Medical Image Analysis Lab, Simon Fraser University, Canada.
Medical Imaging Research Group, Department of Radiology, University of British Columbia, Vancouver, Canada.
Comput Med Imaging Graph. 2018 Jan;63:52-66. doi: 10.1016/j.compmedimag.2017.12.004. Epub 2017 Dec 27.
Tumor volume and metabolic activity are two robust imaging biomarkers for predicting early therapy response in F-fluorodeoxyglucose (FDG) positron emission tomography (PET), which is a modality to image the distribution of radiotracers and thereby observe functional processes in the body. To date, estimation of these two biomarkers requires a lesion segmentation step. While the segmentation methods requiring extensive user interaction have obvious limitations in terms of time and reproducibility, automatically estimating activity from segmentation, which involves integrating intensity values over the volume is also suboptimal, since PET is an inherently noisy modality. Although many semi-automatic segmentation based methods have been developed, in this paper, we introduce a method which completely eliminates the segmentation step and directly estimates the volume and activity of the lesions. We trained two parallel ensemble models using locally extracted 3D patches from phantom images to estimate the activity and volume, which are derivatives of other important quantification metrics such as standardized uptake value (SUV) and total lesion glycolysis (TLG). For validation, we used 54 clinical images from the QIN Head and Neck collection on The Cancer Imaging Archive, as well as a set of 55 PET scans of the Elliptical Lung-Spine Body Phantom™with different levels of noise, four different reconstruction methods, and three different background activities, namely; air, water, and hot background. In the validation on phantom images, we achieved relative absolute error (RAE) of 5.11 % ±3.5% and 5.7 % ±5.25% for volume and activity estimation, respectively, which represents improvements of over 20% and 6% respectively, compared with the best competing methods. From the validation performed using clinical images, we found that the proposed method is capable of obtaining almost the same level of agreement with a group of trained experts, as a single trained expert is, indicating that the method has the potential to be a useful tool in clinical practice.
肿瘤体积和代谢活性是预测 F-氟脱氧葡萄糖（FDG）正电子发射断层扫描（PET）早期治疗反应的两种强大影像学生物标志物，该方法可用于成像示踪剂的分布，从而观察体内的功能过程。迄今为止，这两种生物标志物的估计需要进行病变分割步骤。虽然需要广泛用户交互的分割方法在时间和可重复性方面存在明显的局限性，但从分割中自动估计活性，这涉及到对体积内的强度值进行积分，也是不理想的，因为 PET 是一种固有噪声的模态。尽管已经开发了许多基于半自动分割的方法，但在本文中，我们介绍了一种完全消除分割步骤并直接估计病变体积和活性的方法。我们使用从体模图像中局部提取的 3D 补丁训练了两个并行集成模型，以估计活性和体积，这些都是其他重要量化指标（如标准化摄取值（SUV）和总病变糖酵解（TLG）的导数。为了验证，我们使用了来自癌症成像档案中的 QIN 头颈部数据集的 54 个临床图像，以及一组具有不同噪声水平的椭圆形肺脊柱体模™的 55 个 PET 扫描，有四种不同的重建方法和三种不同的背景活动，即空气、水和热背景。在体模图像的验证中，我们分别实现了体积和活性估计的相对绝对误差（RAE）为 5.11%±3.5%和 5.7%±5.25%，与最佳竞争方法相比，分别提高了 20%和 6%以上。从使用临床图像进行的验证中，我们发现，与一组经过训练的专家相比，该方法几乎可以获得相同的一致性水平，表明该方法有可能成为临床实践中的有用工具。
