Copyright ©The Author(s) 2021.
World J Gastroenterol. Jun 7, 2021; 27(21): 2818-2833
Published online Jun 7, 2021. doi: 10.3748/wjg.v27.i21.2818
Table 1 Artificial intelligence applications in gastric cancer pathology
No. of cases/data set
Machine learning method
Bollschweiler et al[79]Prognosis prediction135 casesANNAccuracy (93%)
Duraipandian et al[80]Tumor classification700 slidesGastricNetAccuracy (100%)
Cosatto et al[65]Tumor classification> 12000 WSIsMILAUC (0.96)
Sharma et al[21]Tumor classification454 casesCNNAccuracy (69% for cancer classification), accuracy (81% for necrosis detection)
Jiang et al[81]Prognosis prediction786 casesSVM classifierAUCs (up to 0.83)
Qu et al[82]Tumor classification9720 imagesDLAUCs (up to 0.97)
Yoshida et al[23]Tumor classification3062 gastric biopsy specimensMLOverall concordance rate (55.6%)
Kather et al[34]Prediction of microsatellite instability1147 cases (gastric and colorectal cancer)Deep residual learningAUC (0.81 for gastric cancer; 0.84 for colorectal cancer)
Garcia et al[30]Tumor classification3257 imagesCNNAccuracy (96.9%)
León et al[83]Tumor classification40 imagesCNNAccuracy (up to 89.7%)
Fu et al[32]Prediction of genomic alterations, gene expression profiling, and immune infiltration> 1000 cases (gastric, colorectal, esophageal, and liver cancers)Neural networks.AUC (0.9) for BRAF mutations prediction in thyroid cancers
Liang et al[84]Tumor classification1900 imagesDLAccuracy (91.1%)
Sun et al[85]Tumor classification500 imagesDLAccuracy (91.6%)
Tomita et al[24]Tumor classification502 cases (esophageal adenocarcinoma and Barret esophagus)Attention-based deep learningAccuracy (83%)
Wang et al[86]Tumor classification608 imagesRecalibrated multi-instance deep learningAccuracy (86.5%)
Iizuka et al[22]Tumor classification1746 biopsy WSIsCNN, RNNAUCs (up to 0.98), accuracy (95.6%)
Kather et al[33]Prediction of genetic alterations and gene expression signatures> 1000 cases (gastric, colorectal, and pancreatic cancer)Neural networksAUC (up to 0.8)