Spatial analysis of tumor infiltrating lymphocytes based on deep learning using histopathology image to predict progression-free survival in colorectal cancer
Xu, H.; Cha, Y. J.; Clemenceau, J. R.; Choi, J.; Lee, S. H.; Kang, J.; Hwang, T. H.
Show abstract
PurposeThis study aimed to explore the prognostic impact of spatial distribution of tumor infiltrating lymphocytes (TILs) quantified by deep learning (DL) approaches based on digitalized whole slide images stained with hematoxylin and eosin in patients with colorectal cancer (CRC). MethodsThe prognostic impact of spatial distributions of TILs in patients with CRC was explored in the Yonsei cohort (n=180) and validated in the TCGA cohort (n=268). Concurrently, two experienced pathologists manually measured TILs at the most invasive margin as 0-3 by the Klintrup-Makinen (KM) grading method and compared to DL approaches. Interobserver agreement for TILs was measured using Cohens kappa coefficient. ResultsOn multivariate analysis of spatial TILs features derived by DL approaches and clinicopathological variables including tumor stage, Microsatellite instability, and KRAS mutations, TILs densities within 200 m of the invasive margin (f_im200) was remained as the most significant prognostic factor for progression-free survival (PFS) (HR 0.004 [95% CI, 0.0001-0.1502], p=.002) in the Yonsei cohort. On multivariate analysis using the TCGA dataset, f_im200 retained prognostic significance for PFS (HR 0.031, [95% CI 0.001-0.645], p=.024). Interobserver agreement of manual KM grading based on Cohens kappa coefficient was insignificant in the Yonsei ({kappa}=.109) and the TCGA ({kappa}=.121), respectively. The survival analysis based on KM grading showed statistically significant different PFS from the TCGA cohort, but not the Yonsei cohort. ConclusionsAutomatic quantification of TILs at the invasive margin based on DL approaches showed a prognostic utility to predict PFS, and could provide robust and reproducible TILs density measurement in patients with CRC. Data and Code AvailabilitySource code and data used for this study is available at the following link: https://github.com/hwanglab/TILs_Analysis
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Explainable, federated deep learning model predicts disease progression risk of cutaneous squamous cell carcinoma 95%
- Cell graph neural networks enable the digital staging of tumor microenvironment and precise prediction of patient survival in gastric cancer 95%
- Image-Based Consensus Molecular Subtyping in Rectal Cancer Biopsies and Response to Neoadjuvant Chemoradiotherapy 94%
Similar papers in this journal
- Computational analysis of pathological image enables interpretable prediction for microsatellite instability 95%
- Pyroptosis-related gene signatures can robustly diagnose skin cutaneous melanoma and predict the prognosis 95%
- Establishment of a prognosis prediction model based on pyroptosis-related signatures associated with the immune microenvironment and molecular heterogeneity in clear cell renal carcinoma 95%
Similar papers in this journal
- Predicting Prognosis and IDH Mutation Status for Patients with Lower-Grade Gliomas Using Whole Slide Images 95%
- Transcriptome Profiling and Characterization of Peritoneal Metastasis Ovarian Cancer Xenografts in Humanized Mice 94%
- Deeper insights into long-term survival heterogeneity of Pancreatic Ductal Adenocarcinoma (PDAC) patients using integrative individual- and group-level transcriptome network analyses 93%
Similar papers in this journal
- Self-Supervised Learning Reveals Clinically Relevant Histomorphological Patterns for Therapeutic Strategies in Colon Cancer 97%
- Teacher-student collaborated multiple instance learning for pan-cancer PDL1 expression prediction from histopathology slides 95%
- Artificial intelligence-based histopathology image analysis identifies a novel subset of endometrial cancers with distinct genomic features and unfavourable outcome 95%
Similar papers in this journal
- Mime: A flexible machine-learning framework to construct and visualize models for clinical characteristics prediction and feature selection 95%
- Finding new cancer epigenetic and genetic biomarkers from cell-free DNA by combining SALP-seq and machine learning：esophageal cancer as an example 93%
- Comparative Analysis of Pathology Foundation Models for Automated Detection of Tertiary Lymphoid Structures in H&E-Stained Digital Pathology Images 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.