Copyright: ©Author(s) 2026.
World J Gastrointest Oncol. Nov 15, 2026; 18(11): 123187
Published online Nov 15, 2026. doi: 10.4251/wjgo.123187
Published online Nov 15, 2026. doi: 10.4251/wjgo.123187
Table 3 Test performance of VGG19 model, ResNet50 model and InceptionV3 model in the training set
| Model | Sensitivity | Specificity | Accuracy | AUROC |
| VGG19 | 0.78 | 0.93 | 0.88 | 0.92 |
| ResNet50 | 0.57 | 0.94 | 0.82 | 0.84 |
| InceptionV3 | 0.67 | 0.99 | 0.89 | 0.95 |
| Ensemble deep learning prediction | 0.85 | 0.93 | 0.90 | 0.89 |
- Citation: Dong WH, Ling X, Chen XD, Qian JP, Jin Y, Gu YJ. Establishment and validation of a multimodal model using deep learning for the recognition of early colorectal cancer. World J Gastrointest Oncol 2026; 18(11): 123187
- URL: https://www.wjgnet.com/1948-5204/full/v18/i11/123187.htm
- DOI: https://dx.doi.org/10.4251/wjgo.123187