CGE_2024v12n4

Cancer Genetics and Epigenetics 2024, Vol.12, No.4, 210-222 http://medscipublisher.com/index.php/cge 211 2 Colon Cancer: An Overview Colorectal cancer (CRC) is a significant global health concern, being the third most common malignancy worldwide and the second leading cause of cancer-related deaths (Ginghina et al., 2022; Rompianesi et al., 2022). The disease originates from the colon or rectum and progresses through a series of genetic and epigenetic alterations, leading to the formation of adenomas and invasive carcinomas (Al-Joufi et al., 2022; Huang and Yang, 2022). Despite advancements in therapeutic strategies, the prognosis for CRC remains closely tied to the stage at diagnosis, with early detection being crucial for improving survival rates (Ginghina et al., 2022; Qiu et al., 2022). 2.1 Epidemiology and pathophysiology CRC affects millions of individuals globally, with a notable incidence in developed countries. The pathophysiology of CRC involves a complex interplay of genetic mutations and epigenetic changes that drive the transformation of normal colonic epithelium into malignant tumors (Al-Joufi et al., 2022; Huang and Yang, 2022). Key genetic alterations include mutations in the APC, KRAS, and TP53 genes, which contribute to the adenoma-carcinoma sequence (Huang and Yang, 2022). Additionally, epigenetic modifications such as DNA methylation and histone modification play a crucial role in CRC progression (Al-Joufi et al., 2022). The tumor microenvironment, including interactions with stromal cells and immune infiltrates, further influences the disease's pathogenesis and progression (Huang and Yang, 2022; Lim et al., 2023). 2.2 Current challenges in early detection and prediction Early detection of CRC is paramount for effective treatment and improved patient outcomes. However, current diagnostic methods, including colonoscopy, histopathological analysis, and imaging techniques, have limitations in sensitivity and specificity (Bernard and Parikesit, 2020; Ginghina et al., 2022). Colonoscopy, while considered the gold standard for detecting and removing polyps, is invasive and requires significant resources (Bernard and Parikesit, 2020). Moreover, the interpretation of histopathological samples is subject to variability among pathologists, which can affect diagnostic accuracy (Bernard and Parikesit, 2020; Thakur et al., 2020). Liquid biopsy has emerged as a promising non-invasive approach, allowing for the detection of circulating tumor markers, but it still faces challenges in standardization and clinical implementation (Ginghina et al., 2022). Additionally, the identification of reliable prognostic factors and the timely diagnosis of metastatic disease, such as colorectal cancer liver metastasis (CRLM), remain critical hurdles (Rompianesi et al., 2022). 2.3 Potential of AI in addressing these challenges Artificial intelligence (AI) holds significant promise in overcoming the current challenges in CRC detection and prediction. AI-powered tools can enhance the accuracy and efficiency of diagnostic processes by analyzing large datasets and identifying patterns that may be missed by human observers (Figure 1) (Thakur et al., 2020; Qiu et al., 2022). For instance, AI algorithms have shown impressive results in pathology image analysis, including gland segmentation and tumor classification, which are essential for accurate diagnosis (Thakur et al., 2020). AI can also facilitate the spatial analysis of tumor-infiltrating lymphocytes (TILs), providing valuable prognostic information and aiding in the stratification of patients for personalized treatment (Lim et al., 2023). Figure 1 Example of colon cancer segmentation (Adopted from Thakur et al., 2010) Image caption: The flow chart of the three-class classification multi-scale fully convolutional network model; The left side represents the training process and the right side represents the inference; The glands are labeled by different colors at last (Adopted from Thakur et al., 2010)

RkJQdWJsaXNoZXIy MjQ4ODYzNQ==