摘要
肝细胞癌(HCC)是最常见的原发性肝癌,也是全球癌症相关死亡的第三大原因。尽管近年来诊疗技术不断进步,HCC的总体治疗效果仍待提升。随着人工智能的发展,影像组学通过从医学影像中提取肉眼无法识别的定量特征,构建预测模型,为HCC的诊断、治疗决策、疗效评估和预后预测提供新路径,助力精准诊疗。本文结合最新研究进展,系统探讨影像组学在HCC智慧诊疗中的应用,以期推动综合诊疗水平的提升。
肝细胞癌(hepatocellular carcinoma,HCC)是全球常见的恶性肿瘤,发病率居全球第6位,病死率居第3
人工智能(artificial intelligence,AI)正在迅速改变传统医疗,尤其是在HCC的诊断和治疗上发挥着越来越重要的作
传统的HCC筛查工具中,US虽然应用广泛,但其对早期HCC的敏感度仅为47%,尤其在小病灶的准确识别方面存在明显不足。尽管CT和MRI具有较高的分辨率,但对早期病变的识别依然受限,尤其是在精准评估病变的异质性特征方面。影像组学技术通过量化深层次影像信息,筛选出与疾病相关的重要特征,为HCC的早期诊断和鉴别诊断提供了新的可能性。
基于影像组学的诊断模型在性能上与经验丰富的影像学专家相当,甚至在某些应用场景中表现更
HCC的组织病理学特征是评估患者预后及复发风险的关键信
首先,在预测HCC组织病理学分级方面,影像组学模型表现出卓越的预测能
HCC的高度异质性使得相同的治疗方案可能产生截然不同的治疗效果。因此,准确识别对于特定治疗方案敏感和获益患者显得尤为重要,影像组学技术在HCC个体化治疗决策的制定中展现出重要价值。Liu
在不可切除HCC的治疗决策中,影像组学同样可发挥关键作用。影像组学在经动脉化疗栓塞(transarterial chemoembolization,TACE)治疗中的应用展现出一定的潜力。Li
局部治疗方法如RFA、TACE、选择性内放射治疗等是HCC治疗的重要手段。然而,由于患者间生物学特征的异质性,其疗效存在显著个体差异。影像组学通过提取和量化医学影像的高阶特征,为局部治疗的疗效判断提供了更精准的工具。
在RFA疗效评估的预测模型研究中,Horvat
影像组学在系统治疗疗效评估中同样具有重要价值,可帮助筛选系统治疗获益最大的患者群,提高治疗的靶向性。Xie
尽管根治性治疗如手术切除和RFA能够显著改善HCC患者的OS率,但术后复发率依然居高不下,而影像组学可有效预测复发风险的大小。Peng
影像组学在预测HCC生存预后的评估中同样具有显著价值。基于MRI特征的影像组学研究表明,利用肿瘤及其周围区域的影像特征可有效预测早期HCC患者在RFA治疗后的PF
在肝移植术后预后评估中,影像组学也表现出重要作用。Nie
目前,影像组学的前沿还包括与各组学的联合应用。病理组学作为一种新兴工具,能够全面提取特征并改善肿瘤预后评估,同时与影像组学的整合可进一步提升模型性能。Feng
尽管影像组学在HCC的诊断、治疗和预后预测中展现了巨大的潜力,但其临床应用仍面临诸多挑战。首先,现有研究多关注模型性能,而忽视了研究设计和结果分析的质量控制,导致可能存在系统误差,影响模型的可靠性和泛化能力。其次,模型结果的生物学可解释性不足,此“黑箱”问题降低了临床医生对预测模型的信任度。此外,缺少多中心、前瞻性的外部验证,进一步限制了模型在真实临床环境中的应用。最后,目前临床指南尚未正式批准基于AI的影像组学模型应用于HCC的诊疗,其临床转化仍处于探索阶段。
影像组学结合AI技术在HCC的诊断、治疗决策、疗效判断和预后评估中展现了巨大的潜力,然而,其临床转化仍面临数据标准化不足、生物学可解释性欠佳及多中心、前瞻性外部验证的缺乏等诸多挑战。未来,影像组学可通过制定统一的数据采集规范、联合多组学研究进一步提高模型的生物可解释性、与深度学习的结合和标准化的多中心验证,有望在HCC智慧诊疗中发挥更大作用。
作者贡献声明
李永海、钱桂香负责文献资料收集、解读与分析以及文章初稿撰写和修改;荚卫东负责文章选题和设计、文章写作思路、稿件最终审阅定稿。
利益冲突
所有作者均声明不存在利益冲突。
参考文献
Bray F, Laversanne M, Sung H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2024, 74(3):229-263. doi:10.3322/caac.21834. [百度学术]
Mak LY, Liu K, Chirapongsathorn S, et al. Liver diseases and hepatocellular carcinoma in the Asia-Pacific region: burden, trends, challenges and future directions[J]. Nat Rev Gastroenterol Hepatol, 2024, 21(12):834-851. doi:10.1038/s41575-024-00967-4. [百度学术]
荚卫东. 精准肝切除治疗肝细胞癌关键技术[J]. 中国普通外科杂志, 2014, 23(1):1-5. doi:10.7659/j.issn.1005-6947.2014.01.001. [百度学术]
Jia WD. Key techniques in precise hepatectomy for hepatocellular carcinoma[J]. China Journal of General Surgery, 2014, 23(1):1-5. doi:10.7659/j.issn.1005-6947.2014.01.001. [百度学术]
李永海, 荚卫东. 人工智能影像组学在肝细胞癌精准诊治中的研究进展[J]. 中华肝脏病杂志, 2020, 28(11):905-909. doi:10.3760/cma.j.cn501113-20201022-00573. [百度学术]
Li YH, Jia WD. Research progress of radiomics with artificial intelligence in precise diagnosis and treatment of hepatocellular carcinoma[J]. Chinese Journal of Hepatology, 2020, 28(11):905-909. doi:10.3760/cma.j.cn501113-20201022-00573. [百度学术]
Bo Z, Song J, He Q, et al. Application of artificial intelligence radiomics in the diagnosis, treatment, and prognosis of hepatocellular carcinoma[J]. Comput Biol Med, 2024, 173:108337. doi:10.1016/j.compbiomed.2024.108337. [百度学术]
Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4):441-446. doi:10.1016/j.ejca.2011.11.036. [百度学术]
Mostafa G, Mahmoud H, Abd El-Hafeez T, et al. The power of deep learning in simplifying feature selection for hepatocellular carcinoma: a review[J]. BMC Med Inform Decis Mak, 2024, 24(1):287. doi:10.1186/s12911-024-02682-1. [百度学术]
Wang Q, Sheng Y, Jiang ZX, et al. What imaging modality is more effective in predicting early recurrence of hepatocellular carcinoma after hepatectomy using radiomics analysis: CT or MRI or both?[J]. Diagnostics (Basel), 2023, 13(12):2012. doi:10.3390/diagnostics13122012. [百度学术]
Yang N, Ma Z, Zhang L, et al. Radiomics-based automated machine learning for differentiating focal liver lesions on unenhanced computed tomography[J]. Abdom Radiol (NY), 2024. doi: 10.1007/s00261-024-04685-y. [Online ahead of print] [百度学术]
Bharti P, Mittal D, Ananthasivan R. Preliminary study of chronic liver classification on ultrasound images using an ensemble model[J]. Ultrason Imaging, 2018, 40(6):357-379. doi:10.1177/0161734618787447. [百度学术]
Popa SL, Grad S, Chiarioni G, et al. Applications of artificial intelligence in the automatic diagnosis of focal liver lesions: a systematic review[J]. J Gastrointestin Liver Dis, 2023, 32(1):77-85. doi:10.15403/jgld-4755. [百度学术]
Guo L, Hao X, Chen L, et al. Early warning of hepatocellular carcinoma in cirrhotic patients by three-phase CT-based deep learning radiomics model: a retrospective, multicentre, cohort study[J]. EClinicalMedicine, 2024, 74:102718. doi:10.1016/j.eclinm.2024.102718. [百度学术]
Deng X, Liao Z. A machine-learning model based on dynamic contrast-enhanced MRI for preoperative differentiation between hepatocellular carcinoma and combined hepatocellular-cholangiocarcinoma[J]. Clin Radiol, 2024, 79(6):e817-e825. doi:10.1016/j.crad.2024.02.001. [百度学术]
Ravina M, Mishra A, Kote R, et al. Role of textural analysis parameters derived from FDG PET/CT in differentiating hepatocellular carcinoma and hepatic metastases[J]. Nucl Med Commun, 2023, 44(5):381-389. doi:10.1097/MNM.0000000000001676. [百度学术]
Ding T, Li X, Mo J, et al. Recurrence risk stratification of hepatocellular carcinomas based on immune gene expression and features extracted from pathological images[J]. PLoS Comput Biol, 2023, 19(12):e1011716. doi:10.1371/journal.pcbi.1011716. [百度学术]
Wang Q, Wang AR, Wu XY, et al. Radiomics models for preoperative prediction of the histopathological grade of hepatocellular carcinoma: A systematic review and radiomics quality score assessment[J]. Eur J Radiol, 2023, 166:111015. doi:10.1016/j.ejrad.2023.111015. [百度学术]
Wei J, Ji Q, Gao Y, et al. A multi-scale, multi-region and attention mechanism-based deep learning framework for prediction of grading in hepatocellular carcinoma[J]. Med Phys, 2023, 50(4):2290-2302. doi:10.1002/mp.16127. [百度学术]
Han YE, Cho Y, Kim MJ, et al. Hepatocellular carcinoma pathologic grade prediction using radiomics and machine learning models of gadoxetic acid-enhanced MRI: a two-center study[J]. Abdom Radiol (NY), 2023, 48(1):244-256. doi:10.1007/s00261-022-03679-y. [百度学术]
Xu ZL, Qian GX, Li YH, et al. Evaluating microvascular invasion in hepatitis B virus-related hepatocellular carcinoma based on contrast-enhanced computed tomography radiomics and clinicoradiological factors[J]. World J Gastroenterol, 2024, 30(45):4801-4816. doi:10.3748/wjg.v30.i45.4801. [百度学术]
Liu JP, Cheng DL, Liao YT, et al. Development of a magnetic resonance imaging-derived radiomics model to predict microvascular invasion in patients with hepatocellular carcinoma[J]. Quant Imaging Med Surg, 2023, 13(6):3948-3961. doi:10.21037/qims-22-1011. [百度学术]
Qin Q, Deng LP, Chen J, et al. The value of MRI in predicting hepatocellular carcinoma with cytokeratin 19 expression: a systematic review and meta-analysis[J]. Clin Radiol, 2023, 78(12):e975-e984. doi:10.1016/j.crad.2023.08.013. [百度学术]
Li SQ, Yang CX, Wu CM, et al. Prediction of glypican-3 expression in hepatocellular carcinoma using multisequence magnetic resonance imaging-based histology nomograms[J]. Quant Imaging Med Surg, 2024, 14(7):4436-4449. doi:10.21037/qims-24-111. [百度学术]
Liu F, Liu D, Wang K, et al. Deep learning radiomics based on Contrast-Enhanced ultrasound might optimize curative treatments for Very-Early or Early-Stage hepatocellular carcinoma patients[J]. Liver Cancer, 2020, 9(4):397-413. doi:10.1159/000505694. [百度学术]
Li J, Zhou M, Tong Y, et al. Tumor growth pattern and intra- and peritumoral radiomics combined for prediction of initial TACE outcome in patients with primary hepatocellular carcinoma[J]. J Hepatocell Carcinoma, 2024, 11:1927-1944. doi:10.2147/JHC.S480554. [百度学术]
Jin Z, Chen L, Zhong B, et al. Machine-learning analysis of contrast-enhanced computed tomography radiomics predicts patients with hepatocellular carcinoma who are unsuitable for initial transarterial chemoembolization monotherapy: A multicenter study[J]. Transl Oncol, 2021, 14(4):101034. doi:10.1016/j.tranon.2021.101034. [百度学术]
Lin X, Wei R, Xu Z, et al. A deep learning model for personalized intra-arterial therapy planning in unresectable hepatocellular carcinoma: a multicenter retrospective study[J]. EClinicalMedicine, 2024, 75:102808. doi:10.1016/j.eclinm.2024.102808. [百度学术]
Liu K, Zheng X, Lu D, et al. A multi-institutional study to predict the benefits of DEB-TACE and molecular targeted agent sequential therapy in unresectable hepatocellular carcinoma using a radiological-clinical nomogram[J]. Radiol Med, 2024, 129(1):14-28. doi:10.1007/s11547-023-01736-0. [百度学术]
Horvat N, Araujo-Filho JAB, Assuncao-Jr AN, et al. Radiomic analysis of MRI to Predict Sustained Complete Response after Radiofrequency Ablation in Patients with Hepatocellular Carcinoma - A Pilot Study[J]. Clinics (Sao Paulo), 2021, 76:e2888. doi:10.6061/clinics/2021/e2888. [百度学术]
Shi ZX, Li CF, Zhao LF, et al. Computed tomography radiomic features and clinical factors predicting the response to first transarterial chemoembolization in intermediate-stage hepatocellular carcinoma[J]. Hepatobiliary Pancreat Dis Int, 2024, 23(4):361-369. doi:10.1016/j.hbpd.2023.06.011. [百度学术]
Yang C, Yang HC, Luo YG, et al. Predicting survival using Whole-Liver MRI radiomics in patients with hepatocellular carcinoma after TACE refractoriness[J]. Cardiovasc Intervent Radiol, 2024, 47(7):964-977. doi:10.1007/s00270-024-03730-z. [百度学术]
Zhang X, He Z, Zhang Y, et al. Prediction of initial objective response to drug-eluting beads transcatheter arterial chemoembolization for hepatocellular carcinoma using CT radiomics-based machine learning model[J]. Front Pharmacol, 2024, 15:1315732. doi: 10.3389/fphar.2024.1315732. [百度学术]
Mahmoud M, Lin KH, Lee RC, et al. Assessment of Y-90 radioembolization treatment response for hepatocellular carcinoma cases using MRI radiomics[J]. Mol Imaging Radionucl Ther, 2024, 33(3):156-166. doi:10.4274/mirt.galenos.2024.59365. [百度学术]
Xie T, Wei Y, Xu L, et al. Self-supervised contrastive learning using CT images for PD-1/PD-L1 expression prediction in hepatocellular carcinoma[J]. Front Oncol, 2023, 13:1103521. doi:10.3389/fonc.2023.1103521. [百度学术]
Song LN, Wang B, Cai JL, et al. Stratifying ICIs-responsive tumor microenvironment in HCC: from parsing out immune-hypoxic crosstalk to clinically applicable MRI-radiomics models[J]. Br J Cancer, 2024, 130(8):1356-1364. doi:10.1038/s41416-023-02463-z. [百度学术]
Wen H, Liang R, Liu X, et al. Predicting pathological response of neoadjuvant conversion therapy for hepatocellular carcinoma patients using CT-Based radiomics model[J]. J Hepatocell Carcinoma, 2024, 11:2145-2157. doi:10.2147/JHC.S487370. [百度学术]
Peng W, Jiang X, Zhang W, et al. A radiomics-based model can predict recurrence-free survival of hepatocellular carcinoma after curative ablation[J]. Asian J Surg, 2023, 46(7):2689-2696. doi:10.1016/j.asjsur.2022.09.130. [百度学术]
Qian GX, Xu ZL, Li YH, et al. Computed tomography-based radiomics to predict early recurrence of hepatocellular carcinoma post-hepatectomy in patients background on cirrhosis[J]. World J Gastroenterol, 2024, 30(15):2128-2142. doi:10.3748/wjg.v30.i15.2128. [百度学术]
Xie Q, Zhao Z, Yang Y, et al. A clinical-radiomic-pathomic model for prognosis prediction in patients with hepatocellular carcinoma after radical resection[J]. Cancer Med, 2024, 13(11):e7374. doi:10.1002/cam4.7374. [百度学术]
Zhao JW, Shu X, Chen XX, et al. Prediction of early recurrence of hepatocellular carcinoma after liver transplantation based on computed tomography radiomics nomogram[J]. Hepatobiliary Pancreat Dis Int, 2022, 21(6):543-550. doi:10.1016/j.hbpd.2022.05.013. [百度学术]
Petukhova-Greenstein A, Zeevi T, Yang JL, et al. Mr imaging biomarkers for the prediction of outcome after radiofrequency ablation of hepatocellular carcinoma: qualitative and quantitative assessments of the liver imaging reporting and data system and radiomic features[J]. J Vasc Interv Radiol, 2022, 33(7):814-824. doi:10.1016/j.jvir.2022.04.006. [百度学术]
Kuang F, Gao Y, Zhou Q, et al. MRI radiomics combined with clinicopathological factors for predicting 3-Year overall survival of hepatocellular carcinoma after hepatectomy[J]. J Hepatocell Carcinoma, 2024, 11:1445-1457. doi:10.2147/JHC.S464916. [百度学术]
Wang D, Zhang L, Sun Z, et al. A radiomics signature associated with underlying gene expression pattern for the prediction of prognosis and treatment response in hepatocellular carcinoma[J]. Eur J Radiol, 2023, 167:111086. doi:10.1016/j.ejrad.2023.111086. [百度学术]
Zhou M, Zhang P, Mao Q, et al. Multisequence MRI-Based radiomic features combined with inflammatory indices for predicting the overall survival of HCC patients after TACE[J]. J Hepatocell Carcinoma, 2024, 11:2049-2061. doi:10.2147/JHC.S481301. [百度学术]
Nie P, Zhang J, Miao W, et al. Incremental value of radiomics-based heterogeneity to the existing risk criteria in predicting recurrence of hepatocellular carcinoma after liver transplantation[J]. Eur Radiol, 2023, 33(9):6608-6618. doi:10.1007/s00330-023-09591-3. [百度学术]
Saalfeld S, Kreher R, Hille G, et al. Prognostic role of radiomics-based body composition analysis for the 1-year survival for hepatocellular carcinoma patients[J]. J Cachexia Sarcopenia Muscle, 2023, 14(5):2301-2309. doi:10.1002/jcsm.13315. [百度学术]
Feng L, Huang W, Pan X, et al. Predicting overall survival in hepatocellular carcinoma patients via a combined MRI radiomics and pathomics signature[J]. Transl Oncol, 2025, 51:102174. doi:10.1016/j.tranon.2024.102174. [百度学术]
Wang G, Ding F, Chen K, et al. CT-based radiomics nomogram to predict proliferative hepatocellular carcinoma and explore the tumor microenvironment[J]. J Transl Med, 2024, 22(1):683. doi:10.1186/s12967-024-05393-3. [百度学术]