Evaluating morphological features for predicting microsatellite instability status in colorectal cancer

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.

Comparison of Microsatellite Instability With Clinicopathologic Data in Patients With Colon Adenocarcinoma

Background Microsatellite instability (MSI) is a genetic condition caused by errors in DNA repair genes that cause colorectal cancer (CRC). The literature contradicts the frequency of MSI in sporadic CRCs and its effect on prognosis. This study investigated the distribution of clinicopathologic features and the relationship between MSI and survival outcomes. Methodology This is a retrospective study of 101 consecutive cases of CRC and immunohistochemical studies. All cases were retrospectively reviewed and reevaluated by histological grade, lymphovascular invasion, perineural invasion, tumor borders, dirty necrosis, tumor-infiltrating lymphocytes (TILs), Crohn's-like lymphoid reaction, mucinous and medullary differentiation, and tumoral budding from pathological slides. An immunohistochemical study was performed in appropriate blocks for using MLH-1, MSH-2, MSH-6, and PMS-2. We collected the clinical stage, pathological tumor stage, lymph node metastasis, age, sex, tumor diameter, distant metastasis, localization, and survival information from patients' clinical data. Results There was no statistically significant difference between the two groups regarding age, gender, tumor diameter, histological grade, tumor border, dirty necrosis, TILs, N and M stage, perineural and lymphovascular invasion, mucinous differentiation, medullary differentiation, and tumor budding characteristics of the patients. The MSI-H group was more frequently located in the right colon and transverse colon (p < 0.001), and the T stage was higher among them than in the MSI-L group (p = 0.014). Upon multivariate regression analysis, MSI status had no significant effect on survival time. Age and stage N and M were independent prognostic factors for colon cancer prognosis. Conclusions Our study presented the distribution of clinicopathological features and their relationship with MSI for 101 regional CRC patients. MSI status was detected by immunohistochemistry. Identifying MSI in CRCs may help personalize therapy planning. As the distribution of the features may vary from population to population, further investigations are needed on this topic.

Artificial intelligence for quantifying Crohn's-like lymphoid reaction and tumor-infiltrating lymphocytes in colorectal cancer

Crohn's-like lymphoid reaction (CLR) and tumor-infiltrating lymphocytes (TILs) are crucial for the host antitumor immune response. We proposed an artificial intelligence (AI)-based model to quantify the density of TILs and CLR in immunohistochemical (IHC)-stained whole-slide images (WSIs) and further constructed the CLR-I (immune) score, a tissue level- and cell level-based immune factor, to predict the overall survival (OS) of patients with colorectal cancer (CRC). The TILs score and CLR score were obtained according to the related density. And the CLR-I score was calculated by summing two scores. The development (Hospital 1, N = 370) and validation (Hospital 2 & 3, N = 144) cohorts were used to evaluate the prognostic value of the CLR-I score. The C-index and integrated area under the curve were used to assess the discrimination ability. A higher CLR-I score was associated with a better prognosis, which was identified by multivariable analysis in the development (hazard ratio for score 3 vs score 0 = 0.22, 95% confidence interval 0.12-0.40, P < 0.001) and validation cohort (0.21, 0.05-0.78, P = 0.020). The AI-based CLR-I score outperforms the single predictor in predicting OS which is objective and more prone to be deployed in clinical practice.