BenTaieb Aïcha, Nosrati Masoud S, Li-Chang Hector, Huntsman David, Hamarneh Ghassan
Department of Computing Sciences, Medical Image Analysis Lab, Simon Fraser University, Burnaby, Canada.
Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, BC, Canada.
J Pathol Inform. 2016 Jul 26;7:28. doi: 10.4103/2153-3539.186899. eCollection 2016.
It has been shown that ovarian carcinoma subtypes are distinct pathologic entities with differing prognostic and therapeutic implications. Histotyping by pathologists has good reproducibility, but occasional cases are challenging and require immunohistochemistry and subspecialty consultation. Motivated by the need for more accurate and reproducible diagnoses and to facilitate pathologists' workflow, we propose an automatic framework for ovarian carcinoma classification.
Our method is inspired by pathologists' workflow. We analyse imaged tissues at two magnification levels and extract clinically-inspired color, texture, and segmentation-based shape descriptors using image-processing methods. We propose a carefully designed machine learning technique composed of four modules: A dissimilarity matrix, dimensionality reduction, feature selection and a support vector machine classifier to separate the five ovarian carcinoma subtypes using the extracted features.
This paper presents the details of our implementation and its validation on a clinically derived dataset of eighty high-resolution histopathology images. The proposed system achieved a multiclass classification accuracy of 95.0% when classifying unseen tissues. Assessment of the classifier's confusion (confusion matrix) between the five different ovarian carcinoma subtypes agrees with clinician's confusion and reflects the difficulty in diagnosing endometrioid and serous carcinomas.
Our results from this first study highlight the difficulty of ovarian carcinoma diagnosis which originate from the intrinsic class-imbalance observed among subtypes and suggest that the automatic analysis of ovarian carcinoma subtypes could be valuable to clinician's diagnostic procedure by providing a second opinion.
已表明卵巢癌亚型是具有不同预后和治疗意义的不同病理实体。病理学家进行的组织分型具有良好的可重复性，但偶尔会遇到具有挑战性的病例，需要免疫组织化学和专科会诊。出于对更准确和可重复诊断的需求以及为了简化病理学家的工作流程，我们提出了一种用于卵巢癌分类的自动框架。
我们的方法受到病理学家工作流程的启发。我们在两个放大倍数水平上分析成像组织，并使用图像处理方法提取基于临床启发的颜色、纹理和基于分割的形状描述符。我们提出了一种精心设计的机器学习技术，由四个模块组成：一个差异矩阵、降维、特征选择和一个支持向量机分类器，以使用提取的特征来区分五种卵巢癌亚型。
本文介绍了我们在一个由八十张高分辨率组织病理学图像组成的临床衍生数据集上的实现细节及其验证。当对未见过的组织进行分类时，所提出的系统实现了95.0%的多类分类准确率。对分类器在五种不同卵巢癌亚型之间的混淆情况（混淆矩阵）的评估与临床医生的混淆情况一致，并反映了诊断子宫内膜样癌和浆液性癌的难度。
我们这项首次研究的结果突出了卵巢癌诊断的难度，这种难度源于各亚型之间存在的内在类别不平衡，并表明卵巢癌亚型的自动分析通过提供第二种观点，可能对临床医生的诊断程序有价值。
