Deep Learning Based Automatic Immune Cell Detection for Immunohistochemistry Images

Abstract

Abstract. Immunohistochemistry (IHC) staining is a widely used technique in the diagnosis of abnormal cells such as cancer. For instance, it can be used to determine the distribution and localization of the differentially expressed biomarkers of immune cells (such as T-cells or B-cells) in cancerous tissue for an immune response study. Typically, the immunological data of interest includes the type, density and location of the immune cells within the tumor samples; this data is of particular interest to pathologists for accurate patient survival prediction. However, to manually count each subset of immune cells under a bright-field microscope for each piece of IHC stained tissue is usually extremely tedious and time consuming. This makes automatic detection very attractive, but it can be very challenging due to the wide variety of cell appearances resulting from different tissue types, block cuttings, and staining processes. This paper presents a novel method for automatic immune cell counting on digitally scanned images of IHC stained slides. The method first uses a sparse color unmixing technique to separate the IHC image into multiple color channels that correspond to different cell structures. Since the immune cell biomarkers that we are interested in are membrane markers, the detection problem is formulated into a deep learning framework using the membrane image channel. The algorithm is evaluated on a clinical data set containing a large number of IHC slides and demonstrates more effective detection than the existing technique and the result is also in accordance with the human observer's output.

In Silico Labeling: Predicting Fluorescent Labels in Unlabeled Images

“…DL has been applied to achieve useful advances in basic segmentation of microscopy images, an initial step in image analysis to distinguish foreground from background (Chen and Chefd’hotel, 2014; Dong et al, 2015; Mao et al, 2015; Ronneberger et al, 2015; Van Valen et al, 2016; Xu et al, 2016), and on segmented images of morphologically simple cells to classify cell shape (Zhong et al, 2012) and predict mitotic state (Held et al, 2010) and cell lineage (Buggenthin et al, 2017). (Long et al, 2010) applied DL methods to unlabeled and unsegmented images of low-density cultures with mixtures of three cell types and trained a network to classify cell types.…”

Relevance of deep learning to facilitate the diagnosis of HER2 status in breast cancer

“…Among deep learning models, convolutional neural networks (ConvNets) is arguably the most studied and validated approach in a range of image understanding tasks such as human face detection1819 and hand-written character recognition20. The pathology community is showing increasing interest in deep learning21 as demonstrated by studies reporting deep learning based image analysis that can accurately localize cells, classify cells into different cell types22232425 and detect tumour regions within tissues2627282930. Further studies are required to assess the validity and utility of deep learning for clinical decision making.…”

Automating cell detection and classification in human brain fluorescent microscopy images using dictionary learning and sparse coding

“…A natural evolution of our method would be the use of deep learning techniques, which have been presenting highly encouraging results for cell detection [62, 63] and histological diagnosis [64], in recent publications. One of our biggest challenges in incorporating deep learning in our studies would be the lack of enough samples for training deep learning neural networks.…”