Abstract
To facilitate both the detection and the interpretation of findings in chest X-rays, comparison with a previous image of the same patient is very valuable to radiologists. Today, the most common approach for deep learning methods to automatically inspect chest X-rays disregards the patient history and classifies only single images as normal or abnormal. Nevertheless, several methods for assisting in the task of comparison through image registration have been proposed in the past. However, as we illustrate, they tend to miss specific types of pathological changes like cardiomegaly and effusion. Due to assumptions on fixed anatomical structures or their measurements of registration quality they tend to produce unnaturally deformed warp fields impacting visualization of the difference image between moving and fixed images. To overcome these limitations, we are the first to use a new paradigm based on individual rib pair segmentation for anatomy penalized registration, which proves a natural way to limit folding of the warp field, especially beneficial for image pairs with large pathological changes. We show that it is possible to develop a deep learning powered solution that can visualize what other methods overlook on a large data set of paired public images, starting from less than 25 fully labeled and 50 partly labeled training images, employing sequential instance memory segmentation with hole dropout, weak labeling, coarse-to-fine refinement and Gaussian mixture model histogram matching. We statistically evaluate the benefits of our method over the SOTA and highlight the limits of currently used metrics for registration of chest X-rays.
Abstract (translated)
为促进在 chest X-ray 中发现和解释发现的双重目的,与同一患者先前图像的比较对于放射科医生来说非常重要。当前,深度学习方法自动检查 chest X-ray 最常用的方法是忽略患者历史,仅将单个图像分类为正常或异常,并将所有图像视为正常。尽管如此,我们曾提出过几种方法,用于通过图像注册进行比较。然而,正如我们所示,它们往往会忽略特定的病理变化,如心脏扩大和液栓。由于对固定解剖学结构的假设或其注册质量的测量,它们往往会产生自然的扭曲场,影响移动和固定图像之间的差异图像可视化。为了克服这些限制,我们将成为第一个使用个体肋骨对分割的新范式来进行解剖学惩罚注册的开创者,该范式证明了限制扭曲场折叠的自然方法,特别是对于那些存在大量病理变化的图像对。我们表明,可以开发一种深度学习驱动的解决方案,可以可视化其他方法忽略的公共图像对大型数据集上的数据,从 fully 标记的测试图像集合中开始,使用空洞 dropout、弱标记、粗到细的 refine 和高斯混合模型概率分布匹配。我们统计评估了我们方法相对于当前用于 chest X-ray 注册的最佳方法的优势,并突出当前使用的标准差限制。
URL
https://arxiv.org/abs/2301.09338