Janowczyk Andrew, Doyle Scott, Gilmore Hannah, Madabhushi Anant
Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA.
Pathology & Anatomical Sciences, SUNY Buffalo, Buffalo, NY, USA.
Comput Methods Biomech Biomed Eng Imaging Vis. 2018;6(3):270-276. doi: 10.1080/21681163.2016.1141063. Epub 2016 Apr 28.
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 -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.
深度学习（DL）最近已成功应用于许多图像分析问题。然而，对于大图像数据（如高分辨率数字病理切片图像）的分割，DL方法往往效率低下。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。对于典型的简单深度学习方案，使用高性能计算环境遍历和询问所有图像像素将需要数百小时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的放大倍数以及相应的计算量，以提供精确的结果。我们在一项针对141张雌激素受体阳性（ER+）乳腺癌图像的细胞核分割任务中评估了我们的方法，结果表明我们平均可以将计算时间减少约85%。我们使用这141张图像中12000个细胞核的专家注释对RADHicaL进行了定量评估。与仅在最高放大倍数下运行的简单DL方法进行的直接比较产生了以下性能指标：检测率分别为0.9407和0.9854，F1分数分别为0.8218和0.8489，真阳性率分别为0.8061和0.8364，阳性预测值分别为0.8822和0.8932。我们的性能指标与数字病理图像的现有细胞核分割方法相比具有优势。
