Artificial intelligence-guided tissue analysis combined with immune infiltrate assessment predicts stage III colon cancer outcomes in PETACC08 study

Abstract

ObjectiveDiagnostic tests, such as Immunoscore, predict prognosis in patients with colon cancer. However, additional prognostic markers could be detected on pathological slides using artificial intelligence tools.DesignWe have developed a software to detect colon tumour, healthy mucosa, stroma and immune cells on CD3 and CD8 stained slides. The lymphocyte density and surface area were quantified automatically in the tumour core (TC) and invasive margin (IM). Using a LASSO algorithm, DGMate (DiGital tuMor pArameTErs), we detected digital parameters within the tumour cells related to patient outcomes.ResultsWithin the dataset of 1018 patients, we observed that a poorer relapse-free survival (RFS) was associated with high IM stromal area (HR 5.65; 95% CI 2.34 to 13.67; p<0.0001) and high DGMate (HR 2.72; 95% CI 1.92 to 3.85; p<0.001). Higher CD3+ TC, CD3+ IM and CD8+ TC densities were significantly associated with a longer RFS. Analysis of variance showed that CD3+ TC yielded a similar prognostic value to the classical CD3/CD8 Immunoscore (p=0.44). A combination of the IM stromal area, DGMate and CD3, designated ‘DGMuneS’, outperformed Immunoscore when used in estimating patients’ prognosis (C-index=0.601 vs 0.578, p=0.04) and was independently associated with patient outcomes following Cox multivariate analysis. A predictive nomogram based on DGMuneS and clinical variables identified a group of patients with less than 10% relapse risk and another group with a 50% relapse risk.ConclusionThese findings suggest that artificial intelligence can potentially improve patient care by assisting pathologists in better defining stage III colon cancer patients’ prognosis.

Prognostic implications of metabolism-associated gene signatures in colorectal cancer

“…The model summarizes all clinical points to provide numerical possibilities for clinical outcomes such as OS, relapse, and drug nonadherence. In addition to traditional clinicopathologic features such as TNM staging, tumor size, and histological subtypes, risk scores based on genetic markers can also be incorporated into a predictive nomogram model to predict clinical outcomes (Reichling et al, 2019;Sjoquist et al, 2018). A nomogram predicted 3-and 5-year recurrence-free survival rates for non-small cell lung cancer and gave a prognostic score calculated by the autophagy gene signature (Liu et al, 2019).…”

“…The R-package ''survival ROC'' drew the Receiver Operating Characteristic (ROC) curve, which was used to investigate the sensitivity and specificity of the survival prediction by the gene marker risk score (Le, Yapp & Yeh, 2019). Area Under Curve (AUC) served as an indicator of prognostic veracity (Le, 2019;Sachs, 2017). The risk curve, survival state diagram, and heatmap were drawn based on the different risk scores of the patients.…”

Adjuvant Chemotherapy for Stage III Colon Cancer

“…The results of Immunoscore ® in the IDEA-France trial (including 1062 patients), recently published, have confirmed the prognostic value of Immunoscore ® in stage III CC and a beneficial effect of 6 months of FOLFOX/CAPOX in high or intermediate Immunoscore ® patients, independently of high-risk/low-risk group (T4/N2 or T1-3/N1), in contrast to patients with a low Immunoscore, for whom 6 months of treatment did not seem to improve patient outcomes [78]. A recent work using artificial intelligence showed that a predictive nomogram based on immune infiltrates and clinical variables identified a group of patients with less than 10% relapse risk and a group with a 50% relapse risk in stage III patients [79]. These findings suggest that machine learning software can assist physicians and pathologists to better define patients' prognosis.…”

Immune landscape and biomarkers for immuno-oncology in colorectal cancers

“…Reichling et al [21] performed whole-slide imaging analysis of 1,018 stage III colon cancers in the PETACC08 study. They developed software to detect colon cancer, normal mucosa, stroma, and immune cells on CD3-and CD8-stained slides.…”