Clinical trial · Observational
Constructing a Multimodal Imaging System to Predict the Risk of Heterochronous Metastasis of Rectal Cancer
Role of Microenvironment Analysis and MRI Radiomic Study in the Risk Stratification of Distant Metastases in Rectal Cancer
- Source
- ClinicalTrials.gov
- Retrieved
- Sep 8, 2026
- Layer
- normalized (units and labels harmonized; values unchanged)
- Run
- ING-CLINICALTRIALS-20260908-000001
Summary
Brief summary (as posted)
The goal of this observational study is to construct a multimodal intelligent model to predict the risk of heterochronous metastasis of rectal cancer, which is helpful for individualized diagnosis and treatment and follow-up planning. The main questions it aims to answer are: * what are the independent risk factors of distant metastasis (DM) in locally advanced rectal cancer (LARC) * What is the influence weight of the above factors on the heterochronous metastasis of LARC, and how to build a risk-prediction model This study will not affect or interfere with the routine medical diagnosis and treatment of participants, and will not increase the cost and risk of participants. Participant's information is protected and identified by a unique code.
Conditions
Conditions (2)
Free-text conditions as registered, with the CancerIndex entity they were reconciled to and the match type.
| Condition (as posted) | Mapped entity | Match | Confidence |
|---|---|---|---|
| Distant Metastasis | — | UNRESOLVED | — |
| Locally Advanced Rectal Cancer | Malignant Rectal Neoplasm | CURATED_BROADER | 0.78 |
Interventions
Interventions (1)
| Intervention | Type | Mapped drug | Match |
|---|---|---|---|
| No intervention was administrated to the two cohorts. | Other | — | UNRESOLVED |
Design
Arms and outcomes
Arms (2)
- label
- Training cohort
- description
- The patients were randomized into a training cohort (n ＝ 211) to train the model. The patients' clinicopathological data were reviewed, including age, sex, obesity, serum carcinoembryonic antigen and cancer antigen 19-9 levels, T- and N-stages evaluated by MRI, yp-T and yp-N stages evaluated by histopathology. The MR-T/N stages of the tumors were assessed by radiologists. The tumor region of interest was manually delineated on high-resolution oblique axial T2WI and generated the VOI using ITK-SNAP. Overall, 1229 features were extracted from each VOI. Biopsy specimens from colonoscopy were sectioned into 5 μm slices and stained with H\&E. Areas with both stromal and tumor cells presented on all four sides were selected to evaluate tumor stroma ratio using an automated scoring method with the highest proportion of stromal components in all measured areas recorded.
- interventionNames
- Other: No intervention was administrated to the two cohorts.
- label
- Validation cohort
- description
- The patients were randomized into a validation cohort (n ＝91) to verify the model. The patients' clinicopathological data were reviewed, including age, sex, obesity, serum carcinoembryonic antigen and cancer antigen 19-9 levels, T- and N-stages evaluated by MRI, yp-T and yp-N stages evaluated by histopathology. The MR-T/N stages of the tumors were assessed by radiologists. The tumor region of interest was manually delineated on high-resolution oblique axial T2WI and generated the VOI using ITK-SNAP. Overall, 1229 features were extracted from each VOI. Biopsy specimens from colonoscopy were sectioned into 5 μm slices and stained with H\&E. Areas with both stromal and tumor cells presented on all four sides were selected to evaluate tumor stroma ratio using an automated scoring method with the highest proportion of stromal components in all measured areas recorded.
Eligibility
Eligibility (as posted)
- Sex
- All
Show eligibility criteria text
Inclusion Criteria: * Newly diagnosed non-mucinous LARC (T3\~T4, or any T with N1\~2, M0) without previous treatment; * No concomitant malignancies or systemic disease; * Complete standard neoadjuvant chemoradiotherapy (NCRT) and radical surgery in our institute; * Underwent rectal MRI and colonoscopy within 2 weeks before NCRT. Exclusion Criteria: * Fail to meet any of the inclusion criteria; * Inadequate MR image quality for analysis, or lack of biopsy tissue for TSR assessment; * Incomplete clinical data or withdraw before last visit. A total of 578 eligible LARC cases were initially reviewed, 276 of which were excluded according to the exclusion criteria. Finally, 302 patients were enrolled in this study and randomized into a training cohort (n ＝ 211) and validation cohort (n ＝ 91).
References
Publications (0)
Data not yet available