DCAN: Deep contour-aware networks for object instance segmentation from histology images
DCAN: Deep contour-aware networks for object instance segmentation from histology images
复制标题
DOI：
10.1016/j.media.2016.11.004
复制
发表时间：
2017-02-01
影响因子：
10.9
通讯作者：
Heng, Pheng-Ann
中科院分区：
文献类型：
--
作者：
Chen, Hao;Qi, Xiaojuan;Heng, Pheng-Ann
在组织病理学图像分析中，病理学家常规采用腺体、细胞核等组织结构的形态来评估腺癌的恶性程度。从组织学图像中准确检测和分割这些感兴趣的对象是获得用于定量诊断的可靠形态学统计数据的重要先决条件。虽然手动注释容易出错、耗时且依赖于操作员，但由于外观变化大、强模仿的存在以及组织学结构的严重退化，从组织学图像中自动检测和分割感兴趣的对象可能非常具有挑战性。为了应对这些挑战，我们在统一的多任务学习框架下提出了一种新颖的深度轮廓感知网络（DCAN），以实现更准确的检测和分割。在所提出的网络中，基于端到端全卷积网络（FCN）探索多级上下文特征来处理大的外观变化。我们进一步建议采用辅助监督机制来克服训练此类深度网络时梯度消失的问题。更重要的是，我们的网络不仅可以输出组织学对象的准确概率图，还可以同时描绘清晰的轮廓以分离聚类对象实例，这进一步提高了分割性能。我们的方法在两项组织学对象分割挑战赛中排名第一，包括 2015 MICCAI 腺体分割挑战赛和 2015 MICCAI 细胞核分割挑战赛。对这两个具有挑战性的数据集的大量实验证明了我们的方法的卓越性能，远远超过了所有其他方法。 (C) 2016 Elsevier B.V. 保留所有权利。
In histopathological image analysis, the morphology of histological structures, such as glands and nuclei, has been routinely adopted by pathologists to assess the malignancy degree of adenocarcinomas. Accurate detection and segmentation of these objects of interest from histology images is an essential prerequisite to obtain reliable morphological statistics for quantitative diagnosis. While manual annotation is error-prone, time-consuming and operator-dependant, automated detection and segmentation of objects of interest from histology images can be very challenging due to the large appearance variation, existence of strong mimics, and serious degeneration of histological structures. In order to meet these challenges, we propose a novel deep contour-aware network (DCAN) under a unified multi-task learning framework for more accurate detection and segmentation. In the proposed network, multi-level contextual features are explored based on an end-to-end fully convolutional network (FCN) to deal with the large appearance variation. We further propose to employ an auxiliary supervision mechanism to overcome the problem of vanishing gradients when training such a deep network. More importantly, our network can not only output accurate probability maps of histological objects, but also depict clear contours simultaneouily for separating clustered object instances, which further boosts the segmentation performance. Our method ranked the first in two histological object segmentation challenges, including 2015 MICCAI Gland Segmentation Challenge and 2015 MICCAI Nuclei Segmentation Challenge. Extensive experiments on these two challenging datasets demonstrate the superior performance of our method, surpassing all the other methods by a significant margin. (C) 2016 Elsevier B.V. All rights reserved.