Abstract 4322: AI assisted detection and characterization of tertiary lymphoid structures in patients with colorectal cancer

Abstract

Abstract Tertiary Lymphoid Structures (TLSs) are ectopic immune cell aggregates that form in response to abnormal physiology and inflammation. TLS presence in the tumor environment has been associated with positive clinical outcomes and response to immune checkpoint inhibition therapy. Using a fluorescent multiplex panel consisting of Pan-cytokeratin (PanCK), Programmed Death Ligand-1 (PD-L1), cluster of differentiation (CD) 8, CD3, and CD68 we developed a HALO-based artificial intelligence (AI) classifier to detect TLSs in colorectal cancer (CRC) tissue. In conjunction with cell-type and spatial analyses, we used the AI TLS classifier to characterize several features of the TLS and peri-TLS environment. We trained the AI classifier using 51 examples of TLSs from 8 patients, and applied it to images of 21 CRC patient tissues. TLSs were detected in 9/21 patient samples. We then used cellular detection and spatial analysis to characterize features of the TLS, including the germinal center (GC), T cell zone and peri-TLS area. We detected a higher cell density (Mean=12250 ±2039 SD; cells/mm2) within the interior of AI-detected GCs relative to the 1st 200 μm outside of the AI-defined GC border (8005±1870). In addition, we examined the spatial distribution of CD3+ and CD8+ T cells relative to the TLS GC. We found elevated CD3+ cell density in the interior of the GC (5784±1649) and within 200 μm of the GC border (5126±2239) which decreased at distances >200 μm from the GC border. We found CD8+ density to be elevated within the 1st 200 μm of the GC border (1903±1182) and declined 400 μm away from the GC border (963±828). The spatial distribution of T cells surrounding an area of high cell density is indicative of a T cell zone surrounding germinal center. Further analysis of the AI-detected TLS GCs indicated that PD-L1+ cell density was highest within the germinal center (355± 534;9) relative to the exterior of the germinal center (1st 150μm outside germinal center:276± 441). We created an AI classifier that can detect TLS(s) within patient tissue in the absence of a B-cell marker and confirmed that our AI classifier was detecting TLSs by characterizing canonical features of TLSs. Further exploration of the TLS and peri-TLS area may offer insights into immune-tumor interaction within the tumor microenvironment, and paired detection of TLSs in a clinical cohort with outcome data may predict patient response to immune checkpoint inhibitor therapy. Citation Format: Samantha Burg, Nathaniel Hart, Astin Powers, Wenjun Zhang. AI assisted detection and characterization of tertiary lymphoid structures in patients with colorectal cancer. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 4322.