黄 斌,曹云太

结直肠癌（colorectal cancer, CRC）是常见的恶性肿瘤，死亡率较高。近年来，基于分子标志物的精准治疗模式不断发展，已成为该疾病治疗的重要方向。微卫星不稳定性（microsatellite instability, MSI）作为CRC的关键分子分型指标，在个体化治疗选择和预后判断中展现出重要的临床意义。随着人工智能（artificial intelligence, AI）技术的迅速发展，利用计算机断层成像（computed tomography, CT）图像构建的人工智能模型因其无创性、可重复性以及潜在的个体化预测能力，已在预测CRC的MSI状态方面取得初步进展。这些模型主要通过深度学习（deep learning, DL）或影像组学（radiomics）技术，从CT影像中挖掘隐藏的特征信息，进而建立非侵入式的预测体系。本文旨在综述基于CT影像的人工智能方法在CRC患者MSI状态预测中的研究现状，以期为临床诊疗提供新的思路和辅助决策支持。

结直肠癌；微卫星不稳定；人工智能；计算机断层成像

[1] SIEGEL R L, WAGLE N S, CERCEK A, 等. Colorectal cancer statistics, 2023[J]. CA: a cancer journal for clinicians, 2023, 73(3): 233-254. [2] NOJADEH J N, BEHROUZ SHARIF S, SAKHINIA E. Microsatellite instability in colorectal cancer[J]. EXCLI journal, 2018, 17: 159-168. [3] GOLIA PERNICKA J S, GAGNIERE J, CHAKRABORTY J, 等. Radiomics-based prediction of microsatellite instability in colorectal cancer at initial computed tomography evaluation[J]. Abdominal Radiology (New York), 2019, 44(11): 3755-3763. [4] FAN S, LI X, CUI X, 等. Computed Tomography-Based Radiomic Features Could Potentially Predict Microsatellite Instability Status in Stage II Colorectal Cancer: A Preliminary Study[J]. Academic Radiology, 2019, 26(12): 1633-1640. [5] PEI Q, YI X, CHEN C, 等. Pre-treatment CT-based radiomics nomogram for predicting microsatellite instability status in colorectal cancer[J]. European Radiology, 2022, 32(1): 714-724. [6] YUAN H, PENG Y, XU X, 等. A Tumoral and Peritumoral CT-Based Radiomics and Machine Learning Approach to Predict the Microsatellite Instability of Rectal Carcinoma[J]. Cancer Management and Research, 2022, 14: 2409-2418. [7] CHEN X, HE L, LI Q, 等. Non-invasive prediction of microsatellite instability in colorectal cancer by a genetic algorithm-enhanced artificial neural network-based CT radiomics signature[J]. European Radiology, 2023, 33(1): 11-22. [8] PAREKH V S, JACOBS M A. Deep learning and radiomics in precision medicine[J]. Expert Review of Precision Medicine and Drug Development, 2019, 4(2): 59-72. [9] CAO W, HU H, GUO J, 等. CT-based deep learning model for the prediction of DNA mismatch repair deficient colorectal cancer: a diagnostic study[J]. Journal of Translational Medicine, 2023, 21(1): 214. [10] CHEN W, ZHENG K, YUAN W, 等. A CT-based deep learning for segmenting tumors and predicting microsatellite instability in patients with colorectal cancers: a multicenter cohort study[J]. La Radiologia Medica, 2025, 130(2): 214-225.

点击下载PDF