The prognostic value of immunoscore in the early-onset colorectal cancer

Abstract

Background: The purpose of this study was to explore the prognostic value of Immunoscore in patients with early-onset colorectal cancer.

Methods: We retrospectively analyzed 708 colorectal adenocarcinoma patients (2017-2020), ultimately including 36 early-onset colorectal cancer cases after exclusions. CD3+/CD8 + lymphocytes were quantified using immunohistochemistry and a self-trained neural network model from Cellpose 2.0. Immunoscore was calculated based on T cell densities in tumor cores and invasive margins, stratified as high or low. Prognostic associations were assessed via Kaplan-Meier analysis, Cox regression, and restricted cubic spline models. Results of Cox regression was validated by post-hoc analysis.

Results: Of all early-onset colorectal cancer patients, 23(63.9%) patients were graded as Immunoscore-high, 13(36.1%) were graded as Immunoscore-low. The self trained model achieved high consistency with manual counting. High Immunoscore correlated with earlier clinical stages (stage I/II: P = 0.011), reduced metastasis risk (N0, P = 0.042; M0, P = 0.009), and lower mortality (P = 0.009). Univariate Cox regression analysis identified Immunoscore as a possible predictor for overall survival (Hazard Ratio = 5.82, P = 0.030) and progression free survival (Hazard Ratio = 3.68, P = 0.014). The Post-hoc power analysis showed the type II error probability (β) of univariate Cox analysis for overall survival with a hazard ratio of 5.82 was 0.282 (28.2%), while for progression free survival with a hazard ratio of 3.68, β was 0.006 (0.6%). Restricted cubic spline showed that the influence of CD3+/CD8 + cells in different region on prognosis was not simply linear. Although Immunoscore didn't remain statistically significant as an independent predictor of OS (Hazard Ratio = 4.76; P = 0.138) and PFS (Hazard Ratio = 1.83; P = 0.360) in multivariate Cox regression analysis, stratified Kapan-Meier curves by MMR status and clinical stage showed well separation.

Conclusion: Immunoscore can serve as a possible indicator in predicting prognosis of patients with early-onset colorectal cancer, but still need large sample research validation.

Keywords: Cellpose 2.0; Early onset colorectal cancer; Immunoscore; Machine learning.

Fig. 1

Flow chart of patients inclusion and exclusion process

Fig. 2

Training and counting process of the model. (a) Original picture from IM region in a CD3 + stained slide. (b) Example of processed picture. (c) Visualization of counting results. (d) Each cell in stained slides is represented by features (e.g., color, size, shape) within multidimensional space. While positive cells (red spheres) could be distinguished using only two critical features. By eliminating one axis, we reduced data complexity from 3D to 2D representation and simplified model training. (e) Model training process. (f) Intraclass correlation coefficient between model and manual counting results. ICC, intraclass correlation coefficient

Fig. 3

Cell density and IS. (a) Regional division of IM (red area) and CT (green area). Red boxes are micromatrices selected randomly. (b) Distribution of cell density in different regions. (c) Calculation process of immunoscore. Immunoscore 5 levels in total, IS0, IS1, IS2, IS3, IS4. Among them, IS0-1 are graded as IS-Low, IS2-4 are graded as IS-High. CT, core of tumor; IM, invasive margin; IS, immunoscore

Fig. 4

Restricted cubic spline analysis of the effect of CD3+/CD8 + cells in CT and IM region on prognosis. The influence of density of CD3 + cells in CT region on OS and PFS was not linear. As the cell density increasing, CD3 + cells in CT region became the risk factor on prognosis. While low density of CD8 + cells was protective factor of prognosis. CT, core of tumor; IM, invasive margin

Fig. 5

Kaplan-Meier survival curves of early-onset colorectal cancer patients stratifed by immunoscore. (a) K-M curves for OS, (b) K-M curves for PFS in patients with EOCRC in different IS groups. OS, overall survival; PFS, progression free survival; IS, immunoscore

Fig. 6

Kaplan-Meier survival curves of dMMR EOCRC patients and pMMR EOCRC patients stratifed by IS. (a) K-M curves for OS, (b) K-M curves for PFS in dMMR EOCRC patients in different IS groups. (c) K-M curves for OS, (d) K-M curves for PFS in pMMR EOCRC patients in different IS groups. OS, overall survival; PFS, progression free survival; IS, immunoscore

Fig. 7

Kaplan-Meier survival curves of stage I-II EOCRC patients and stage III-IV EOCRC patients stratifed by IS. (a) K-M curves for OS, (b) K-M curves for PFS in stage I-II EOCRC patients in different IS groups. (c) K-M curves for OS, (d) K-M curves for PFS in stage III-IV EOCRC patients in different IS groups. OS, overall survival; PFS, progression free survival; IS, immunoscore

Fig. 8

Post-hoc power analysis of the univariate Cox regression results for IS. (a) When the HR of IS for OS exceeded 6.99, the statistical power reached 0.80. (b) When the HR of IS for PFS exceeded 2.28, the statistical power reached 0.80. IS, immunoscore; HR, hazard ratio; OS, overall survival; PFS, progression free survival