Association between the expression of epithelial-mesenchymal transition (EMT)-related markers and oncologic outcomes of colorectal cancer.

BACKGROUND: Epithelial-mesenchymal transition (EMT) is a key step in the development of colorectal cancer (CRC) that confers metastatic capabilities to cancer cells. The present study aimed to assess the immunohistochemical (IHC) expression and impact of EMT markers, including E-cadherin, Vimentin, ß-catenin, and SMAD4, on the oncologic outcomes of CRC. METHODS: This was a retrospective review of 118 CRC patients. Tissue slides were retrieved from the slide archive and five tissue microarray construction blocks were constructed. IHC for E-cadherin, Vimentin, ß-catenin, and SMAD4 was done. The main outcome was the association between abnormal marker expression and overall survival (OS), and disease-free survival (DFS). RESULTS: Adenocarcinomas accounted for 71.2% of tumors, whereas 25.4% and 3.4% were mucinous and signet ring cell carcinomas. The rates of lymphovascular invasion and perineural invasion were 72.9% and 20.3%, respectively. There was a positive, significant correlation, and association between the four markers. Abnormal expression of E-cadherin was associated with significantly lower OS (p < 0.0001) and similar DFS (p = 0.06). Abnormal Vimentin expression was associated with a significantly higher rate of distant metastasis (p = 0.005) and significantly lower OS and DFS (p < 0.0001). Abnormal expression of ß-catenin was associated with significantly lower OS (p < 0.0001) and similar DFS (p = 0.15). Abnormal expression of SMAD4 was associated with significantly lower OS and DFS (p < 0.0001). Abnormal expression of all four markers was associated with a higher disease recurrence, lower OS, and lower DFS. CONCLUSION: Abnormal expression of each marker was associated with lower OS, whereas abnormal expression of Vimentin and SMAD4 only was associated with lower DFS.

Evaluation of cell proliferation marker CDC-7 in salivary adenoid cystic carcinoma.

BACKGROUND: Adenoid cystic carcinoma (AdCC) is considered one of the most common destructive types of malignant salivary gland tumor that have high affinity to perineural invasion (PNI). This study was conducted to access different histological features of AdCC, and assessment of the immunohistochemical expression of CDC-7. METHODS: Thirty formalin-fixed paraffin incorporated tissue blocks of AdCC were classified according to the WHO histopathological types. The immune-expression of CDC-7 positive area was evaluated according to percentage area as following: Negative = 0 %, Weak = 1-10 %, Moderate = 11-49 %, and Strong = 50-100. The correlations between expression of the marker and different clinico-pathological variables were investigated using Chi-square (χ2) test. The P-value ≤ 0.05 was considered statistically significant. RESULTS: The expression of CDC-7 revealed statistical significant difference between the different tumor types (p ≤ 0.05). CONCLUSION: The biological behavior of AdCC can be predicated from the expression of CDC-7.

Deep Neural Network for the Prediction of KRAS Genotype in Rectal Cancer.

BACKGROUND: KRAS mutation can alter the treatment plan after resection of colorectal cancer. Despite its importance, the KRAS status of several patients remains unchecked because of the high cost and limited resources. This study developed a deep neural network (DNN) to predict the KRAS genotype using hematoxylin and eosin (H&E)-stained histopathological images. STUDY DESIGN: Three DNNs were created (KRAS_Mob, KRAS_Shuff, and KRAS_Ince) using the structural backbone of the MobileNet, ShuffleNet, and Inception networks, respectively. The Cancer Genome Atlas was screened to extract 49,684 image tiles that were used for deep learning and internal validation. An independent cohort of 43,032 image tiles was used for external validation. The performance was compared with humans, and a virtual cost-saving analysis was done. RESULTS: The KRAS_Mob network (area under the receiver operating curve [AUC] 0.8, 95% CI 0.71 to 0.89) was the best-performing model for predicting the KRAS genotype, followed by the KRAS_Shuff (AUC 0.73, 95% CI 0.62 to 0.84) and KRAS_Ince (AUC 0.71, 95% CI 0.6 to 0.82) networks. Combing the KRAS_Mob and KRAS_Shuff networks as a double prediction approach showed improved performance. KRAS_Mob network accuracy surpassed that of two independent pathologists (AUC 0.79 [95% CI 0.64 to 0.93], 0.51 [95% CI 0.34 to 0.69], and 0.51 (95% CI 0.34 to 0.69]; p < 0.001 for all comparisons). CONCLUSION: The DNN has the potential to predict the KRAS genotype directly from H&E-stained histopathological slide images. As an algorithmic screening method to prioritize patients for laboratory confirmation, such a model might possibly reduce the number of patients screened, resulting in significant test-related time and economic savings.