Strategies to Reduce the Expert Supervision Required for Deep Learning-Based Segmentation of Histopathological Images

Frontiers in Medicine

卷:6

Adrien Foucart²  Christine Decaestecker²  Yves-Rémi Van Eycke² 

[1] Digital Image Analysis in Pathology (DIAPath), Center for Microscopy and Molecular Imaging (CMMI), Université Libre de Bruxelles, Charleroi, Belgium;

[2] Laboratory of Image Synthesis and Analysis (LISA), Ecole Polytechnique de Bruxelles, Université Libre de Bruxelles, Brussels, Belgium;

关键词: histopathology;    deep learning;    image segmentation;    image annotation;    data augmentation;    generative adversarial networks;   

DOI  :  10.3389/fmed.2019.00222

来源: DOAJ

【 摘 要 】

The emergence of computational pathology comes with a demand to extract more and more information from each tissue sample. Such information extraction often requires the segmentation of numerous histological objects (e.g., cell nuclei, glands, etc.) in histological slide images, a task for which deep learning algorithms have demonstrated their effectiveness. However, these algorithms require many training examples to be efficient and robust. For this purpose, pathologists must manually segment hundreds or even thousands of objects in histological images, i.e., a long, tedious and potentially biased task. The present paper aims to review strategies that could help provide the very large number of annotated images needed to automate the segmentation of histological images using deep learning. This review identifies and describes four different approaches: the use of immunohistochemical markers as labels, realistic data augmentation, Generative Adversarial Networks (GAN), and transfer learning. In addition, we describe alternative learning strategies that can use imperfect annotations. Adding real data with high-quality annotations to the training set is a safe way to improve the performance of a well configured deep neural network. However, the present review provides new perspectives through the use of artificially generated data and/or imperfect annotations, in addition to transfer learning opportunities.

【 授权许可】

Unknown