Correlation Between DCAMKL-1 Protein Expression and K-ras Gene Mutation in Colorectal Cancer.

Aim: To investigate the correlation between doublecortin and CaM kinase-like-1 (DCAMKL-1) protein expression, K-ras gene mutation, and their impact on patient prognosis in colorectal cancer (CRC). Methods: Immunohistochemistry was used to detect the expression of DCAMKL-1 protein in 60 cases of colorectal adenoma, 82 cases of CRC (including 65 cases of lymph node metastasis) and paraffin-embedded paracancerous intestinal mucosal tissue. K-ras gene mutations in primary CRC lesions were detected using an amplification-refractory mutation system and fluorescent polymerase chain reaction. The relationship between DCAMKL-1 protein expression and K-ras gene mutations with the clinicopathological characteristics of patients with CRC was analyzed. Univariate Kaplan‒Meier survival analysis and multivariate Cox regression analysis were performed using follow-up data. Results: The mutation rate of the K-ras gene in 82 cases of CRC was 48.8% (40/82). The positivity rate for the presence of DCAMKL-1 protein in CRC was 70.7% (58/82), significantly higher than that for colorectal adenomas (53.3%; 32/60) and paracancerous intestinal mucosa (0%; 0/82) (P<0.05). The positive expression rate for the presence of DCAMKL-1 protein in 65 patients with lymph node metastasis was higher in the primary lesions (69.2%; 45/65) than in the lymph node metastases (52.3%; 34/65) (χ2=12.087, P=0.001). The K-ras gene mutation status was positively correlated with DCAMKL-1 protein expression (r=0.252, P=0.022). Conclusion: In this study, a potential positive correlation between K-ras gene mutation and DCAMKL-1 protein expression was identified in CRC tissues. The assessment of K-ras gene mutation status and DCAMKL-1 protein expression holds promise for augmenting early diagnosis and prognosis evaluation in CRC. This approach may improve the overall prognosis and survival outcomes for CRC patients.

TGMIL: A hybrid multi-instance learning model based on the Transformer and the Graph Attention Network for whole-slide images classification of renal cell carcinoma.

BACKGROUND AND OBJECTIVES: The pathological diagnosis of renal cell carcinoma is crucial for treatment. Currently, the multi-instance learning method is commonly used for whole-slide image classification of renal cell carcinoma, which is mainly based on the assumption of independent identical distribution. But this is inconsistent with the need to consider the correlation between different instances in the diagnosis process. Furthermore, the problem of high resource consumption of pathology images is still urgent to be solved. Therefore, we propose a new multi-instance learning method to solve this problem. METHODS: In this study, we proposed a hybrid multi-instance learning model based on the Transformer and the Graph Attention Network, called TGMIL, to achieve whole-slide image of renal cell carcinoma classification without pixel-level annotation or region of interest extraction. Our approach is divided into three steps. First, we designed a feature pyramid with the multiple low magnifications of whole-slide image named MMFP. It makes the model incorporates richer information, and reduces memory consumption as well as training time compared to the highest magnification. Second, TGMIL amalgamates the Transformer and the Graph Attention's capabilities, adeptly addressing the loss of instance contextual and spatial. Within the Graph Attention network stream, an easy and efficient approach employing max pooling and mean pooling yields the graph adjacency matrix, devoid of extra memory consumption. Finally, the outputs of two streams of TGMIL are aggregated to achieve the classification of renal cell carcinoma. RESULTS: On the TCGA-RCC validation set, a public dataset for renal cell carcinoma, the area under a receiver operating characteristic (ROC) curve (AUC) and accuracy of TGMIL were 0.98±0.0015,0.9191±0.0062, respectively. It showcased remarkable proficiency on the private validation set of renal cell carcinoma pathology images, attaining AUC of 0.9386±0.0162 and ACC of 0.9197±0.0124. Furthermore, on the public breast cancer whole-slide image test dataset, CAMELYON 16, our model showed good classification performance with an accuracy of 0.8792. CONCLUSIONS: TGMIL models the diagnostic process of pathologists and shows good classification performance on multiple datasets. Concurrently, the MMFP module efficiently diminishes resource requirements, offering a novel angle for exploring computational pathology images.