Artificial intelligence- enhanced white-light colonoscopy with attention guidance predicts colorectal cancer invasion depth

Journal article

Xiaobei Luo, Jiahao Wang, Zelong Han, Yang Yu, Zhenyu Chen, Feiyang Huang, Yumeng Xu, Jianqun Cai, Qiang Zhang, Weiguang Qiao, others
Gastrointestinal Endoscopy, vol. 94, Mosby, 2021, pp. 627--638

Link to paper

Cite

APA Click to copy
Luo, X., Wang, J., Han, Z., Yu, Y., Chen, Z., Huang, F., … others. (2021). Artificial intelligence- enhanced white-light colonoscopy with attention guidance predicts colorectal cancer invasion depth. Gastrointestinal Endoscopy, 94, 627–638.

Chicago/Turabian Click to copy
Luo, Xiaobei, Jiahao Wang, Zelong Han, Yang Yu, Zhenyu Chen, Feiyang Huang, Yumeng Xu, et al. “Artificial Intelligence- Enhanced White-Light Colonoscopy with Attention Guidance Predicts Colorectal Cancer Invasion Depth.” Gastrointestinal Endoscopy 94 (2021): 627–638.

MLA Click to copy
Luo, Xiaobei, et al. “Artificial Intelligence- Enhanced White-Light Colonoscopy with Attention Guidance Predicts Colorectal Cancer Invasion Depth.” Gastrointestinal Endoscopy, vol. 94, Mosby, 2021, pp. 627–38.

BibTeX Click to copy

@article{luo2021a,
  title = {Artificial intelligence- enhanced white-light colonoscopy with attention guidance predicts colorectal cancer invasion depth},
  year = {2021},
  journal = {Gastrointestinal Endoscopy},
  pages = {627--638},
  publisher = {Mosby},
  volume = {94},
  author = {Luo, Xiaobei and Wang, Jiahao and Han, Zelong and Yu, Yang and Chen, Zhenyu and Huang, Feiyang and Xu, Yumeng and Cai, Jianqun and Zhang, Qiang and Qiao, Weiguang and others}
}

Background and Aims

Endoscopic submucosal dissection (ESD) and EMR are applied in treating superficial colorectal neoplasms but are contraindicated by deeply invasive colorectal cancer (CRC). The invasion depth of neoplasms can be examined by an automated artificial intelligence (AI) system to determine the applicability of ESD and EMR.

Methods

A deep convolutional neural network with a tumor localization branch to guide invasion depth classification was constructed on the GoogLeNet architecture. The model was trained using 7734 nonmagnified white-light colonoscopy (WLC) images supplemented by image augmentation from 657 lesions labeled with histopathologic analysis of invasion depth. An independent testing dataset consisting of 1634 WLC images from 156 lesions was used to validate the model.

Results

For predicting noninvasive and superficially invasive neoplasms, the model achieved an overall accuracy of 91.1% (95% confidence interval [CI], 89.6%-92.4%), with 91.2% sensitivity (95% CI, 88.8%-93.3%) and 91.0% specificity (95% CI, 89.0%-92.7%) at an optimal cutoff of .41 and the area under the receiver operating characteristic (AUROC) curve of .970 (95% CI, .962-.978). Inclusion of the advanced CRC data significantly increased the sensitivity in differentiating superficial neoplasms from deeply invasive early CRC to 65.3% (95% CI, 61.9%-68.8%) with an AUROC curve of .729 (95% CI, .699-.759), similar to experienced endoscopists (.691; 95% CI, .624-.758).

Conclusions

We have developed an AI-enhanced attention-guided WLC system that differentiates noninvasive or superficially submucosal invasive neoplasms from deeply invasive CRC with high accuracy, sensitivity, and specificity.