WeChat Mini Program
Old Version Features

    • AI Assisted Detection and Characterization of Tertiary Lymphoid Structures in Patients with Colorectal Cancer

    Samantha Burg,Nathaniel Hart,Astin Powers, Wenjun Zhang

    CANCER RESEARCH（2023）

    Cited 0|Views3
    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.
    More
    Translated text
    Key words
    Tumor Microenvironment
    求助PDF
    上传PDF
    View via Publisher
    Bibtex
    AI Read Science
    AI Summary
    AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
    Example
    Background
    Key content
    Introduction
    Methods
    Results
    Related work
    Fund
    Key content
    • Pretraining has recently greatly promoted the development of natural language processing (NLP)
    • We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
    • We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
    • The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
    • Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
    Upload PDF to Generate Summary
    Must-Reading Tree
    Example
    Generate MRT to find the research sequence of this paper
    Data Disclaimer
    The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
    Chat Paper
    Summary is being generated by the instructions you defined