Singhrao Kamal, Fu Jie, Parikh Neil R, Mikaeilian Argin G, Ruan Dan, Kishan Amar U, Lewis John H
Department of Radiation Oncology, University of California, Los Angeles, Los Angeles, CA, 90095, USA.
Department of Radiation Oncology, Cedars-Sinai Medical Center, Los Angeles, CA, 90048, USA.
Med Phys. 2020 Dec;47(12):6405-6413. doi: 10.1002/mp.14498. Epub 2020 Oct 19.
Clinical sites utilizing magnetic resonance imaging (MRI)-only simulation for prostate radiotherapy planning typically use fiducial markers for pretreatment patient positioning and alignment. Fiducial markers appear as small signal voids in MRI images and are often difficult to discern. Existing clinical methods for fiducial marker localization require multiple MRI sequences and/or manual interaction and specialized expertise. In this study, we develop a robust method for automatic fiducial marker detection in prostate MRI simulation images and quantify the pretreatment alignment accuracy using automatically detected fiducial markers in MRI.
In this study, a deep learning-based algorithm was used to convert MRI images into labeled fiducial marker volumes. Seventy-seven prostate cancer patients who received marker implantation prior to MRI and CT simulation imaging were selected for this study. Multiple-Echo T -VIBE MRI images were acquired, and images were stratified (at the patient level) based on the presence of intraprostatic calcifications. Ground truth (GT) contours were defined by an expert on MRI using CT images. Training was done using the pix2pix generative adversarial network (GAN) image-to-image translation package and model testing was done using fivefold cross validation. For performance comparison, an experienced medical dosimetrist and a medical physicist each manually contoured fiducial markers in MRI images. The percent of correct detections and F classification scores are reported for markers detected using the automatic detection algorithm and human observers. The patient positioning errors were quantified by calculating the target registration errors (TREs) from fiducial marker driven rigid registration between MRI and CBCT images. Target registration errors were quantified for fiducial marker contours defined on MRI by the automatic detection algorithm and the two expert human observers.
Ninety-six percent of implanted fiducial markers were correctly identified using the automatic detection algorithm. Two expert raters correctly identified 97% and 96% of fiducial markers, respectively. The F classification score was 0.68, 0.75, and 0.72 for the automatic detection algorithm and two human raters, respectively. The main source of false discoveries was intraprostatic calcifications. The mean TRE differences between alignments from automatic detection algorithm and human detected markers and GT were <1 mm.
We have developed a deep learning-based approach to automatically detect fiducial markers in MRI-only simulation images in a clinically representative patient cohort. The automatic detection algorithm-predicted markers can allow for patient setup with similar accuracy to independent human observers.
利用仅磁共振成像（MRI）模拟进行前列腺放疗计划的临床机构通常使用基准标记物进行治疗前患者的定位和对齐。基准标记物在MRI图像中表现为小的信号空洞，且常常难以辨别。现有的基准标记物定位临床方法需要多个MRI序列和/或人工交互以及专业知识。在本研究中，我们开发了一种在前列腺MRI模拟图像中自动检测基准标记物的稳健方法，并使用MRI中自动检测到的基准标记物来量化治疗前的对齐精度。
在本研究中，使用基于深度学习的算法将MRI图像转换为标记的基准标记物体积。选择77例在MRI和CT模拟成像前接受标记物植入的前列腺癌患者进行本研究。采集多回波T-VIBE MRI图像，并根据前列腺内钙化的存在情况（在患者层面）对图像进行分层。由专家在MRI上使用CT图像定义真实轮廓（GT）。使用pix2pix生成对抗网络（GAN）图像到图像转换软件包进行训练，并使用五重交叉验证进行模型测试。为了进行性能比较，一位经验丰富的医学剂量师和一位医学物理学家分别在MRI图像中手动勾勒基准标记物。报告使用自动检测算法和人类观察者检测到的标记物的正确检测百分比和F分类分数。通过计算MRI和CBCT图像之间基于基准标记物驱动的刚性配准的目标配准误差（TRE）来量化患者定位误差。对由自动检测算法和两位专家人类观察者在MRI上定义的基准标记物轮廓量化目标配准误差。
使用自动检测算法正确识别了96%的植入基准标记物。两位专家评分者分别正确识别了97%和96%的基准标记物。自动检测算法和两位人类评分者的F分类分数分别为0.68、0.75和0.72。错误发现的主要来源是前列腺内钙化。自动检测算法与人类检测到的标记物和GT之间的对齐的平均TRE差异<1毫米。
我们开发了一种基于深度学习的方法，用于在具有临床代表性的患者队列的仅MRI模拟图像中自动检测基准标记物。自动检测算法预测的标记物能够以与独立人类观察者相似的精度进行患者摆位。
