Deep Learning Based Multiomics Model for Risk Stratification of Postoperative Distant Metastasis in Colorectal Cancer.
[RATIONALE AND OBJECTIVES] To develop deep learning-based multiomics models for predicting postoperative distant metastasis (DM) and evaluating survival prognosis in colorectal cancer (CRC) patients.
- p-value P=0.006
- p-value P=0.023
- OR 2.00
APA
Yao X, Han X, et al. (2026). Deep Learning Based Multiomics Model for Risk Stratification of Postoperative Distant Metastasis in Colorectal Cancer.. Academic radiology, 33(3), 858-871. https://doi.org/10.1016/j.acra.2025.08.040
MLA
Yao X, et al.. "Deep Learning Based Multiomics Model for Risk Stratification of Postoperative Distant Metastasis in Colorectal Cancer.." Academic radiology, vol. 33, no. 3, 2026, pp. 858-871.
PMID
40912950
Abstract
[RATIONALE AND OBJECTIVES] To develop deep learning-based multiomics models for predicting postoperative distant metastasis (DM) and evaluating survival prognosis in colorectal cancer (CRC) patients.
[MATERIALS AND METHODS] This retrospective study included 521 CRC patients who underwent curative surgery at two centers. Preoperative CT and postoperative hematoxylin-eosin (HE) stained slides were collected. A total of 381 patients from Center 1 were split (7:3) into training and internal validation sets; 140 patients from Center 2 formed the independent external validation set. Patients were grouped based on DM status during follow-up. Radiological and pathological models were constructed using independent imaging and pathological predictors. Deep features were extracted with a ResNet-101 backbone to build deep learning radiomics (DLRS) and deep learning pathomics (DLPS) models. Two integrated models were developed: Nomogram 1 (radiological + DLRS) and Nomogram 2 (pathological + DLPS).
[RESULTS] CT- reported T (cT) stage (OR=2.00, P=0.006) and CT-reported N (cN) stage (OR=1.63, P=0.023) were identified as independent radiologic predictors for building the radiological model; pN stage (OR=1.91, P=0.003) and perineural invasion (OR=2.07, P=0.030) were identified as pathological predictors for building the pathological model. DLRS and DLPS incorporated 28 and 30 deep features, respectively. In the training set, area under the curve (AUC) for radiological, pathological, DLRS, DLPS, Nomogram 1, and Nomogram 2 models were 0.657, 0.687, 0.931, 0.914, 0.938, and 0.930. DeLong's test showed DLRS, DLPS, and both nomograms significantly outperformed conventional models (P<.05). Kaplan-Meier analysis confirmed effective 3-year disease-free survival (DFS) stratification by the nomograms.
[CONCLUSION] Deep learning-based multiomics models provided high accuracy for postoperative DM prediction. Nomogram models enabled reliable DFS risk stratification in CRC patients.
[MATERIALS AND METHODS] This retrospective study included 521 CRC patients who underwent curative surgery at two centers. Preoperative CT and postoperative hematoxylin-eosin (HE) stained slides were collected. A total of 381 patients from Center 1 were split (7:3) into training and internal validation sets; 140 patients from Center 2 formed the independent external validation set. Patients were grouped based on DM status during follow-up. Radiological and pathological models were constructed using independent imaging and pathological predictors. Deep features were extracted with a ResNet-101 backbone to build deep learning radiomics (DLRS) and deep learning pathomics (DLPS) models. Two integrated models were developed: Nomogram 1 (radiological + DLRS) and Nomogram 2 (pathological + DLPS).
[RESULTS] CT- reported T (cT) stage (OR=2.00, P=0.006) and CT-reported N (cN) stage (OR=1.63, P=0.023) were identified as independent radiologic predictors for building the radiological model; pN stage (OR=1.91, P=0.003) and perineural invasion (OR=2.07, P=0.030) were identified as pathological predictors for building the pathological model. DLRS and DLPS incorporated 28 and 30 deep features, respectively. In the training set, area under the curve (AUC) for radiological, pathological, DLRS, DLPS, Nomogram 1, and Nomogram 2 models were 0.657, 0.687, 0.931, 0.914, 0.938, and 0.930. DeLong's test showed DLRS, DLPS, and both nomograms significantly outperformed conventional models (P<.05). Kaplan-Meier analysis confirmed effective 3-year disease-free survival (DFS) stratification by the nomograms.
[CONCLUSION] Deep learning-based multiomics models provided high accuracy for postoperative DM prediction. Nomogram models enabled reliable DFS risk stratification in CRC patients.
MeSH Terms
Humans; Colorectal Neoplasms; Deep Learning; Male; Female; Retrospective Studies; Middle Aged; Risk Assessment; Aged; Tomography, X-Ray Computed; Nomograms; Neoplasm Metastasis; Prognosis; Neoplasm Staging; Adult; Multiomics
같은 제1저자의 인용 많은 논문 (5)
- Baseline [F]FDG PET/CT characterization of extramedullary disease and prognostic value in relapsed/refractory B-cell acute lymphoblastic leukemia treated with CAR-T cells.
- SPC25 promotes gastric cancer cells G1/S cell cycle transition and tumorigenesis by enhancing SLC1A5-mediated glutamine metabolism.
- 18 F-FDG PET/CT Manifestation of Unilateral Breast Involvement in a Male Patient With T-Cell Acute Lymphoblastic Leukemia.
- A Novel CT Habitat Radiomics Approach for HER2 Status Prediction in Gastric Cancer.
- Hyaluronic acid-coated Cu/Mn Prussian blue nanocubes amplify cuproptosis and cGAS-STING signaling for synergistic prostate cancer therapy.