Deep learning and body composition model for predicting postoperative complications in colorectal cancer
Source check: Source checked. Not independent scientific confirmation.
Finding: Body-composition CT segmentation and 3D ResNet-18 features are combined with clinical predictors; 154 retrospective CRC cases (99 development, 55 external validation), best combined AUC 0.944/0.855.
Technology: CT body-composition segmentation and 3D ResNet-18 image features are combined with clinical predictors to estimate postoperative complications in colorectal cancer.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- CT body-composition segmentation and 3D ResNet-18 image features are combined with clinical predictors to estimate postoperative complications in colorectal cancer.
- Test and result
- Body-composition CT segmentation and 3D ResNet-18 features are combined with clinical predictors; 154 retrospective CRC cases (99 development, 55 external validation), best combined AUC 0.944/0.855. Methods describe the segmentation, feature extraction and model comparison; Results report an independent two-center validation cohort and AUC. Prognostic association only; no treatment effect or patient-outcome improvement established.
- Limitation / still unknown
- limited to the stated retrospective/in-silico/prototype setting.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.frontiersin.org/journals/medical-technology/articles/10.3389/fmedt.2026.1817439/full
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.