In a groundbreaking study published in Nature Communications, researchers have unveiled a cutting-edge technology, MSIntuit CRC, designed to revolutionize the diagnosis and treatment of colorectal cancer (CRC). Microsatellite Instability (MSI), a tumor genotype present in approximately 15% of CRC cases, plays a pivotal role in clinical management, with diagnostic, prognostic, and therapeutic implications. Colorectal cancer ranked as the third most prevalent cancer globally, taking nearly one million lives out of the two million new cases reported in 2020. Recent clinical trials have underscored the significance of the MSI phenotype, particularly in the context of immune checkpoint inhibitor (ICI) therapies.
Dr. Saillard and colleagues conducted a blind clinical validation of MSIntuit on a large external cohort of 600 consecutive resected CRC cases diagnosed across 9 diverse pathology labs over two years. Their findings reveal that MSIntuit serves as an efficient pre-screening tool, excluding almost half of the non-MSI population and thereby simplifying MSI screening. The tool boasts an automatic slide quality check and addresses the challenge of defining an operating threshold with a calibration step, making it directly applicable to clinical practice.
The researchers addressed key questions for clinical routine use, assessing MSIntuit’s intra and inter-scanner variability, as well as inter-block variability. Their meticulous approach emphasizes the potential impact on oncologist decision-making, enabling prompt access to tailored treatments and optimizing costs and organizational efficiency in pathology labs.
According to Saillard et al., as the demand for biomarker testing tools rises, MSIntuit CRC marks a significant advancement, representing a step toward the development of an AI diagnostic capable of identifying actionable biomarkers from a single H&E slide in routine clinical practice. This innovation brings us closer to the realization of precision medicine’s vision.
The blind validation of 600 CRC cases in the present study affirms the robustness of MSIntuit as an effective pre-screening tool. In light of the growing demand for biomarker testing in clinical practice, such tools play a pivotal role in simplifying and expediting the diagnostic process. This represents an initial stride in the evolution of AI-based solutions capable of identifying biomarkers from a single hematoxylin-eosin (H&E) slides used in routine clinical settings, thereby advancing the potential of precision medicine. The study findings not only contribute to the ongoing refinement of diagnostic methodologies but also hold promise for enhancing the efficiency and accuracy of cancer detection and treatment planning in the era of personalized medicine.
Reference
Saillard C, Dubois R, Tchita O, Loiseau N, Garcia T, Adriansen A, et al. Validation of MSIntuit as an AI-based pre-screening tool for MSI detection from colorectal cancer histology slides. Nat Commun. 2023 Nov 6;14(1):6695.