头颈部骨MRI深度学习生成合成CT
本研究回顾性纳入39例头颈部骨MRI与CT检查的儿童和成人患者,配准后训练三种编码器-解码器模型将骨MRI转换为合成CT。Light_U-Net定量表现优于VGG-16模型;使用不同环境数据训练时性能下降,而将本地数据与其他医院、厂商或MRI技术数据联合扩增后性能提升。
要点
- Light_U-Net架构在骨MRI转合成CT的定量指标上优于VGG-16模型。
- 平均绝对误差损失带来更高的骨精确率,均方误差损失带来更高的骨召回率。
- 跨环境训练时性能下降,联合多医院、多厂商、多MR技术数据扩增后性能提升。
核心结论
- 研究优化了一个稳健的深度学习模型用于骨MRI转合成CT,在不同医院、厂商和MRI技术数据上训练时表现出良好性能和泛化性。
- 该方法有望促进下游图像处理并推动其进入临床实践。
研究设计与样本
- 回顾性研究,纳入39例头颈部骨MRI和CT检查的儿童与成人患者。
- 每例患者的MR与CT数据集采用多点仿射变换进行空间配准,生成配对MR与CT切片用于模型训练,采用4折交叉验证。
- 损失函数包括平均绝对误差、均方误差及加权平均;性能指标包括Pearson R、平均绝对误差、均方误差、骨精确率和骨召回率。
- 通过在不同条件下训练和验证考察模型泛化性。
诊断标准与关键数值
- 性能指标为Pearson R、平均绝对误差、均方误差、骨精确率和骨召回率,原文未给出各指标的具体数值。
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
BACKGROUND AND PURPOSE: Bone MR imaging techniques enable visualization of cortical bone without the need for ionizing radiation. Automated conversion of bone MR imaging to synthetic CT is highly desirable for downstream image processing and eventual clinical adoption. Given the complex anatomy and pathology of the head and neck, deep learning models are ideally suited for learning such mapping.
MATERIALS AND METHODS: This was a retrospective study of 39 pediatric and adult patients with bone MR imaging and CT examinations of the head and neck. For each patient, MR imaging and CT data sets were spatially coregistered using multiple-point affine transformation. Paired MR imaging and CT slices were generated for model training, using 4-fold cross-validation. We trained 3 different encoder-decoder models: Light_U-Net (2 million parameters) and VGG-16 U-Net (29 million parameters) without and with transfer learning. Loss functions included mean absolute error, mean squared error, and a weighted average. Performance metrics included Pearson R, mean absolute error, mean squared error, bone precision, and bone recall. We investigated model generalizability by training and validating across different conditions.
RESULTS: The Light_U-Net architecture quantitatively outperformed VGG-16 models. Mean absolute error loss resulted in higher bone precision, while mean squared error yielded higher bone recall. Performance metrics decreased when using training data captured only in a different environment but increased when local training data were augmented with those from different hospitals, vendors, or MR imaging techniques.
CONCLUSIONS: We have optimized a robust deep learning model for conversion of bone MR imaging to synthetic CT, which shows good performance and generalizability when trained on different hospitals, vendors, and MR imaging techniques. This approach shows promise for facilitating downstream image processing and adoption into clinical practice.
引用
- Bambach S, Ho ML. Deep Learning for Synthetic CT from Bone MRI in the Head and Neck. AJNR Am J Neuroradiol. 2022. PMID: 36920777. doi:10.3174/ajnr.A7588
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。