两阶段深度学习算法模拟放射科医生搜索模式检测细微骨折
本研究基于斯坦福MURA和LERA数据集及公共数据,构建两阶段深度卷积神经网络系统模拟放射科医生搜索模式,用于检测三角骨撕脱骨折和Segond骨折。两阶段系统在交叉验证中AUC分别为0.959和0.989,均优于单阶段分类器(AUC 0.860和0.909,P值分别为0.0086和0.0074),并在外部测试集上表现良好。
要点
- 两阶段系统(先裁剪感兴趣区再分类)检测三角骨撕脱骨折和Segond骨折的AUC分别为0.959和0.989。
- 单阶段分类器检测相同骨折的AUC分别为0.860和0.909,两阶段系统均显著更优(P=0.0086和P=0.0074)。
- 两阶段系统在外部测试集上泛化良好,提示聚焦特定图像区域有助于发现易漏诊的细微骨折。
关键影像表现/征象
- 梯度类激活映射用于检查在决定最终分类中重要性更高的图像区域。
- 物体检测器在所有验证和测试图像中准确裁剪了感兴趣区。
诊断标准与关键数值
- 两阶段系统检测三角骨撕脱骨折的交叉验证AUC为0.959,单阶段分类器为0.860(P=0.0086)。
- 两阶段系统检测Segond骨折的交叉验证AUC为0.989,单阶段分类器为0.909(P=0.0074)。
- 两阶段系统检测三角骨撕脱骨折和Segond骨折的交叉验证准确率分别为90.8%和92.5%。
临床应用与阅片要点
- 两阶段系统首先裁剪背侧三角骨或胫骨外侧髁区域,再对裁剪图像进行分类,模拟放射科医生先定位后判读的搜索模式。
- 聚焦特定图像区域似乎有助于检测可能被遗漏的细微骨折。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To develop and evaluate a two-stage deep convolutional neural network system that mimics a radiologist's search pattern for detecting two small fractures: triquetral avulsion fractures and Segond fractures.
MATERIALS AND METHODS: We obtained 231 lateral wrist radiographs and 173 anteroposterior knee radiographs from the Stanford MURA and LERA datasets and the public domain to train and validate a two-stage deep convolutional neural network system: (1) object detectors that crop the dorsal triquetrum or lateral tibial condyle, trained on control images, followed by (2) classifiers for triquetral and Segond fractures, trained on a 1:1 case:control split. A second set of classifiers was trained on uncropped images for comparison. External test sets of 50 lateral wrist radiographs and 24 anteroposterior knee radiographs were used to evaluate generalizability. Gradient-class activation mapping was used to inspect image regions of greater importance in deciding the final classification.
RESULTS: The object detectors accurately cropped the regions of interest in all validation and test images. The two-stage system achieved cross-validated area under the receiver operating characteristic curve values of 0.959 and 0.989 on triquetral and Segond fractures, compared with 0.860 (p = 0.0086) and 0.909 (p = 0.0074), respectively, for a one-stage classifier. Two-stage cross-validation accuracies were 90.8% and 92.5% for triquetral and Segond fractures, respectively.
CONCLUSION: A two-stage pipeline increases accuracy in the detection of subtle fractures on radiographs compared with a one-stage classifier and generalized well to external test data. Focusing attention on specific image regions appears to improve detection of subtle findings that may otherwise be missed.
引用
- Ren M, Yi PH. Deep learning detection of subtle fractures using staged algorithms to mimic radiologist search pattern. Skeletal Radiol. 2021. PMID: 33576861. doi:10.1007/s00256-021-03739-2
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。