Li Beibin, Mercan Ezgi, Mehta Sachin, Knezevich Stevan, Arnold Corey W, Weaver Donald L, Elmore Joann G, Shapiro Linda G
University of Washington, Seattle, WA.
Seattle Children's Hospital, Seattle, WA.
Proc IAPR Int Conf Pattern Recogn. 2021 Jan;2020:8727-8734. doi: 10.1109/icpr48806.2021.9412824. Epub 2021 May 5.
In this study, we propose the Ductal Instance-Oriented Pipeline (DIOP) that contains a duct-level instance segmentation model, a tissue-level semantic segmentation model, and three-levels of features for diagnostic classification. Based on recent advancements in instance segmentation and the Mask RCNN model, our duct-level segmenter tries to identify each ductal individual inside a microscopic image; then, it extracts tissue-level information from the identified ductal instances. Leveraging three levels of information obtained from these ductal instances and also the histopathology image, the proposed DIOP outperforms previous approaches (both feature-based and CNN-based) in all diagnostic tasks; for the four-way classification task, the DIOP achieves comparable performance to general pathologists in this unique dataset. The proposed DIOP only takes a few seconds to run in the inference time, which could be used interactively on most modern computers. More clinical explorations are needed to study the robustness and generalizability of this system in the future.
在本研究中，我们提出了面向导管实例的管道（DIOP），它包含一个导管级实例分割模型、一个组织级语义分割模型以及用于诊断分类的三级特征。基于实例分割和Mask RCNN模型的最新进展，我们的导管级分割器试图识别微观图像内的每个导管个体；然后，它从识别出的导管实例中提取组织级信息。利用从这些导管实例以及组织病理学图像中获得的三级信息，所提出的DIOP在所有诊断任务中均优于先前的方法（基于特征的方法和基于卷积神经网络的方法）；对于四路分类任务，DIOP在这个独特的数据集中达到了与普通病理学家相当的性能。所提出的DIOP在推理时仅需几秒钟即可运行，这在大多数现代计算机上都可以交互使用。未来需要更多的临床探索来研究该系统的稳健性和通用性。
