Deep learning nuclei detection: A simple approach can deliver state-of-the-art results
Deep learning nuclei detection: A simple approach can deliver state-of-the-art results
复制标题
DOI：
10.1016/j.compmedimag.2018.08.010
复制
发表时间：
2018-12-01
影响因子：
5.7
通讯作者：
Hahn, Horst K.
中科院分区：
文献类型：
--
作者：
Hoefener, Henning;Homeyer, Andre;Hahn, Horst K.
背景：深卷积神经网络已成为组织病理学图像中细胞核检测的广泛工具。许多实现共享一种基本方法，包括生成指示核中心存在的中间图，我们将其称为PMAP。然而，这些实现往往在几个参数上存在差异，从而导致检测质量不同。方法：我们确定了几个基本参数，并使用它们的组合来配置基本的PMAP方法。我们在多个数据集上对各种配置的检测质量、效率和训练工作量进行了全面的评估和比较。结果：PMAP的后处理对检测质量的影响最大。此外，还确定了两种不同的网络体系结构，它们可以提高检测质量或运行时性能。在H&E染色的结直肠腺癌图像和乳腺肿瘤组织的Ki-67染色图像上，最佳配置产生的F1度量分别为0.816和0.819。平均训练时间不到15,000次，平均每秒处理415万像素。结论：基本的PMAP方法受某些参数的影响较大。我们的评估提供了关于它们的影响和最佳环境的指导。如果配置得当，这种简单而高效的方法可以产生与更复杂和耗时的最先进方法相同的检测质量。(C)2018年作者。爱思唯尔有限公司出版。
Background: Deep convolutional neural networks have become a widespread tool for the detection of nuclei in histopathology images. Many implementations share a basic approach that includes generation of an intermediate map indicating the presence of a nucleus center, which we refer to as PMap. Nevertheless, these implementations often still differ in several parameters, resulting in different detection qualities.Methods: We identified several essential parameters and configured the basic PMap approach using combinations of them. We thoroughly evaluated and compared various configurations on multiple datasets with respect to detection quality, efficiency and training effort.Results: Post-processing of the PMap was found to have the largest impact on detection quality. Also, two different network architectures were identified that improve either detection quality or runtime performance. The best-performing configuration yields f1-measures of 0.816 on H&E stained images of colorectal adenocarcinomas and 0.819 on Ki-67 stained images of breast tumor tissue. On average, it was fully trained in less than 15,000 iterations and processed 4.15 megapixels per second at prediction time.Conclusions: The basic PMap approach is greatly affected by certain parameters. Our evaluation provides guidance on their impact and best settings. When configured properly, this simple and efficient approach can yield equal detection quality as more complex and time-consuming state-of-the-art approaches. (C) 2018 The Authors. Published by Elsevier Ltd.