Deep learning-based image analysis methods for brightfield-acquired multiplex immunohistochemistry images

Diagnostic Pathology

Rajarsi Gupta¹  Syeda Areeha Batool¹  Chao Chen¹  Joel Saltz¹  Tahsin Kurc¹  Maozheng Zhao²  David Paredes²  Dimitris Samaras²  Shahira Abousamra²  Kenneth R. Shroyer³  Danielle J. Fassler³  Luisa Escobar-Hoyos⁴  Beatrice S. Knudsen⁵ 

[1] Department of Biomedical Informatics, Stony Brook University Renaissance School of Medicine, 101 Nicolls Rd, 11794, Stony Brook, USA;Department of Computer Science, Stony Brook University, 100 Nicolls Rd, 11794, Stony Brook, USA;Department of Pathology, Stony Brook University Renaissance School of Medicine, 101 Nicolls Rd, 11794, Stony Brook, USA;Department of Pathology, Stony Brook University Renaissance School of Medicine, 101 Nicolls Rd, 11794, Stony Brook, USA;Department Therapeutic Radiology, Yale University, 15 York Street, 06513, New Haven, CT, USA;Department of Pathology, University of Utah, 2000 Circle of Hope, 84112, Salt Lake City, UT, USA;

关键词: Multiplex immunohistochemistry;    Digital pathology image analysis;    Deep learning;    Tumor immune microenvironment;   

DOI  :  10.1186/s13000-020-01003-0

来源: Springer

【 摘 要 】

BackgroundMultiplex immunohistochemistry (mIHC) permits the labeling of six or more distinct cell types within a single histologic tissue section. The classification of each cell type requires detection of uniquely colored chromogens localized to cells expressing biomarkers of interest. The most comprehensive and reproducible method to evaluate such slides is to employ digital pathology and image analysis pipelines to whole-slide images (WSIs). Our suite of deep learning tools quantitatively evaluates the expression of six biomarkers in mIHC WSIs. These methods address the current lack of readily available methods to evaluate more than four biomarkers and circumvent the need for specialized instrumentation to spectrally separate different colors. The use case application for our methods is a study that investigates tumor immune interactions in pancreatic ductal adenocarcinoma (PDAC) with a customized mIHC panel.MethodsSix different colored chromogens were utilized to label T-cells (CD3, CD4, CD8), B-cells (CD20), macrophages (CD16), and tumor cells (K17) in formalin-fixed paraffin-embedded (FFPE) PDAC tissue sections. We leveraged pathologist annotations to develop complementary deep learning-based methods: (1) ColorAE is a deep autoencoder which segments stained objects based on color; (2) U-Net is a convolutional neural network (CNN) trained to segment cells based on color, texture and shape; and (3) ensemble methods that employ both ColorAE and U-Net, collectively referred to as ColorAE:U-Net. We assessed the performance of our methods using: structural similarity and DICE score to evaluate segmentation results of ColorAE against traditional color deconvolution; F1 score, sensitivity, positive predictive value, and DICE score to evaluate the predictions from ColorAE, U-Net, and ColorAE:U-Net ensemble methods against pathologist-generated ground truth. We then used prediction results for spatial analysis (nearest neighbor).ResultsWe observed that (1) the performance of ColorAE is comparable to traditional color deconvolution for single-stain IHC images (note: traditional color deconvolution cannot be used for mIHC); (2) ColorAE and U-Net are complementary methods that detect six different classes of cells with comparable performance; (3) combinations of ColorAE and U-Net in ensemble methods outperform ColorAE and U-Net alone; and (4) ColorAE:U-Net ensemble methods can be employed for detailed analysis of the tumor microenvironment (TME).SummaryWe developed a suite of scalable deep learning methods to analyze 6 distinctly labeled cell populations in mIHC WSIs. We evaluated our methods and found that they reliably detected and classified cells in the PDAC tumor microenvironment. We also utilized the ColorAE:U-Net ensemble method to analyze 3 mIHC WSIs with nearest neighbor spatial analysis. We demonstrate a proof of concept that these methods can be employed to quantitatively describe the spatial distribution of immune cells within the tumor microenvironment. These complementary deep learning methods are readily deployable for use in clinical research studies.

【 授权许可】

CC BY