A resolution adaptive deep hierarchical (RADHicaL) learning scheme applied to nuclear segmentation of digital pathology images.
A resolution adaptive deep hierarchical (RADHicaL) learning scheme applied to nuclear segmentation of digital pathology images.
复制标题
DOI：
10.1080/21681163.2016.1141063
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Madabhushi A
中科院分区：
文献类型：
--
作者：
Janowczyk A;Doyle S;Gilmore H;Madabhushi A
深度学习（DL）最近已成功应用于许多图像分析问题。然而，DL方法对于大图像数据（诸如高分辨率数字病理切片图像）的分割往往是低效的。例如，以40倍放大率扫描的典型乳腺活检图像包含数十亿像素，其中通常只有一小部分属于感兴趣的类别。对于一个典型的幼稚的深度学习方案，解析和询问所有图像像素将代表使用高性能计算环境的数百甚至数千小时的计算时间。在本文中，我们提出了一种分辨率自适应深度分层（RADHicaL）学习方案，其中利用较低分辨率的DL网络来确定是否需要更高级别的放大，从而计算，以提供精确的结果。我们使用141个ER+乳腺癌图像的队列对核分割任务进行了评估，并显示我们可以将计算时间平均减少约85%。对这141幅图像中的12，000个细胞核进行专家注释，用于RADHicaL的定量评价。与单纯DL方法进行头对头比较，仅在最高放大倍数下操作，产生以下性能指标：0.9407 vs 0.9854检出率，0.8218 vs 0.8489 F评分，0.8061 vs 0.8364真阳性率和0.8822 vs 0.8932阳性预测值。我们的性能指标与最先进的数字病理图像核分割方法相比毫不逊色。
Deep learning (DL) has recently been successfully applied to a number of image analysis problems. However, DL approaches tend to be inefficient for segmentation on large image data, such as high-resolution digital pathology slide images. For example, typical breast biopsy images scanned at 40× magnification contain billions of pixels, of which usually only a small percentage belong to the class of interest. For a typical naïve deep learning scheme, parsing through and interrogating all the image pixels would represent hundreds if not thousands of hours of compute time using high performance computing environments. In this paper, we present a resolution adaptive deep hierarchical (RADHicaL) learning scheme wherein DL networks at lower resolutions are leveraged to determine if higher levels of magnification, and thus computation, are necessary to provide precise results. We evaluate our approach on a nuclear segmentation task with a cohort of 141 ER+ breast cancer images and show we can reduce computation time on average by about 85%. Expert annotations of 12,000 nuclei across these 141 images were employed for quantitative evaluation of RADHicaL. A head-to-head comparison with a naïve DL approach, operating solely at the highest magnification, yielded the following performance metrics: .9407 vs .9854 Detection Rate, .8218 vs .8489 F-score, .8061 vs .8364 true positive rate and .8822 vs 0.8932 positive predictive value. Our performance indices compare favourably with state of the art nuclear segmentation approaches for digital pathology images.