Skip to Main Content
Principal Investigator
Shuoyu Xu
Bio-totem Pte Ltd
Position Title
Chief Scientific Officer
About this CDAS Project
PLCO (Learn more about this study)
Project ID
Initial CDAS Request Approval
Nov 22, 2021
Exploring prognostic value of tumor infiltrating lymphocytes (TILs) in multiple cancer types
Tumor-infiltrating lymphocytes (TILs) are important prognostic biomarkers in triple negative breast cancer (TNBC) as well as in many other types of solid tumors. The International Immuno-Oncology Biomarker Working Group (TIL-WG) has established a detailed reporting guideline for visual assessment of TILs (VTA) for TNBC which helps to reduce manual scoring variations but inherent limitations still exist. The development of new computational TIL assessment (CTA) methods is a promising solution to address these limitations. More importantly, quantitative TILs-based measurements derived from CTA methods could provide more insights on tumor microenvironment to facilitate better patient prognosis. We have previously developed and validated a CTA method for TILs assessment in two international triple-negative breast cancer cohorts[1]. We intend to further refine and validate our methods on multiple cancer types from a larger cohort such as PLCO trial.

[1] Sun, P., He, J., Chao, X., Chen, K., Xu, Y., Huang, Q., Yun, J., Li, M., Luo, R., Kuang, J. and Wang, H., 2021. A computational tumor-infiltrating lymphocyte assessment method comparable with visual reporting guidelines for triple-negative breast cancer. EBioMedicine, 70, p.103492.

1. Development and validation of deep learning based imagen analysis algorithm
1.1 Pan-cancer segmentation model to identify tumor, stroma and necrosis areas from WSI
1.2 Pan-cancer nuclei detection and classification model to identify tumor cell, lymphocyte, stroma cell and other cells.
2. Establishing TILs-based digital biomarkers for prognostic analysis
2.1 Conventional TILs metrics following guidelines from International TILS working group, such as intra-tumoral TILs, stroma-TILs, etc.
2.2 Spatial distribution related TILs metrics, including hotspot based measurements, graph based measurements, etc.
3 Exploring immune phenotypes based on TILs metrics
3.1 Classifying samples into immune inflamed, excluded and desert and studying its correlation with prognosis and treatment efficacy.


Prof Sun Peng, Sun Yat-sen University Cancer Center