Best of ASCO - 2014 Annual Meeting

 

Welcome

Publication-only abstracts (abstract number preceded by an "e"), published in conjunction with the 2019 ASCO Annual Meeting but not presented at the Meeting, can be found online only.

Quantitative image profiling of the tumor microenvironment on double stained immunohistochemistry images using deep learning.

Sub-category:
Molecular Diagnostics and Imaging

Category:
Developmental Therapeutics and Tumor Biology (Nonimmuno)

Meeting:
2019 ASCO Annual Meeting

Abstract No:
e14619

Citation:
J Clin Oncol 37, 2019 (suppl; abstr e14619)

Author(s): Mate Levente Nagy, Anna Juncker-Jensen, Ben Ovadia, Robert Smale, Karen Yamamoto, Josette William, Nicholas Hoe, Raghav Padmanabhan; NeoGenomics, Aliso Viejo, CA

Abstract Disclosures

Abstract:

Background: Spatial locations of immune cells in the tumor microenvironment (TME) correlate with clinical outcome in cancers. A worse patient outcome has been reported in oral squamous cancer for individuals with an increased number of regulatory T cells within 30µm of CD8+ cells [1]. The spatial relationship between CD8+ and PD-L1+ cells has become an area of interest for understanding PD-L1 inhibition. The combined assessment of CD8 and PD-L1 in NSCLC tumors was shown to outperform CD8 or PD-L1 alone as prognostic markers for predicting treatment with immune checkpoint inhibitors [2]. Methods: As reported in these cases, quantifying spatial relationships between two biomarkers is valuable in providing clinical insights. Spatial analytics of the TME requires accurate cell segmentation and classification. To that end, NeoGenomics has developed a deep learning pipeline to automatically segment and classify cells from whole slide double stained IHC images. Results: In this study, we performed IHC double staining and cell classification analysis on two sets of assays (CD8+ PD-L1+ and CD8+ FoxP3+) in NSCLC tumors by modifying our MultiOmyx analysis pipeline [3]. In addition to cell segmentation and classification image outputs, we also generate tables with cell morphological information, phenotype counts and densities, and biomarker intensities that can be used to define H-score-like measures. Advanced spatial analytics is performed to identify clustering patterns of various phenotypes. These analyses enable investigation of complex cell interactions in TMEs. Conclusions: NeoGenomics quantitative double stained IHC assay is compatible with any two biomarkers of interest even if they are expressed on the same cell as long as the sub-cellular localization of the markers is different (membrane CD8, nuclear FoxP3). The combination of double staining for CD8+ PD-L1+ or CD8+ FoxP3+ and quantifying spatial relationships between the two biomarkers is capable of providing the needed context to guide treatment decisions. References:

Feng Z et al., JCI Insight. 2017 Jul 20:e93652

Steele KE et al., J Immunother Cancer 2018;6:20

Nagy ML et al., AACR Annual Meeting 2018; April 14-18, 2018; Chicago, IL

 
Other Abstracts in this Sub-Category:

 

1. Image-guided surgery for tumor agnostic detection of solid tumors using the pH-activated micellar imaging agent ONM-100.

Meeting: 2019 ASCO Annual Meeting Abstract No: 3068 First Author: Floris Jan Voskuil
Category: Developmental Therapeutics and Tumor Biology (Nonimmuno) - Molecular Diagnostics and Imaging

 

2. Radiomics features to identify distinct subtypes of triple-negative breast cancers.

Meeting: 2019 ASCO Annual Meeting Abstract No: 3069 First Author: Haruka Itakura
Category: Developmental Therapeutics and Tumor Biology (Nonimmuno) - Molecular Diagnostics and Imaging

 

3. [18F] Fluciclatide PET as a biomarker of clinical response to combination therapy of pazopanib and paclitaxel in patients with platinum-resistant or platinum-refractory advanced ovarian cancer: Results of a phase Ib study.

Meeting: 2019 ASCO Annual Meeting Abstract No: 3070 First Author: Rohini Sharma
Category: Developmental Therapeutics and Tumor Biology (Nonimmuno) - Molecular Diagnostics and Imaging

 

More...