基于深度学习的口腔颌面部金属伪影消除与临床验证
测试集RMSE为0.015–0.024、SSIM为0.957–0.965;220例临床病例改良利克特量表总体得分3.73±1.13,效果较满意。
要点
- GAN模型可有效消除充填体、冠类、钛板钛钉、托槽及金属异物伪影。
- 测试集定量指标RMSE和SSIM在5类金属间差异无统计学意义。
- 临床病例主观评分整体较满意,两名评价者间一致性高(ICC=0.972)。
核心结论
- 构建的CT金属伪影消除GAN模型可有效去除金属伪影干扰并提升图像质量。
研究设计与样本
- 金属伪影涵盖充填体、冠类、钛板钛钉类、托槽类、金属异物类5种。
- 数据集随机分为训练集800对和测试集200对,训练集用于训练GAN模型,测试集用于评估性能。
- 用训练好的模型对剩余220例临床金属伪影CT数据进行消除,由2名高年资主治医师用改良利克特量表评价。
主要发现
- 测试集中充填体、冠类、钛板钛钉类、托槽类和金属异物类的RMSE分别为0.018±0.004、0.023±0.007、0.015±0.003、0.019±0.004、0.024±0.008(F=1.29,P=0.274)。
- 上述5类的SSIM分别为0.963±0.023、0.961±0.023、0.965±0.013、0.958±0.022、0.957±0.026(F=2.22,P=0.069)。
- 2名评价者评分的组内相关系数为0.972。
- 220例临床病例的改良利克特量表总体得分为(3.73±1.13)分。
- 充填体、冠类、钛板钛钉类、托槽类和金属异物类的改良利克特量表得分分别为(3.68±1.13)、(3.67±1.16)、(3.97±1.03)、(3.83±1.14)、(3.33±1.12)分(F=1.44,P=0.145)。
临床怎么用
- 该GAN模型可用于口腔颌面部CT中5类常见金属修复材料或异物的伪影消除,提升图像可读性。
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)。
原文
Objective: To construct a kind of neural network for eliminating the metal artifacts in CT images by training the generative adversarial networks (GAN) model, so as to provide reference for clinical practice. Methods: The CT data of patients treated in the Department of Radiology, West China Hospital of Stomatology, Sichuan University from January 2017 to June 2022 were collected. A total of 1 000 cases of artifact-free CT data and 620 cases of metal artifact CT data were obtained, including 5 types of metal restorative materials, namely, fillings, crowns, titanium plates and screws, orthodontic brackets and metal foreign bodies. Four hundred metal artifact CT data and 1 000 artifact-free CT data were utilized for simulation synthesis, and 1 000 pairs of simulated artifacts and metal images and simulated metal images (200 pairs of each type) were constructed. Under the condition that the data of the five metal artifacts were equal, the entire data set was randomly (computer random) divided into a training set (800 pairs) and a test set (200 pairs). The former was used to train the GAN model, and the latter was used to evaluate the performance of the GAN model. The test set was evaluated quantitatively and the quantitative indexes were root-mean-square error (RMSE) and structural similarity index measure (SSIM). The trained GAN model was employed to eliminate the metal artifacts from the CT data of the remaining 220 clinical cases of metal artifact CT data, and the elimination results were evaluated by two senior attending doctors using the modified LiKert scale. Results: The RMSE values for artifact elimination of fillings, crowns, titanium plates and screws, orthodontic brackets and metal foreign bodies in test set were 0.018±0.004, 0.023±0.007, 0.015±0.003, 0.019±0.004, 0.024±0.008, respectively (F=1.29, P=0.274). The SSIM values were 0.963±0.023, 0.961±0.023, 0.965±0.013, 0.958±0.022, 0.957±0.026, respectively (F=2.22, P=0.069). The intra-group correlation coefficient of 2 evaluators was 0.972. For 220 clinical cases, the overall score of the modified LiKert scale was (3.73±1.13), indicating a satisfactory performance. The scores of modified LiKert scale for fillings, crowns, titanium plates and screws, orthodontic brackets and metal foreign bodies were (3.68±1.13), (3.67±1.16), (3.97±1.03), (3.83±1.14), (3.33±1.12), respectively (F=1.44, P=0.145). Conclusions: The metal artifact reduction GAN model constructed in this study can effectively remove the interference of metal artifacts and improve the image quality. 目的: 通过训练生成对抗网络(generative adversarial networks,GAN)模型,构建一种用于消除CT图像金属伪影的神经网络,以期为临床提供参考。 方法: 收集2017年1月至2022年6月四川大学华西口腔医院影像科就诊患者的CT资料,共纳入1 000例无伪影CT数据和620例金属伪影CT数据,包含充填体、冠类、钛板钛钉类、托槽类、金属异物类5种。将400例金属伪影CT数据和1 000例无伪影CT数据用于仿真合成,构建出1 000对配对的模拟金属及伪影图像和模拟金属图像(每种200对)。在保证5种金属伪影数据相等的情况下,将整个数据集随机(计算机随机)分为训练集(800对)和测试集(200对),前者用于训练GAN模型,后者用于评估GAN模型性能。定量评价测试集均方根误差(root-mean-square error,RMSE)和结构相似性(structural similarity index measure,SSIM)。用训练好的GAN模型对剩余的220例临床病例颌面部CT图像金属伪影进行消除,并由2名高年资主治医师分别使用改良利克特量表对消除结果进行评价。 结果: 测试集中充填体、冠类、钛板钛钉类、托槽类和金属异物类伪影消除的RMSE值分别为0.018±0.004、0.023±0.007、0.015±0.003、0.019±0.004、0.024±0.008(F=1.29,P=0.274),SSIM值分别为0.963±0.023、0.961±0.023、0.965±0.013、0.958±0.022、0.957±0.026(F=2.22,P=0.069),总体差异均无统计学意义。2名评价者评分的组内相关系数为0.972,对于220例临床病例,改良利克特量表的总体得分为(3.73±1.13)分,整体消除效果较满意。充填体、冠类、钛板钛钉类、托槽类和金属异物类的改良利克特量表得分分别为(3.68±1.13)、(3.67±1.16)、(3.97±1.03)、(3.83±1.14)、(3.33±1.12)分,总体差异无统计学意义(F=1.44,P=0.145)。 结论: 本项研究构建的CT图像金属伪影消除GAN模型,可有效去除金属伪影的干扰,提升图像质量。.
引用
- Zeng W, Zhou SL, Guo JX, et al. [Metal artifact reduction and clinical verification in oral and maxillofacial region based on deep learning]. Zhonghua Kou Qiang Yi Xue Za Zhi. 2023. PMID: 37271998. doi:10.3760/cma.j.cn112144-20230302-00067
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。