Computer-aided diagnosis in predicting the invasion depth of early colorectal cancer: a systematic review and meta-analysis of diagnostic test accuracy

BackgroundEndoscopic resection (ER) is widely applied to treat early colorectal cancer (CRC). Predicting the invasion depth of early CRC is critical in determining treatment strategies. The use of computer-aided diagnosis (CAD) algorithms could theoretically make accurate and objective predictions regarding the suitability of lesions for ER indication based on invasion depth. This study aimed to assess diagnostic test accuracy of CAD algorithms in predicting the invasion depth of early CRC and to compare the performance between the CAD algorithms and endoscopists.MethodsMultiple databases were searched until June 30, 2022 for studies that evaluated the diagnostic performance of CAD algorithms for invasion depth of CRC. Meta-analysis of diagnostic test accuracy using a bivariate mixed-effects model was performed.ResultsTen studies consisting of 13 arms (13,918 images from 1472 lesions) were included. Due to significant heterogeneity, studies were stratified into Japan/Korea-based or China-based studies. For the former, the area under the curve (AUC), sensitivity, and specificity of the CAD algorithms were 0.89 (95% CI 0.86-0.91), 62% (95% CI 50-72%), and 96% (95% CI 93-98%), respectively. For the latter, AUC, sensitivity, and specificity were 0.94 (95% CI 0.92-0.96), 88% (95% CI 78-94%), and 88% (95% CI 80-93%), respectively. The performance of the CAD algorithms in Japan/Korea-based studies was not significantly different from that of all endoscopists (0.88 vs. 0.91, P = 0.10) but was inferior to that of expert endoscopists (0.88 vs. 0.92, P = 0.03). The performance of the CAD algorithms in China-based studies was better than that of all endoscopists (0.94 vs. 0.90, P = 0.01).ConclusionThe CAD algorithms showed comparable accuracy for prediction of invasion depth of early CRC compared to all endoscopists, which was still lower than expert endoscopists in diagnostic accuracy; more improvements should be achieved before it can be extensively applied to clinical practice.

Automated summary

This study evaluated the diagnostic accuracy of computer-aided diagnosis (CAD) algorithms in predicting the invasion depth of early colorectal cancer (CRC) and compared it to the performance of endoscopists. The results showed that in Japan/Korea-based studies, the CAD algorithms had comparable performance to all endoscopists but were inferior to expert endoscopists. In China-based studies, the CAD algorithms performed better than all endoscopists. Overall, while the CAD algorithms showed comparable accuracy in predicting the invasion depth of early CRC, further improvements are needed before their extensive application in clinical practice.