Ameyaw Samuel Arthur, Afari Derrick Adu, Boateng John
Department of Computer Engineering, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana, knust.edu.gh.
Department of Clinical Microbiology, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana, knust.edu.gh.
Biomed Res Int. 2025 Sep 18;2025:9214337. doi: 10.1155/bmri/9214337. eCollection 2025.
Colon cancer remains a significant global health burden, accounting for approximately 10% of all cancer cases worldwide and ranking as the second leading cause of cancer-related mortality. Despite advances in treatment, the 5-year survival rate for late-stage colorectal cancer remains as low as 14%, whereas early detection can improve survival to over 90%. This review explores recent advancements in image-based analyses for the morphology and staging of colon cancer, focusing on key imaging modalities, including colonoscopy, computed tomography (CT), magnetic resonance imaging (MRI), endoscopic ultrasound (EUS), histopathological analysis, and the integration of artificial intelligence (AI) and machine learning (ML) algorithms. A systematic literature review was conducted using peer-reviewed studies from databases such as PubMed, Scopus, and IEEE Xplore. Selection criteria included studies published within the past decade that evaluated imaging techniques for colon cancer detection, staging, and treatment planning. AI and ML applications in colon cancer imaging were also examined, with an emphasis on their diagnostic accuracy, staging precision, and impact on clinical decision-making. Findings indicate that AI-assisted imaging techniques enhance lesion detection sensitivity (88%-94%) and improve staging accuracy compared to conventional radiology methods. AI models have also demonstrated superior predictive capabilities in treatment response and prognosis, with deep learning-based algorithms achieving over 90% accuracy in 5-year survival prediction. Despite these advancements, challenges persist, including interobserver variability, dataset biases, regulatory concerns, and the need for standardized AI validation protocols. Addressing these challenges requires interdisciplinary collaboration among clinicians, researchers, and policymakers to refine AI algorithms, develop standardized imaging protocols, and ensure equitable AI applications across diverse populations. By leveraging advancements in imaging and AI-driven analysis, colon cancer diagnosis and management can be significantly improved, ultimately enhancing early detection rates, treatment personalization, and patient survival outcomes.
结肠癌仍然是一项重大的全球健康负担，约占全球所有癌症病例的10%，是癌症相关死亡的第二大主要原因。尽管治疗取得了进展，但晚期结直肠癌的5年生存率仍低至14%，而早期检测可将生存率提高到90%以上。本综述探讨了基于图像分析在结肠癌形态学和分期方面的最新进展，重点关注关键成像模态，包括结肠镜检查、计算机断层扫描（CT）、磁共振成像（MRI）、内镜超声（EUS）、组织病理学分析以及人工智能（AI）和机器学习（ML）算法的整合。使用来自PubMed、Scopus和IEEE Xplore等数据库的同行评审研究进行了系统的文献综述。选择标准包括过去十年内发表的评估结肠癌检测、分期和治疗计划成像技术的研究。还研究了AI和ML在结肠癌成像中的应用，重点关注其诊断准确性、分期精度以及对临床决策的影响。研究结果表明，与传统放射学方法相比，AI辅助成像技术提高了病变检测敏感性（88%-94%）并改善了分期准确性。AI模型在治疗反应和预后方面也表现出卓越的预测能力，基于深度学习的算法在5年生存预测中的准确率超过90%。尽管取得了这些进展，但挑战依然存在，包括观察者间的变异性、数据集偏差、监管问题以及对标准化AI验证协议的需求。应对这些挑战需要临床医生、研究人员和政策制定者之间的跨学科合作，以优化AI算法、制定标准化成像协议并确保AI在不同人群中的公平应用。通过利用成像和AI驱动分析的进展，结肠癌的诊断和管理可以得到显著改善，最终提高早期检测率、治疗个性化程度和患者生存结果。
