Muller Florence M, Maebe Jens, Vanhove Christian, Vandenberghe Stefaan
Medical Image and Signal Processing (MEDISIP), Department of Electronics and Information Systems, Faculty of Engineering and Architecture, Ghent University, Ghent, Belgium.
Med Phys. 2023 Sep;50(9):5643-5656. doi: 10.1002/mp.16385. Epub 2023 Apr 5.
In preclinical settings, micro-computed tomography (CT) provides a powerful tool to acquire high resolution anatomical images of rodents and offers the advantage to in vivo non-invasively assess disease progression and therapy efficacy. Much higher resolutions are needed to achieve scale-equivalent discriminatory capabilities in rodents as those in humans. High resolution imaging however comes at the expense of increased scan times and higher doses. Specifically, with preclinical longitudinal imaging, there are concerns that dose accumulation may affect experimental outcomes of animal models.
Dose reduction efforts under the ALARA (as low as reasonably achievable) principles are thus a key point of attention. However, low dose CT acquisitions inherently induce higher noise levels which deteriorate image quality and negatively impact diagnostic performance. Many denoising techniques already exist, and deep learning (DL) has become increasingly popular for image denoising, but research has mostly focused on clinical CT with limited studies conducted on preclinical CT imaging. We investigate the potential of convolutional neural networks (CNN) for restoring high quality micro-CT images from low dose (noisy) images. The novelty of the CNN denoising frameworks presented in this work consists of utilizing image pairs with realistic CT noise present in the input as well as the target image used for the model training; a noisier image acquired with a low dose protocol is matched to a less noisy image acquired with a higher dose scan of the same mouse.
Low and high dose ex vivo micro-CT scans of 38 mice were acquired. Two CNN models, based on a 2D and 3D four-layer U-Net, were trained with mean absolute error (30 training, 4 validation and 4 test sets). To assess denoising performance, ex vivo mice and phantom data were used. Both CNN approaches were compared to existing methods, like spatial filtering (Gaussian, Median, Wiener) and iterative total variation image reconstruction algorithm. Image quality metrics were derived from the phantom images. A first observer study (n = 23) was set-up to rank overall quality of differently denoised images. A second observer study (n = 18) estimated the dose reduction factor of the investigated 2D CNN method.
Visual and quantitative results show that both CNN algorithms exhibit superior performance in terms of noise suppression, structural preservation and contrast enhancement over comparator methods. The quality scoring by 23 medical imaging experts also indicates that the investigated 2D CNN approach is consistently evaluated as the best performing denoising method. Results from the second observer study and quantitative measurements suggest that CNN-based denoising could offer a 2-4× dose reduction, with an estimated dose reduction factor of about 3.2 for the considered 2D network.
Our results demonstrate the potential of DL in micro-CT for higher quality imaging at low dose acquisition settings. In the context of preclinical research, this offers promising future prospects for managing the cumulative severity effects of radiation in longitudinal studies.
在临床前研究中，微型计算机断层扫描（CT）为获取啮齿动物的高分辨率解剖图像提供了强大工具，并且具有在体内非侵入性评估疾病进展和治疗效果的优势。要在啮齿动物中实现与人同等的分辨能力，需要更高的分辨率。然而，高分辨率成像的代价是扫描时间增加和剂量提高。具体而言，对于临床前纵向成像，人们担心剂量累积可能会影响动物模型的实验结果。
因此，遵循“尽可能合理达到低剂量”（ALARA）原则进行剂量降低是一个关键关注点。然而，低剂量CT采集本身会导致更高的噪声水平，从而降低图像质量并对诊断性能产生负面影响。已经存在许多去噪技术，深度学习（DL）在图像去噪方面越来越受欢迎，但研究大多集中在临床CT上，对临床前CT成像的研究有限。我们研究了卷积神经网络（CNN）从低剂量（有噪声）图像中恢复高质量微型CT图像的潜力。本研究中提出的CNN去噪框架的新颖之处在于，在模型训练中使用输入图像和目标图像中都存在逼真CT噪声的图像对；用低剂量协议采集的噪声更大的图像与对同一只小鼠进行的高剂量扫描采集的噪声较小的图像相匹配。
对38只小鼠进行了低剂量和高剂量离体微型CT扫描。基于二维和三维四层U-Net的两个CNN模型使用平均绝对误差进行训练（30个训练集、4个验证集和4个测试集）。为了评估去噪性能，使用了离体小鼠和体模数据。将两种CNN方法与现有方法进行比较，如空间滤波（高斯、中值、维纳）和迭代全变差图像重建算法。图像质量指标来自体模图像。开展了第一项观察者研究（n = 23），以对不同去噪图像的整体质量进行排名。第二项观察者研究（n = 18）估计了所研究的二维CNN方法的剂量降低因子。
视觉和定量结果表明，与比较方法相比，两种CNN算法在噪声抑制、结构保留和对比度增强方面均表现出卓越性能。23名医学影像专家的质量评分也表明，所研究的二维CNN方法一直被评估为性能最佳的去噪方法。第二项观察者研究的结果和定量测量表明，基于CNN的去噪可以将剂量降低2至4倍，对于所考虑的二维网络，估计剂量降低因子约为3.2。
我们的结果证明了深度学习在微型CT中用于低剂量采集设置下更高质量成像的潜力。在临床前研究的背景下，这为在纵向研究中管理辐射的累积严重影响提供了有希望的未来前景。
