A structured latent model for ovarian carcinoma subtyping from histopathology slides
A structured latent model for ovarian carcinoma subtyping from histopathology slides
复制标题
DOI：
10.1016/j.media.2017.04.008
复制
发表时间：
2017-07-01
影响因子：
10.9
通讯作者：
Hamarneh, Ghassan
中科院分区：
文献类型：
--
作者：
BenTaieb, Aicha;Li-Chang, Hector;Hamarneh, Ghassan
卵巢癌的准确分型是一个越来越关键且往往具有挑战性的诊断过程。本工作致力于卵巢癌亚型自动分类模型的开发。具体地说，我们提出了一种新的受临床启发的卵巢癌组织病理学图像亚型的上下文模型。整个幻灯片图像是使用在多倍放大下提取的组织块的集合来建模的。提出了一种高效的特征学习策略用于组织块的特征表示。显著的、有区别的组织区域的位置被视为潜在变量，允许该模型显式地忽略对分类不重要的大组织切片的部分。这些潜在变量被考虑在结构化的公式中，以对组织的多倍放大分析所表示的上下文信息进行建模。定义了一种新的、结构化的潜在支持向量机公式，并将其用于组合来自多个放大的信息，同时在潜在变量框架内运行。我们的方法的结构和背景性质解决了在组织病理学图像分类中普遍存在的类内差异和病理学家的工作量的挑战。在133名患者的数据集上进行的广泛实验证明了所提出的方法相对于最先进的组织病理学图像分类方法的有效性和准确性。我们实现了90%的平均多类分类准确率，超过了现有的工作，同时获得了在相同数据集上测试的六名临床医生的基本一致。(C)2017爱思唯尔B.V.保留所有权利。
Accurate subtyping of ovarian carcinomas is an increasingly critical and often challenging diagnostic process. This work focuses on the development of an automatic classification model for ovarian carcinoma subtyping. Specifically, we present a novel clinically inspired contextual model for histopathology image subtyping of ovarian carcinomas. A whole slide image is modelled using a collection of tissue patches extracted at multiple magnifications. An efficient and effective feature learning strategy is used for feature representation of a tissue patch. The locations of salient, discriminative tissue regions are treated as latent variables allowing the model to explicitly ignore portions of the large tissue section that are unimportant for classification. These latent variables are considered in a structured formulation to model the contextual information represented from the multi-magnification analysis of tissues. A novel, structured latent support vector machine formulation is defined and used to combine information from multiple magnifications while simultaneously operating within the latent variable framework. The structural and contextual nature of our method addresses the challenges of intra-class variation and pathologists' workload, which are prevalent in histopathology image classification. Extensive experiments on a dataset of 133 patients demonstrate the efficacy and accuracy of the proposed method against state-of-the-art approaches for histopathology image classification. We achieve an average multi-class classification accuracy of 90%, outperforming existing works while obtaining substantial agreement with six clinicians tested on the same dataset. (C) 2017 Elsevier B.V. All rights reserved.