Pattern recognition in medical imaging

最近在模式识别方面的工作表明，计算机可以等同于甚至超过人类专家的图像分类和模式分析。 现代成像系统在空间和光谱分辨率以及动态范围方面远远超过人眼，因此潜在地允许基于机器的图像图案分析系统执行这样的任务。 我们已经开发的模式分析系统，其特点和出版被称为WND-CHARM。 WND-CHARM的一个关键特性是它可以提供图像相似性的定量度量。 单个图像或图像组之间的定量比较允许建立由图像表示的生理过程的进展的时间过程。 一个独立的验证，在一个过程中的形态模式的连续演变是由计算机检测到的是它的能力，将这些图像在没有先验信息的顺序。 随后，从一个时间点到另一个时间点的变化程度可以用于确定生理过程是平滑和连续的还是通过离散阶段进行。 不连续的过程意味着生物控制的存在，在过渡，并可能指向医疗干预的关键阶段。 我们发表的工作表明，年龄相关的肌肉退化（少肌症）在C。秀丽线虫的咽发生在三个不连续的阶段。 这是第一个表征离散后发育形态状态在任何生物体。 肌肉退化分阶段发生的观察结果意味着它可能是一个受调节的过程，并且可能受到干预以防止或延迟这些转变。 我们目前的工作将调查这些阶段是否可以在哺乳动物组织中持续观察到，以及饮食和药物白藜芦醇等干预措施是否会影响这些形态变化的时间或幅度。 我们还发表了研究人群中骨关节炎（OA）进展的工作，包括巴尔的摩老龄化纵向研究（BLSA）。 我们能够证明WND-CHARM能够在膝关节X线片中诊断OA的存在，其准确性接近训练有素的放射科医生小组。 最近，我们发表了WND-CHARM可以预测未来发生的放射学可检测的骨关节炎的X射线评分为放射学清晰。 我们能够证明，未来20年中度OA的发展可以通过由三名放射科医生组成的小组进行的无OA X线评分来预测，准确率> 70%。 最近，我们能够进一步描述OA进展，并确定早期，缓慢的变化期，然后快速退化。 我们正在使用从骨关节炎倡议获得的MRI数据集对这些研究进行随访。 我们对癌症活检的H& E染色切片的图像处理工作表明，切片和染色的一致性是医学样本有效图像分析的关键因素。 最近，我们能够证明，使用颜色敏感图像特征的常用方法不如在预处理步骤中将苏木精和伊红染色去卷积为单独的通道，随后将其作为单独的灰度通道处理。 此外，我们分析了许多常用的图像特征和分类算法，以确定它们的相对有效性，以及提出策略，提高分类器的性能。 这些研究报告已于去年发表。我们的成功诊断和分类黑色素瘤转移，使我们扩大这种分析，以调查几种类型的癌症可作为商业组织微阵列。 我们目前的工作重点是通过BLSA和骨关节炎倡议（OAI）研究几种人体组织的生理年龄。 我们要解决的一个问题是，衰老是否像我们在C.我们正在研究的组织主要是肌肉和骨骼，使用几种方式（CT，MRI，组织学）成像。虚弱发作的表征是这些研究的潜在结果之一，也可能表征节段性衰老。 来自BLSA和其他研究的纵向数据的可用性将使我们能够确定这些生活转变在多大程度上可以通过非侵入性成像技术预测，类似于我们如何能够预测晚年骨关节炎的发作。

Recent work in pattern recognition has demonstrated that computers can equal or even surpass image classification and pattern analysis by human experts. Modern imaging systems far exceed the human eye in spatial and spectral resolution as well as dynamic range, thus potentially allowing machine-based image pattern analysis systems to perform such tasks. The pattern analysis system we have developed, characterized and published is called WND-CHARM. A key property of WND-CHARM is that it can provide quantitative measures of image similarity. Quantitative comparisons between individual images or groups of images allow the establishment of a time-course for the progression of a physiological process represented by images. An independent verification that the continuous evolution of morphological patterns in a process is detected by the computer is its ability to place these images in order without a priori information. Subsequently, the degree of change from one timepoint to another can be used to determine if the physiological process is smooth and continuous or progresses through discrete stages. Discontinuous processes imply the presence of biological control at the transitions, and may point to key stages for medical interventions. Our published work has shown that age-related muscle degeneration (sarcopenia) in the C. elegans pharynx occurs in three discrete stages. This was the first characterization of discrete post-developmental morphological states in any organism. The observation that muscle degeneration occurs in stages implies that it may be a regulated process, and may be subject to intervention to prevent or delay these transitions. Our current work will investigate if these stages can be consistently observed in mammalian tissues, and whether interventions such as diet and the drug resveratrol affects the timing or magnitude of these morphological changes. We have also published work investigating the progression of osteoarthritis (OA) in the human population comprising the Baltimore Longitudinal Study of Aging (BLSA). We were able to show that WND-CHARM is able to diagnose the existence of OA in knee X-Rays with accuracies approaching that of a panel of highly trained radiologists. More recently, we have published work that WND-CHARM can predict the future onset of radiologically detectable osteoarthritis in X-Rays that were scored as radiologically clear. We were able to show that the development of moderate OA two decades in the future can be predicted with > 70% accuracy from an X-Ray scored as free of OA by a panel of three radiologists. Recently, we were able to further characterize OA progression and identify an early, slow period of change followed by rapid degeneration. We are following up these studies with an MRI dataset we obtained from the Osteoarthritis Initiative. Our work with processing images of H&E-stained sections of cancer biopsies has shown that consistency of sectioning and staining is a key factor in effective image analysis of medical samples. More recently we were able to demonstrate that the common approach to the use of color-sensitive image features is not as effective as deconvolving the Hematoxylin and Eosin stains into separate channels in a pre-processing step and subsequently treating them as separate grayscale channels. Additionally we analyzed many commonly used image-feature and classification algorithms to determine their relative effectiveness as well as propose strategies for improving classifier performance. These studies have been published in the previous year. Our success diagnosing and sub-classifying melanoma metastases has led us to expand this analysis to a survey of several types of cancers available as commercial tissue microarrays. Our current work focuses on studying physiological age in several human tissues available through the BLSA and the Osteoarthritis Initiative (OAI). A question we are addressing is whether aging progresses through distinguishable states as we have observed in C. elegans, and the degree to which physiological age progresses synchronously in different tissues within individuals.The tissues we are studying are primarily muscle and bone, imaged using several modalities (CT, MRI, histology). The characterization of the onset of frailty is one of the potential outcomes of these studies, as well as potentially characterizing segmental aging. The availability of longitudinal data from the BLSA and other studies will allow us to determine the degree to which these life transitions are predictable from non-invasive imaging techniques, similarly to how we were able to predict the onset of osteoarthritis in later life.