16 December 2020 in Nature
21 February 2017 in Scientific Reports
Immunohistochemistry (IHC) is a widely used technique in pathology to evidence protein expression in tissue samples. However, this staining technique is known for presenting inter-batch variations. Whole slide imaging in digital pathology offers a possibility to overcome this problem by means of image normalisation techniques. In the present paper we propose a methodology to objectively evaluate the need of image normalisation and to identify the best way to perform it. This methodology uses tissue microarray (TMA) materials and statistical analyses to evidence the possible variations occurring at colour and intensity levels as well as to evaluate the efficiency of image normalisation methods in correcting them. We applied our methodology to test different methods of image normalisation based on blind colour deconvolution that we adapted for IHC staining. These tests were carried out for different IHC experiments on different tissue types and targeting different proteins with different subcellular localisations. Our methodology enabled us to establish and to validate inter-batch normalization transforms which correct the non-relevant IHC staining variations. The normalised image series were then processed to extract coherent quantitative features characterising the IHC staining patterns.
1 October 2018 in Medical Image Analysis
14 August 2014 in Journal of the American Medical Informatics Association
Background and objective Extracting accurate information from complex biological processes involved in diseases, such as cancers, requires the simultaneous targeting of multiple proteins and locating their respective expression in tissue samples. This information can be collected by imaging and registering adjacent sections from the same tissue sample and stained by immunohistochemistry (IHC). Registration accuracy should be on the scale of a few cells to enable protein colocalization to be assessed. Methods We propose a simple and efficient method based on the open-source elastix framework to register virtual slides of adjacent sections from the same tissue sample. We characterize registration accuracies for different types of tissue and IHC staining. Results Our results indicate that this technique is suitable for the evaluation of the colocalization of biomarkers on the scale of a few cells. We also show that using this technique in conjunction with a sequential IHC labeling and erasing technique offers improved registration accuracies. Discussion Brightfield IHC enables to address the problem of large series of tissue samples, which are usually required in clinical research. However, this approach, which is simple at the tissue processing level, requires challenging image analysis processes, such as accurate registration, to view and extract the protein colocalization information. Conclusions The method proposed in this work enables accurate registration (on the scale of a few cells) of virtual slides of adjacent tissue sections on which the expression of different proteins is evidenced by standard IHC. Furthermore, combining our method with a sequential labeling and erasing technique enables cell-scale colocalization.
15 October 2019 in Frontiers in Medicine
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.