Artificial Intelligence for Predicting Microsatellite Instability Based on Tumor Histomorphology: A Systematic Review

Abstract

Microsatellite instability (MSI)/defective DNA mismatch repair (dMMR) is receiving more attention as a biomarker for eligibility for immune checkpoint inhibitors in advanced diseases. However, due to high costs and resource limitations, MSI/dMMR testing is not widely performed. Some attempts are in progress to predict MSI/dMMR status through histomorphological features on H&E slides using artificial intelligence (AI) technology. In this study, the potential predictive role of this new methodology was reviewed through a systematic review. Studies up to September 2021 were searched through PubMed and Embase database searches. The design and results of each study were summarized, and the risk of bias for each study was evaluated. For colorectal cancer, AI-based systems showed excellent performance with the highest standard of 0.972; for gastric and endometrial cancers they showed a relatively low but satisfactory performance, with the highest standard of 0.81 and 0.82, respectively. However, analyzing the risk of bias, most studies were evaluated at high-risk. AI-based systems showed a high potential in predicting the MSI/dMMR status of different cancer types, and particularly of colorectal cancers. Therefore, a confirmation test should be required only for the results that are positive in the AI test.

Clinicopathological characteristics of high microsatellite instability/mismatch repair-deficient colorectal cancer: A narrative review

“…Significant progress has also been made in the development of AI-assisted models to predict MSI status in CRC based on the distinct histomorphological features of MSI-H/dMMR tumors (Table 1) (61). For example, an open-source AI system that was trained using routine pathology slides from eight multicenter cohorts facilitated accurate and fully automated prediction of MSI status, yielding an area under the curve (AUC) value of 0.96 (95% CI, 0.94-0.98) (50).…”

Diagnostic Performance of Immunohistochemistry Compared to Molecular Techniques for Microsatellite Instability and p53 Mutation Detection in Endometrial Cancer

“…Furthermore, artificial intelligence is a promising solution to characterise histomorphological EC molecular subtypes and their disease prognosis [37][38][39]. Studies are ongoing in this specific field.…”

Artificial intelligence in head and neck cancer diagnosis

“… 33 WSI has enabled the application of AI tools in pathology. 34 , 35 A brief and general description of different AI modalities is summarized in Table 1 .…”