Fast and label-free automated detection of microsatellite status in early colon cancer using artificial intelligence integrated infrared imaging. (March 2023)

• Record Type: Journal Article
• Authors: Gerwert, Klaus; Schörner, Stephanie; Großerueschkamp, Frederik; Kraeft, Anna–Lena; Schuhmacher, David; Sternemann, Carlo; Feder, Inke S.; Wisser, Sarah; Lugnier, Celine; Arnold, Dirk; Teschendorf, Christian; Mueller, Lothar; Timmesfeld, Nina; Mosig, Axel; Reinacher-Schick, Anke; Tannapfel, Andrea
• Is Part Of: European journal of cancer. Volume 182(2023)
• Page Start: 122
• Page End: 131
• Publication Date: 2023-03
• Subjects: Microsatellite instability -- Colon cancer -- Artificial intelligence -- Deep learning -- Infrared imaging -- Label-free -- Convolutional neural networks; Cancer -- Periodicals; Neoplasms -- Periodicals; Cancer -- Périodiques; Cancer; Tumors; Electronic journals; Periodicals; Electronic journals; 616.994
• DOI: 10.1016/j.ejca.2022.12.026
• Languages: English
• ISSNs: 0959-8049

Abstract

Abstract: Purpose: Microsatellite instability (MSI) due to mismatch repair (MMR) defects accounts for 15–20% of colon cancers (CC). MSI testing is currently standard of care in CC with immunohistochemistry of the four MMR proteins representing the gold standard. Instead, label-free quantum cascade laser (QCL) based infrared (IR) imaging combined with artificial intelligence (AI) may classify MSI/microsatellite stability (MSS) in unstained tissue sections user-independently and tissue preserving. Methods: Paraffin-embedded unstained tissue sections of early CC from patients participating in the multicentre AIO ColoPredict Plus (CPP) 2.0 registry were analysed after dividing into three groups (training, test, and validation). IR images of tissue sections using QCL-IR microscopes were classified by AI (convolutional neural networks [CNN]) using a two-step approach. The first CNN (modified U-Net) detected areas of cancer while the second CNN (VGG-Net) classified MSI/MSS. End-points were area under receiver operating characteristic (AUROC) and area under precision recall curve (AUPRC). Results: The cancer detection in the first step was based on 629 patients (train n = 273, test n = 138, and validation n = 218). Resulting classification AUROC was 1.0 for the validation dataset. The second step classifying MSI/MSS was performed on 547 patients (train n = 331, test n = 69, and validation n = 147) reaching AUROC and AUPRC of 0.9 and 0.74, respectively, for the validation cohort. Conclusion: Our novel label-free digital pathology approach accurately and rapidly classifies MSI vs. MSS. The tissue sections analysed were not processed leaving the sample unmodified for subsequent analyses. Our approach demonstrates an AI-based decision support tool potentially driving improved patient stratification and precision oncology in the future. Graphical abstract: Image 1 Highlights: Testing of microsatellite instability has become standard of care in colon cancer. Immunohistochemistry may render false negative results in 10% of cases. An infrared absorption spectrum summarises the biochemistry in the analysed tissue. Artificial intelligence can use infrared imaging to challenge immunohistochemistry. Infrared imaging works label-free preserving tissue for further analyses.