Search

ObjectiveMismatch Repair Deficiency (dMMR) / Microsatellite Instability (MSI) is a key biomarker in colorectal cancer (CRC). Universal screening of CRC patients for dMMR/MSI status is now recommended, but contributes to increased workload for pathologists and delayed therapeutic decisions. Deep learning has the potential to ease dMMR/MSI testing in clinical practice, yet no comprehensive validation of a clinically approved tool has been conducted.DesignWe developed an MSI pre-screening tool, MSIntuit, that uses deep learning to identify MSI status from H&E slides. For training, we used 859 slides from the TCGA database. A blind validation was subsequently performed on an independent dataset of 600 consecutive CRC patients. Each slide was digitised using Phillips-UFS and Ventana-DP200 scanners. Thirty dMMR/MSI slides were used for calibration on each scanner. Prediction was then performed on the remaining 570 patients following an automated quality check step. The inter and intra-scanner reliability was studied to assess MSIntuit’s robustness.ResultsMSIntuit reached a sensitivity and specificity of 97% (95% CI: 93-100%) / 46% (42-50%) on DP200 and of 95% (90-98%) / 47% (43-51%) on UFS scanner. MSIntuit reached excellent agreement on the two scanners (Cohen’s κ: 0.82) and was repeatable across multiple rescanning of the same slide (Fleiss’ κ: 0.82).ConclusionWe performed a successful blind validation of the first clinically approved AI-based tool for MSI detection from H&E slides. MSIntuit reaches sensitivity comparable to gold standard methods (92-95%) while ruling out almost half of the non-MSI population, paving the way for its use in clinical practice.

Although primary tumor sidedness (PTS) has a known prognostic role in sporadic colorectal cancer (CRC), its role in Inflammatory Bowel Disease related CRC (IBD-CRC) is largely unknown. Thus, we aimed to evaluate the prognostic role of PTS in patients with IBD-CRC.All eligible patients with surgically treated, non-metastatic IBD-CRC were retrospectively identified from institutional databases at ten European and Asian academic centers. Long term endpoints included recurrence-free (RFS) and overall survival (OS). Multivariable Cox proportional hazard regression as well as propensity score analyses were performed to evaluate whether PTS was significantly associated with RFS and OS.A total of 213 patients were included in the analysis, of which 32.4% had right-sided (RS) tumors and 67.6% had left-sided (LS) tumors. PTS was not associated with OS and RFS even on univariable analysis (5-year OS for RS vs LS tumors was 68.0% vs 77.3%, respectively, p = 0.31; 5-year RFS for RS vs LS tumors was 62.8% vs 65.4%, respectively, p = 0.51). Similarly, PTS was not associated with OS and RFS on propensity score matched analysis (5-year OS for RS vs LS tumors was 82.9% vs 91.3%, p = 0.79; 5-year RFS for RS vs LS tumors was 85.1% vs 81.5%, p = 0.69). These results were maintained when OS and RFS were calculated in patients with RS vs LS tumors after excluding patients with rectal tumors (5-year OS for RS vs LS tumors was 68.0% vs 77.2%, respectively, p = 0.38; 5-year RFS for RS vs LS tumors was 62.8% vs 59.2%, respectively, p = 0.98).In contrast to sporadic CRC, PTS does not appear to have a prognostic role in IBD-CRC.