Artificial Intelligence in Colorectal Cancer: From Patient Screening over Tailoring Treatment Decisions to Identification of Novel Biomarkers.

BACKGROUND: Artificial intelligence (AI) is increasingly entering and transforming not only medical research but also clinical practice. In the last 10 years, new AI methods have enabled computers to perform visual tasks, reaching high performance and thereby potentially supporting and even outperforming human experts. This is in particular relevant for colorectal cancer (CRC), which is the 3rd most common cancer type in general, as along the CRC patient journey many complex visual tasks need to be performed: from endoscopy over imaging to histopathology; the screening, diagnosis, and treatment of CRC involve visual image analysis tasks. SUMMARY: In all these clinical areas, AI models have shown promising results by supporting physicians, improving accuracy, and providing new biological insights and biomarkers. By predicting prognostic and predictive biomarkers from routine images/slides, AI models could lead to an improved patient stratification for precision oncology approaches in the near future. Moreover, it is conceivable that AI models, in particular together with innovative techniques such as single-cell or spatial profiling, could help identify novel clinically as well as biologically meaningful biomarkers that could pave the way to new therapeutic approaches. KEY MESSAGES: Here, we give a comprehensive overview of AI in colorectal cancer, describing and discussing these developments as well as the next steps which need to be taken to incorporate AI methods more broadly into the clinical care of CRC.

Deep learning for dual detection of microsatellite instability and POLE mutations in colorectal cancer histopathology.

In the spectrum of colorectal tumors, microsatellite-stable (MSS) tumors with DNA polymerase ε (POLE) mutations exhibit a hypermutated profile, holding the potential to respond to immunotherapy similarly to their microsatellite-instable (MSI) counterparts. Yet, due to their rarity and the associated testing costs, systematic screening for these mutations is not commonly pursued. Notably, the histopathological phenotype resulting from POLE mutations is theorized to resemble that of MSI. This resemblance not only could facilitate their detection by a transformer-based Deep Learning (DL) system trained on MSI pathology slides, but also indicates the possibility for MSS patients with POLE mutations to access enhanced treatment options, which might otherwise be overlooked. To harness this potential, we trained a Deep Learning classifier on a large dataset with the ground truth for microsatellite status and subsequently validated its capabilities for MSI and POLE detection across three external cohorts. Our model accurately identified MSI status in both the internal and external resection cohorts using pathology images alone. Notably, with a classification threshold of 0.5, over 75% of POLE driver mutant patients in the external resection cohorts were flagged as "positive" by a DL system trained on MSI status. In a clinical setting, deploying this DL model as a preliminary screening tool could facilitate the efficient identification of clinically relevant MSI and POLE mutations in colorectal tumors, in one go.

Concurrent loss of MLH1, PMS2 and MSH6 immunoexpression in digestive system cancers indicating a widespread dysregulation in DNA repair processes.

Immunohistochemical analysis of mismatch repair (MMR) protein expression is widely used to identify tumors with a deficient MMR (dMMR). MMR proteins (MLH1/PMS2 and MSH2/MSH6) work as functional heterodimers, which usually leads to the loss of expression in only one functional MMR heterodimer. Recently, there have been studies showing the simultaneous loss of immunoexpression in proteins of both heterodimers. Yet, this phenomenon has been rarely investigated. In this study, we retrospectively considered cases of different digestive system cancers (gastric cancer, ampullary cancer, small bowel cancer, colorectal cancer), which were immunohistochemically tested for dMMR within a 4-year period at our university hospital (n=352). Of the 103 cases showing dMMR, 5 cases (1.4% of all, 5.1% of dMMR cases) showed a concurrent loss of MLH1, PMS2 and MSH6 immunoexpression, whereas in the other 98 dMMR cases only one MMR heterodimer was affected. MLH1-/PMS2-/MSH6- cancer cases almost arose throughout the entire digestive tract: from the gastric antrum to the left colic flexur. To provide a comprehensive molecular characterization of this MLH1-/PMS2-/MSH6- immunophenotype, tumors were analyzed for microsatellite instability, MLH1 promotor hypermethylation and BRAF exon 15 status. Furthermore, we performed next-generation sequencing focusing on genes related to DNA repair. Here, we could detect pathogenic germline variants as well as multiple sporadic mutations in different genes involved in MMR and homologous recombination repair (HRR) respectively. The affected MMR/HRR-related genes were: ATM, BARD1, BRCA1, CDK12, CHEK1, CHEK2, FANCA, MLH1, MSH6, PALB2, TP53. Considering the biologic function of HRR/MMR proteins as potential drug targets and the low frequency of most of these mutations in digestive system cancers in general, their common occurrence in our MLH1-/PMS2-/MSH6- cases seems to be even more noteworthy, highlighting the need for recognition, awareness and further investigation of this unusual IHC staining pattern.