机会性筛查工具的关键组成部分。我们的目标是在侧位 X 光片上检测胸椎和腰椎 VB 的大致位置，包括骨折的椎体。
男性骨质疏松性骨折研究（MrOS）数据集包括来自 6 个临床中心的 5994 名年龄≥65 岁男性的脊柱 X 光片。两个分割模型，U-Net 和 Mask-RCNN（基于区域的卷积神经网络），分别在 MrOS 数据集上进行回顾性训练，然后通过组合它们创建一个集合。VB 检测成功率的主要性能指标包括在保留测试集上进行对象检测的精度、召回率和 F1 分数。交并比（IoU）和骰子系数也被计算为测试集的性能的次要指标。从一家四级医疗机构获得了一个单独的外部数据集进行泛化性测试，该数据集包括来自≥65 岁男性和女性的诊断临床 X 光片。
训练后的模型在检测所有 VB 时的 F1 分数分别为 U-Net = 83.42%、Mask-RCNN = 86.30%和集合 = 88.34%，在检测严重骨折的椎体时的 F1 分数分别为 U-Net = 87.88%、Mask-RCNN = 92.31%和集合 = 97.14%。训练后的模型在每个 VB 的平均 IoU 分别为 U-Net 的 0.759 和 Mask-RCNN 的 0.709。训练后的模型在外部数据集检测所有 VB 时的 F1 分数分别为 U-Net = 81.11%、Mask-RCNN = 79.24%和集合 = 87.72%。
结合 U-Net 和 Mask-RCNN 预测的集合模型在检测侧位 X 光片上的 VB 方面表现最佳，并很好地推广到外部数据集。该模型可以成为正在开发的自动机会性筛查工具中检测 X 光片上所有椎体骨折的管道的关键组成部分。
