使用深度学习在CT上鉴别良性与恶性椎体骨折
本研究回顾性纳入433例脊柱CT患者(恶性骨折296例、良性骨折137例),由一名高年资放射科医生评估6项影像特征、三名低年资放射科医生作出诊断预测,并采用ResNet50深度学习网络以10折交叉验证评估诊断性能。结果显示软组织肿块和骨质破坏高度提示恶性,横行骨折线高度提示良性;ResNet50的逐切片诊断敏感度、特异度和准确率分别为0.90、0.79和85%,合并为逐患者诊断后分别为0.95、0.80和88%。
要点
- 软组织肿块和骨质破坏高度提示恶性椎体骨折,横行骨折线高度提示良性骨折。
- ResNet50逐切片诊断敏感度0.90、特异度0.79、准确率85%。
- 切片合并为逐患者诊断后敏感度0.95、特异度0.80、准确率88%。
核心结论
- ResNet50在CT鉴别良恶性椎体骨折中取得了良好准确率,未来可通过更多病例和优化方法进一步提升以用于临床实施。
研究设计与样本
- 回顾性研究,从脊柱CT图像数据库中选取433例患者(恶性骨折296例、良性骨折137例),采用ResNet50网络并以10折交叉验证评估诊断性能,阈值设为0.5。
关键影像表现/征象
- 软组织肿块和骨质破坏高度提示恶性椎体骨折。
- 横行骨折线高度提示良性椎体骨折。
诊断标准与关键数值
- ResNet50逐切片诊断敏感度0.90、特异度0.79、准确率85%。
- ResNet50切片合并为逐患者诊断后敏感度0.95、特异度0.80、准确率88%,恶性概率阈值0.5。
- 三名放射科医生(经验分别为5年、3年、1年)阅片准确率分别为99%、95.2%、92.8%。
临床应用与阅片要点
- ResNet50可用于CT上良恶性椎体骨折的鉴别诊断,逐患者诊断的敏感度0.95、特异度0.80、准确率88%。
局限性
- 原文指出需更多病例和优化方法以用于未来临床实施。
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
OBJECTIVES: To evaluate the performance of deep learning using ResNet50 in differentiation of benign and malignant vertebral fracture on CT.
METHODS: A dataset of 433 patients confirmed with 296 malignant and 137 benign fractures was retrospectively selected from our spinal CT image database. A senior radiologist performed visual reading to evaluate six imaging features, and three junior radiologists gave diagnostic prediction. A ROI was placed on the most abnormal vertebrae, and the smallest square bounding box was generated. The input channel into ResNet50 network was 3, including the slice with its two neighboring slices. The diagnostic performance was evaluated using 10-fold cross-validation. After obtaining the malignancy probability from all slices in a patient, the highest probability was assigned to that patient to give the final diagnosis, using the threshold of 0.5.
RESULTS: Visual features such as soft tissue mass and bone destruction were highly suggestive of malignancy; the presence of a transverse fracture line was highly suggestive of a benign fracture. The reading by three radiologists with 5, 3, and 1 year of experience achieved an accuracy of 99%, 95.2%, and 92.8%, respectively. In ResNet50 analysis, the per-slice diagnostic sensitivity, specificity, and accuracy were 0.90, 0.79, and 85%. When the slices were combined to ve per-patient diagnosis, the sensitivity, specificity, and accuracy were 0.95, 0.80, and 88%.
CONCLUSION: Deep learning has become an important tool for the detection of fractures on CT. In this study, ResNet50 achieved good accuracy, which can be further improved with more cases and optimized methods for future clinical implementation.
KEY POINTS: • Deep learning using ResNet50 can yield a high accuracy for differential diagnosis of benign and malignant vertebral fracture on CT. • The per-slice diagnostic sensitivity, specificity, and accuracy were 0.90, 0.79, and 85% in deep learning using ResNet50 analysis. • The slices combined with per-patient diagnostic sensitivity, specificity, and accuracy were 0.95, 0.80, and 88% in deep learning using ResNet50 analysis.
引用
- Li Y, Zhang Y, Zhang E, et al. Differential diagnosis of benign and malignant vertebral fracture on CT using deep learning. Eur Radiol. 2021. PMID: 33993335. doi:10.1007/s00330-021-08014-5
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。