The goal of this study is to test better ways to predict if cancer will return after surgery in adults (18+) who have been diagnosed with stage II or III colon cancer.

The main questions it aims to answer are:

• Can computer programs (Artificial Intelligence) and special blood tests give more accurate information about the risk of cancer returning than the methods doctors use today?
• Does combining these new tests help doctors better understand which patients really need chemotherapy and which do not?

Researchers will compare the new computer and blood tests to the standard hospital methods used now to see if the new way is more accurate in predicting the cancer's behavior

Participants will:

• Sign a form saying they agree to take part in the study
• Have their standard surgery to remove the tumor
• Give a few extra teaspoons of blood during their regular, scheduled hospital visits
• Allow researchers to scan and study a small piece of the tumor that was already removed during surgery
• Continue with their normal hospital check-ups for up to five years so researchers can track their health

The MARBLE study is a prospective, multicentric, single-arm exploratory trial designed to integrate novel tissue- and blood-based prognostic modalities to improve risk stratification for patients with Stage II and III colon cancer. The study evaluates three primary prognostic modalities:

• Pathological Tumor-Node-Metastasis (pTNM) staging
• Machine Learning (ML) Histopathology: A validated graph neural network model analyzes digitized hematoxylin and eosin (H&E) stained slides to generate survival predictions and predict regional gene expression independent of pTNM stage
• Multi-modal ctDNA Assay: An in-house circulating tumor DNA (ctDNA) assay that moves beyond mutation detection by profiling epigenomic markers and genome-wide fragmentomic patterns in cell-free DNA (cfDNA) to enhance sensitivity for minimal residual disease (MRD).

Study Design and Workflow Participants are stratified post-surgery into four treatment-related groups (A-D) that reflect real-world standard-of-care (SoC) pathways rather than randomized arms:

• Group A: Low-risk Stage II (no adjuvant chemotherapy).
• Group B/C: Intermediate to high-risk Stage II/III (3-6 months of adjuvant chemotherapy).
• Group D: High-risk Stage III (6 months of chemotherapy), featuring intensified longitudinal sampling every 6 months for 36 months post-treatment to capture MRD dynamics.

Statistical Approach The primary analysis involves comparing mono-modal and multi-modal risk models to evaluate their prognostic performance for Time to Recurrence (TTR).

Technical evaluation will utilize Cox proportional hazards models, assessing discrimination via ΔC-index, model fit through likelihood ratio testing, and clinical utility using Net Reclassification Improvement (NRI). The study also quantifies the lead time between molecular (ctDNA) and radiological recurrence.

Inclusion Criteria:

1. Voluntary written informed consent of the participant or their legally authorized representative has been obtained prior to any screening procedures.
2. Male and female participants, at least 18 years of age at the time of signing the Informed Consent Form (ICF).
3. Newly diagnosed primary colon tumor clinically and/or histologically consistent with localized colon adenocarcinoma and planned for curative-intent surgical resection.
4. Clinical stage compatible with non-metastatic disease at time of screening and considered eligible for standard curative-intent management according to investigator assessment.
5. WHO (ECOG) performance status ≤ 3 at baseline.

Exclusion Criteria:

1. Participant has been diagnosed with metastatic disease (Stage IV)
2. Participant has been diagnosed with rectal cancer
3. Participant has been diagnosed with synchronous primary colon tumors (i.e., presence of two or more primary colon tumors detected simultaneously at diagnosis)
4. Participant has received prior systemic therapy (chemotherapy, targeted therapy, immunotherapy, or radiotherapy) for colon cancer
5. Participation in an interventional Study with an investigational medicinal product (IMP) or device within 30 days prior to inclusion.
6. Participant had prior history of colon cancer requiring systemic treatment or major colorectal oncologic surgery.
7. Any severe, uncontrolled, or life-threatening medical condition that, in the opinion of the investigator, could interfere with study participation, interpretation of study assessments, or pose excessive risk to the participant (e.g. severe cardiac, hepatic, renal, or uncontrolled infectious disease).

The MARBLE study focuses on a target population of approximately 400 adult participants with pathologically confirmed Stage II or III colon cancer. To achieve this enrollment, the study plans to screen up to 500 patients who are receiving standard-of-care surgical treatment for suspected localized colon cancer.

There are currently no plans to share de-identified individual participant data with the general public. This is to ensure the strict protection of participant confidentiality and the security of personal health information as required by the General Data Protection Regulation (GDPR) and Belgian law