Kwak Jin Tae, Hewitt Stephen M
Department of Computer Science and Engineering, Sejong University, Seoul 05006, Korea.
Tissue Array Research Program, Laboratory of Pathology, Center for Cancer Research, National Cancer Institute, National Institutes of Health, MD 20852, USA.
Comput Methods Programs Biomed. 2017 Apr;142:91-99. doi: 10.1016/j.cmpb.2017.02.023. Epub 2017 Feb 22.
Various digital pathology tools have been developed to aid in analyzing tissues and improving cancer pathology. The multi-resolution nature of cancer pathology, however, has not been fully analyzed and utilized. Here, we develop an automated, cooperative, and multi-resolution method for improving prostate cancer diagnosis.
Digitized tissue specimen images are obtained from 5 tissue microarrays (TMAs). The TMAs include 70 benign and 135 cancer samples (TMA1), 74 benign and 89 cancer samples (TMA2), 70 benign and 115 cancer samples (TMA3), 79 benign and 82 cancer samples (TMA4), and 72 benign and 86 cancer samples (TMA5). The tissue specimen images are segmented using intensity- and texture-based features. Using the segmentation results, a number of morphological features from lumens and epithelial nuclei are computed to characterize tissues at different resolutions. Applying a multiview boosting algorithm, tissue characteristics, obtained from differing resolutions, are cooperatively combined to achieve accurate cancer detection.
In segmenting prostate tissues, the multiview boosting method achieved≥ 0.97 AUC using TMA1. For detecting cancers, the multiview boosting method achieved an AUC of 0.98 (95% CI: 0.97-0.99) as trained on TMA2 and tested on TMA3, TMA4, and TMA5. The proposed method was superior to single-view approaches, utilizing features from a single resolution or merging features from all the resolutions. Moreover, the performance of the proposed method was insensitive to the choice of the training dataset. Trained on TMA3, TMA4, and TMA5, the proposed method obtained an AUC of 0.97 (95% CI: 0.96-0.98), 0.98 (95% CI: 0.96-0.99), and 0.97 (95% CI: 0.96-0.98), respectively.
The multiview boosting method is capable of integrating information from multiple resolutions in an effective and efficient fashion and identifying cancers with high accuracy. The multiview boosting method holds a great potential for improving digital pathology tools and research.
已开发出多种数字病理学工具，以辅助分析组织并改善癌症病理学。然而，癌症病理学的多分辨率特性尚未得到充分分析和利用。在此，我们开发一种用于改善前列腺癌诊断的自动化、协作式多分辨率方法。
从5个组织微阵列（TMA）获取数字化组织标本图像。这些TMA包括70个良性样本和135个癌症样本（TMA1）、74个良性样本和89个癌症样本（TMA2）、70个良性样本和115个癌症样本（TMA3）、79个良性样本和82个癌症样本（TMA4）以及72个良性样本和86个癌症样本（TMA5）。利用基于强度和纹理的特征对组织标本图像进行分割。根据分割结果，计算来自管腔和上皮细胞核的一些形态学特征，以在不同分辨率下表征组织。应用多视图增强算法，将从不同分辨率获得的组织特征进行协作组合，以实现准确的癌症检测。
在分割前列腺组织时，多视图增强方法使用TMA1实现了≥0.97的AUC。在检测癌症方面，多视图增强方法在TMA2上训练并在TMA3、TMA4和TMA5上测试时，AUC为0.98（95%CI：0.97 - 0.99）。所提出的方法优于单视图方法，单视图方法利用单一分辨率的特征或合并所有分辨率的特征。此外，所提出方法的性能对训练数据集的选择不敏感。在所提出的方法在TMA3、TMA4和TMA5上训练时，分别获得了0.97（95%CI：0.96 - 0.98）、0.98（95%CI：0.96 - 0.99）和0.97（95%CI：0.96 - 0.98）的AUC。
多视图增强方法能够以有效且高效的方式整合来自多个分辨率的信息，并高精度地识别癌症。多视图增强方法在改善数字病理学工具和研究方面具有巨大潜力。
