Deep Learning?based Angiogram Generation Model for Cerebral Angiography without Misregistration Artifacts
Deep Learning?based Angiogram Generation Model for Cerebral Angiography without Misregistration Artifacts
复制标题
基于深度学习的脑血管造影血管造影生成模型，无配准不良伪影
DOI：
10.1148/radiol.2021203692
复制
发表时间：
2021
期刊：
影响因子：
19.7
通讯作者：
Miki Yukio
中科院分区：
文献类型：
--
作者：
Ueda Daiju;Katayama Yutaka;Yamamoto Akira;Ichinose Tsutomu;Arima Hironori;Watanabe Yusuke;Walston Shannon L.;Tatekawa Hiroyuki;Takita Hirotaka;Honjo Takashi;Shimazaki Akitoshi;Kabata Daijiro;Ichida Takao;Goto Takeo;Miki Yukio
背景数字减影血管造影（DSA）通过从动态血管造影图像中减去掩模图像来生成图像。然而，在这方面，患者运动引起的配准不良伪影可能导致DSA图像不清晰，从而中断手术。目的为了训练和验证基于深度学习（DL）的模型，以生成DSA-材料与方法采用回顾性模型建立和验证研究方法，对动态脑血管造影图像和DSA图像对进行连续性分析，从2019年1月到2019年4月收集。显示配准不良的血管造影片首先由两名放射科医生按患者进行分离，并分类到配准不良测试数据集中。将非配准错误血管造影片按每例患者8：1的比例分为开发和外部测试数据集。将开发数据集按每例患者3：1的比例分为训练和验证数据集。通过使用训练数据集创建DL模型，使用验证数据集进行调整，然后使用外部测试数据集进行定量评估，并使用配准不良测试数据集进行视觉评估。定量评价使用峰值信噪比（PSNR）和结构相似性（SSIM）与混合线性模型。通过使用一个数字rating scale.ResultsThe训练，验证，nonmisregistration测试，和misregistration测试数据集包括10 751，2784，1346，和711配对图像收集40例患者（平均年龄，62岁± 11 [标准差]; 33名妇女）进行视觉评价。在定量评价中，DL生成的血管造影片显示平均PSNR值为40.2 dB ± 4.05，平均SSIM值为0.97 ± 0.02，表明与配对DSA图像具有较高的一致性。在视觉评估中，DL生成的血管造影片的中位数评分与所有24个序列的原始DSA图像相似或更好。ConclusionThe deep learning based model提供了临床有用的脑血管造影片，不含直接来自动态血管造影片的临床显著伪影。
BackgroundDigital subtraction angiography (DSA) generates an image by subtracting a mask image from a dynamic angiogram. However, patient movement–caused misregistration artifacts can result in unclear DSA images that interrupt procedures.PurposeTo train and to validate a deep learning (DL)–based model to produce DSA-like cerebral angiograms directly from dynamic angiograms and then quantitatively and visually evaluate these angiograms for clinical usefulness.Materials and MethodsA retrospective model development and validation study was conducted on dynamic and DSA image pairs consecutively collected from January 2019 through April 2019. Angiograms showing misregistration were first separated per patient by two radiologists and sorted into the misregistration test data set. Nonmisregistration angiograms were divided into development and external test data sets at a ratio of 8:1 per patient. The development data set was divided into training and validation data sets at ratio of 3:1 per patient. The DL model was created by using the training data set, tuned with the validation data set, and then evaluated quantitatively with the external test data set and visually with the misregistration test data set. Quantitative evaluations used the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) with mixed liner models. Visual evaluation was conducted by using a numerical rating scale.ResultsThe training, validation, nonmisregistration test, and misregistration test data sets included 10 751, 2784, 1346, and 711 paired images collected from 40 patients (mean age, 62 years ± 11 [standard deviation]; 33 women). In the quantitative evaluation, DL-generated angiograms showed a mean PSNR value of 40.2 dB ± 4.05 and a mean SSIM value of 0.97 ± 0.02, indicating high coincidence with the paired DSA images. In the visual evaluation, the median ratings of the DL-generated angiograms were similar to or better than those of the original DSA images for all 24 sequences.ConclusionThe deep learning–based model provided clinically useful cerebral angiograms free from clinically significant artifacts directly from dynamic angiograms.Published under a CC BY 4.0 license.