High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection.
High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection.
复制标题
DOI：
10.1371/journal.pone.0196828
复制
发表时间：
2018
期刊：
影响因子：
3.7
通讯作者：
González F
中科院分区：
文献类型：
--
作者：
Cruz-Roa A;Gilmore H;Basavanhally A;Feldman M;Ganesan S;Shih N;Tomaszewski J;Madabhushi A;González F
在全切片图像（WSI）上精确检测浸润性癌症是数字病理学诊断和分级任务的关键第一步。卷积神经网络（CNN）是计算机视觉任务中最流行的表示学习方法，已成功应用于数字病理学，包括肿瘤和有丝分裂检测。然而，CNN通常只适用于相对较小的图像尺寸（200 × 200像素）。直到最近，全卷积网络（FCN）才能够处理更大的图像尺寸（500 × 500像素）进行语义分割。因此，将CNN直接应用于WSI在计算上是不可行的，因为对于WSI，CNN将需要数十亿或数万亿的参数。为了解决这个问题，本文提出了一种新的方法，高通量自适应采样全载玻片组织病理学图像分析（HASHI），其中包括：i）一种新的有效的自适应采样方法的基础上的概率梯度和准蒙特卡罗采样，和，ii）一个强大的表示学习分类器的基础上CNN。我们将HASHI应用于WSI上浸润性乳腺癌的自动检测。HASHI使用涉及近500例病例的三个不同数据队列进行训练和验证，然后在癌症基因组图谱的195项研究中进行独立测试。结果表明：（1）自适应采样方法是一种有效的处理WSI的策略，通过获得密集采样的比较结果，在不影响预测精度的情况下（24小时内采集1600万个样本），（1分钟内采集2，000个样本），以及（2）在独立的测试数据集上，HASHI对来自多个站点、扫描仪和平台的数据有效且稳健，平均骰子系数达到76%。
Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200 × 200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500 × 500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (∼6 million of samples in 24 hours) with far fewer samples (∼2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%.
登录
查看更多内容
Histostitcher（©）：一种交互式程序，用于从组织碎片中精确，快速重建整个组织学切片。
DOI：
10.1016/j.compmedimag.2011.01.010
发表时间：
2011-10
期刊：
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
影响因子：
--
作者：
Chappelow J;Tomaszewski JE;Feldman M;Shih N;Madabhushi A
通讯作者：
Madabhushi A
影响因子：
7.5
作者：
Arevalo, John;Cruz-Roa, Angel;Gonzalez, Fabio A.
通讯作者：
Gonzalez, Fabio A.
DOI：
10.1146/annurev-bioeng-112415-114722
发表时间：
2016-07-11
影响因子：
9.7
作者：
Bhargava R;Madabhushi A
通讯作者：
Madabhushi A
影响因子：
4.6
作者：
Cruz-Roa A;Gilmore H;Basavanhally A;Feldman M;Ganesan S;Shih NNC;Tomaszewski J;González FA;Madabhushi A
通讯作者：
Madabhushi A
影响因子：
--
作者：
Cruz-Roa A;Díaz G;Romero E;González FA
通讯作者：
González FA