Instance segmentation of immune cells in human lupus nephritis using deep learning: comparing performance on sample preparation and staining panels

Madeleine S. Durkee; Rebecca Abraham; Adam Sibley; Benjamin Cifu; Junting Ai; Vladimir M. Liarski; Marcus R. Clark; Maryellen L. Giger

doi:10.1117/12.2545110

17 February 2020 Instance segmentation of immune cells in human lupus nephritis using deep learning: comparing performance on sample preparation and staining panels

Madeleine S. Durkee, Rebecca Abraham, Adam Sibley, Benjamin Cifu, Junting Ai, Vladimir M. Liarski, Marcus R. Clark, Maryellen L. Giger

Author Affiliations +

Proceedings Volume 11243, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues XVIII; 112430T (2020) https://doi.org/10.1117/12.2545110
Event: SPIE BiOS, 2020, San Francisco, California, United States

Abstract

Computer vision and deep learning are integral tools in the improvement of high-throughput analysis of cellular images. Specifically, optimization of algorithms for object detection and instance segmentation tasks are important in cellular image analysis to segment and classify multi-object, multi-class images. In this work, we employ an instance segmentation pipeline with Mask RCNN, using a ResNet-101 and Feature Pyramid Network convolutional backbone to segment and classify T cells and antigen presenting cells (APCs) in multi-channel fluorescence confocal images of lupus nephritis biopsies. This task was first performed on a dataset of fresh frozen biopsies stained for T cells (CD3 and CD4) and two APC populations: 1) myeloid dendritic cells (BDCA1 and CD11c), and 2) plasmacytoid dendritic cells (BDCA2 and CD123). The network achieved an average sensitivity of 0.82, specificity of 0.91, and Jaccard index of 0.79 across all cell types. However, relative to fresh frozen tissue, samples prepared through formalin fixation and paraffin embedding (FFPE) provide larger potential datasets for investigating immune activity. Training this same network architecture on an FFPE database of lupus nephritis tissue stained with the same antibody panel, the network achieved an average sensitivity of 0.82, specificity of 0.92, and Jaccard index of 0.77 across all cell types. In addition to working with FFPE tissue, it would also be beneficial to identify APCs with a single stain and image more cell types with a single staining panel. We have trained this network on a single-stained APC panel FFPE dataset to achieve an average sensitivity of 0.79, specificity of 0.86, and Jaccard index of 0.63 across all cell types. These three trained networks were used to assess differences in cell shape features between fixation and staining protocols.

Conference Presentation

Citation Download Citation

Madeleine S. Durkee, Rebecca Abraham, Adam Sibley, Benjamin Cifu, Junting Ai, Vladimir M. Liarski, Marcus R. Clark, and Maryellen L. Giger "Instance segmentation of immune cells in human lupus nephritis using deep learning: comparing performance on sample preparation and staining panels", Proc. SPIE 11243, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues XVIII, 112430T (17 February 2020); https://doi.org/10.1117/12.2545110

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available