Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases.
Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases.
复制标题
DOI：
10.4103/2153-3539.186902
复制
发表时间：
2016
影响因子：
--
通讯作者：
Madabhushi A
中科院分区：
文献类型：
--
作者：
Janowczyk A;Madabhushi A
深度学习（DL）是一种表示学习方法，非常适合数字病理学（DP）中的图像分析挑战。在DP的上下文中的各种图像分析任务包括检测和计数（例如，有丝分裂事件），分割（例如，细胞核），和组织分类（例如，癌性对非癌性）。不幸的是，载玻片制备、染色和扫描的差异、供应商平台以及生物学差异（例如不同等级疾病的呈现）的问题使得这些图像分析任务特别具有挑战性。传统的方法，其中领域特定的线索是手动识别和开发成特定于任务的“手工制作”的功能，可能需要广泛的调整，以适应这些变化。然而，DL采用了一种更加领域不可知的方法，将特征发现和实现相结合，以最大限度地区分感兴趣的类别。虽然DL方法在一些DP相关的图像分析任务中表现良好，例如检测和组织分类，但当前可用的开源工具和教程没有提供关于挑战的指导，例如（a）选择适当的放大率，（B）管理训练（或学习）数据集中的注释中的错误，以及（c）识别包含信息丰富样本的合适训练集。这些基本概念，需要成功地将DL范式转化为DP任务，对于（i）具有最少数字组织学经验的DL专家和（ii）具有最少DL经验的DP和图像处理专家来说是不平凡的，可以自行推导，因此值得专门的教程。本文通过七个独特的DP任务作为用例来研究这些概念，以阐明产生可比的技术，在许多情况下，上级的结果，从国家的最先进的手工制作的基于特征的分类方法。具体来说，在本教程中，我们将展示如何使用具有单一网络架构的开源框架（Caffe）来解决：（a）核分割（12，000个细胞核的F-评分为0.83），（B）上皮分割（1735个区域的F评分为0.84），（c）小管分割（795个小管的F评分为0.83），（d）淋巴细胞检测（3064个淋巴细胞的F-评分为0.90），（e）有丝分裂检测（550个有丝分裂事件中的F-评分为0.53），（f）浸润性导管癌检测（在50k个测试片上的F分数为0.7648），和（g）淋巴瘤分类（在374个图像上的分类准确度为0.97）。本文代表了迄今为止DP中DL方法的最大综合研究，在评估期间使用了超过1200张DP图像。本文附带的补充在线材料包括使用所提供的源代码、训练模型和输入数据的分步说明。
Deep learning (DL) is a representation learning approach ideally suited for image analysis challenges in digital pathology (DP). The variety of image analysis tasks in the context of DP includes detection and counting (e.g., mitotic events), segmentation (e.g., nuclei), and tissue classification (e.g., cancerous vs. non-cancerous). Unfortunately, issues with slide preparation, variations in staining and scanning across sites, and vendor platforms, as well as biological variance, such as the presentation of different grades of disease, make these image analysis tasks particularly challenging. Traditional approaches, wherein domain-specific cues are manually identified and developed into task-specific “handcrafted” features, can require extensive tuning to accommodate these variances. However, DL takes a more domain agnostic approach combining both feature discovery and implementation to maximally discriminate between the classes of interest. While DL approaches have performed well in a few DP related image analysis tasks, such as detection and tissue classification, the currently available open source tools and tutorials do not provide guidance on challenges such as (a) selecting appropriate magnification, (b) managing errors in annotations in the training (or learning) dataset, and (c) identifying a suitable training set containing information rich exemplars. These foundational concepts, which are needed to successfully translate the DL paradigm to DP tasks, are non-trivial for (i) DL experts with minimal digital histology experience, and (ii) DP and image processing experts with minimal DL experience, to derive on their own, thus meriting a dedicated tutorial. This paper investigates these concepts through seven unique DP tasks as use cases to elucidate techniques needed to produce comparable, and in many cases, superior to results from the state-of-the-art hand-crafted feature-based classification approaches. Specifically, in this tutorial on DL for DP image analysis, we show how an open source framework (Caffe), with a singular network architecture, can be used to address: (a) nuclei segmentation (F-score of 0.83 across 12,000 nuclei), (b) epithelium segmentation (F-score of 0.84 across 1735 regions), (c) tubule segmentation (F-score of 0.83 from 795 tubules), (d) lymphocyte detection (F-score of 0.90 across 3064 lymphocytes), (e) mitosis detection (F-score of 0.53 across 550 mitotic events), (f) invasive ductal carcinoma detection (F-score of 0.7648 on 50 k testing patches), and (g) lymphoma classification (classification accuracy of 0.97 across 374 images). This paper represents the largest comprehensive study of DL approaches in DP to date, with over 1200 DP images used during evaluation. The supplemental online material that accompanies this paper consists of step-by-step instructions for the usage of the supplied source code, trained models, and input data.