Advanced Classification of Colon Tumors From CT Scans Using Deep Learning for Optimized Treatment Decision-making. (DeepColScan)

Advanced Classification of Colon Tumors From CT Scans Using Deep Learning for Optimized Treatment Decision-making : a Multicenter Study

This study aims to improve the classification of colon tumors using deep learning models trained on CT scans, specifically to distinguish between T1-T2 vs. T3-T4 stages and N- vs. N+ lymph node involvement. This classification is critical to guide preoperative treatment such as chemotherapy or immunotherapy. Given the limited accuracy of radiologists in current staging practice, automated image-based AI tools could enhance diagnostic precision and reproducibility, leading to more personalized and effective treatment planning. The investigator will develop and validate convolutional and transformer-based deep learning models using a large annotated dataset from multiple centers. Secondary objectives include fine-grained staging (T1 to T4), subgroup-specific models (MSS vs MSI), and predictive models for surgical

Study Overview

• Status: Not yet recruiting
• Conditions: Colonic Neoplasm

Detailed Description

This is a retrospective, non-interventional, observational study evaluating the use of deep learning methods to improve preoperative CT-based TNM staging in patients with colon cancer. The study is conducted across multiple sites within the AP-HP hospital network (Paris, France) and uses data extracted from the institutional Health Data Warehouse.

Radiologic accuracy in assessing tumor stage (T) and lymph node status (N) remains limited, despite being critical for selecting neoadjuvant treatments. Artificial intelligence models trained on annotated imaging data may provide more consistent, reproducible, and accurate classification.

The study cohort includes adult patients who underwent colon resection between January 2017 and November 2024, with a preoperative CT scan and corresponding pathology report. Eligible cases are identified using standardized diagnostic (ICD-10) and procedural (CCAM) codes. Imaging and clinical data are de-identified prior to analysis.

Several AI model architectures will be tested, including 3D convolutional neural networks and transformer-based approaches. CT scans will be pre-processed using standard pipelines; pathology labels will be extracted using natural language processing (NLP) techniques or manual review when needed. Model performance will be assessed through cross-validation and evaluated using AUC, F1-score, sensitivity, and specificity.

Exploratory analyses will include fine-grained tumor staging and the potential prognostic value of image-based features for clinical outcomes such as survival.

No study-related procedures are performed. All analyses are conducted on existing data, in compliance with French data protection and ethical regulations.

• Study Type: Observational
• Enrollment (Estimated): 1000

Contacts and Locations

• Study Contact: Name: Quentin Vanderbecq, MD; Phone Number: 00 33 1 49 28 20 00; Email: quentin.vanderbecq@aphp.fr
• Study Contact Backup: Name: Mathilde WAGNER, MD,PhD; Phone Number: 00 33 1 49 28 20 00; Email: mathilde.wagner@aphp.fr

Study Locations

• France
  • Paris, France, 75012
    • Departement of radiology, saint Antoin Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Adults (≥18 years) with pathologically confirmed colon cancer who underwent surgical resection at participating hospitals and had an available preoperative thoraco-abdominopelvic CT performed within the institution and linked to a pathology report containing TNM staging within 90 days of surgery. Imaging and reports extracted from institutional data warehouse; ambiguous or missing labels resolved by manual medical review.

Description

Inclusion Criteria:

Adults who underwent colon resection surgery at an AP-HP hospital between 01/01/2017 and 01/11/2024, with:

A preoperative abdominopelvic CT scan available within 60 days prior to surgery.

A corresponding pathology report (anatomopathological results) available within 90 days post-surgery.

Colon resection identified by CCAM procedure codes:

HHFA002, HHFA004, HHFA005, HHFA006, HHFA008, HHFA009, HHFA010, HHFA014, HHFA017, HHFA018, HHFA021, HHFA022, HHFA023, HHFA024, HHFA026, HHFA028, HHFA029, HHFA030, HHFA031, HHFC040, HHFC296.

Confirmed diagnosis of colon tumor by ICD-10 code:

C18* (colonic neoplasms).

Exclusion Criteria:

Patients who received neoadjuvant chemotherapy prior to surgery, identified by ICD-10 codes Z511 or Z512 recorded before the surgical act.

These exclusions will be refined and confirmed through manual medical record review to ensure accuracy.

Absence of usable CT imaging or anatomical pathology data linked to the surgical event.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort
Tran-validation group; Adults with pathologically confirmed colon cancer who underwent preoperative thoraco-abdominopelvic CT and subsequent colectomy at participating centers; cases meeting imaging and pathology quality criteria used for model training and internal cross-validation. AI / Deep Learning CT Analysis: Retrospective analysis of existing preoperative CT scans and linked pathology/clinical data to develop and evaluate automated staging models. No experimental drug, device, or procedure is administered.
Test group; Distinct subset (aleatory taken at the beginning of model training) of eligible colon cancer cases withheld from model development to provide independent performance validation for T and N classification models and exploratory secondary analyses.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic performance of CT-based deep learning models for T (T1-2 vs T3-4) and N (N- vs N+) staging.	Area under the ROC curve (AUC) and F1-score of deep learning models in (a) classifying early vs advanced T stage (T1-2 vs T3-4) and (b) nodal status (N- vs N+) compared with pathology gold standard. Sensitivity, specificity, PPV, NPV reported as supportive metrics; model performance compared to historical radiologist benchmarks when available.	Index preoperative CT through postoperative pathology report (within 90 days of surgery).

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Detection performance for T4 tumors on preoperative CT.	AUC, F1, sensitivity, specificity for binary classification T4 vs non-T4 (T1-3). Analyses stratified by tumor location and contrast phase when data permit.	Index CT to pathology confirmation (≤90 days post-surgery).
Multiclass T-stage classification accuracy (T1, T2, T3, T4).	Macro-averaged F1, per-class sensitivity/specificity, confusion matrix, and Cohen's kappa comparing model-predicted 4-class T stage with pathology.	Index CT to pathology confirmation (≤90 days).
Prognostic value of CT-derived model features for clinical outcomes and survival.	Association between model outputs (probabilities, embeddings) and (a)coverall survival, (b) disease-free survival. Evaluated using Kaplan-Meier analysis, log-rank tests, and multivariable Cox models adjusted for clinical covariates where available.	From index CT to last follow-up (up to 5 years, or maximum available follow-up in EHR).

Collaborators and Investigators

• Sponsor: Assistance Publique - Hôpitaux de Paris
• Collaborators: Institut National de Recherche en Informatique et en Automatique
• Investigators: Principal Investigator: Quentin Vanderbecq, MD, Assistance Publique - Hôpitaux de Paris

Study record dates

Study Major Dates

• Study Start (Estimated): February 1, 2026
• Primary Completion (Estimated): February 1, 2028
• Study Completion (Estimated): February 1, 2028

Study Registration Dates

• First Submitted: February 6, 2026
• First Submitted That Met QC Criteria: February 6, 2026
• First Posted (Actual): February 12, 2026

Study Record Updates

• Last Update Posted (Actual): February 12, 2026
• Last Update Submitted That Met QC Criteria: February 6, 2026
• Last Verified: February 1, 2025

More Information

Terms related to this study

• Keywords: machine learning; colorectal neoplasms; AI; Colon cancer; deep learning; CT scan; radiology; tumor staging; TNM classification
• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Intestinal Diseases; Gastrointestinal Neoplasms; Digestive System Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Intestinal Neoplasms; Rectal Diseases; Colonic Diseases; Colorectal Neoplasms; Colonic Neoplasms
• Other Study ID Numbers: APHP251408

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No