IEEE/ACM Trans Comput Biol Bioinform. 2022 Jul-Aug;19(4):2431-2441. doi: 10.1109/TCBB.2021.3062230. Epub 2022 Aug 8.
Histopathological identification of tumor tissue is one of the routine pathological diagnoses for pathologists. Recently, computational pathology has been successfully interpreted by a variety of deep learning-based applications. Nevertheless, the high-efficient and spatial-correlated processing of individual patches have always attracted attention in whole-slide image (WSI) analysis. In this paper, we propose a high-throughput system to detect tumor regions in colorectal cancer histology slides precisely. We train a deep convolutional neural network (CNN) model and design a Monte Carlo (MC) adaptive sampling method to estimate the most representative patches in a WSI. Two conditional random field (CRF) models are designed, namely the correction CRF and the prediction CRF are integrated for spatial dependencies of patches. We use three datasets of colorectal cancer from The Cancer Genome Atlas (TCGA) to evaluate the performance of the system. The overall diagnostic time can be reduced from 56.7 percent to 71.7 percent on the slides of a varying tumor distribution, with an increase in classification accuracy.
肿瘤组织的组织病理学鉴定是病理学家的常规病理诊断之一。最近，计算病理学已经被各种基于深度学习的应用成功地解释了。然而，在全切片图像（WSI）分析中，对单个斑块的高效和空间相关处理一直受到关注。在本文中，我们提出了一种高通量系统，以精确检测结直肠癌组织学切片中的肿瘤区域。我们训练了一个深度卷积神经网络（CNN）模型，并设计了一种蒙特卡罗（MC）自适应采样方法来估计 WSI 中最具代表性的斑块。设计了两个条件随机场（CRF）模型，即校正 CRF 和预测 CRF，用于整合斑块的空间依赖性。我们使用来自癌症基因组图谱（TCGA）的三个结直肠癌数据集来评估系统的性能。在肿瘤分布不同的幻灯片上，整体诊断时间可以从 56.7%减少到 71.7%，同时提高了分类准确性。
