计算机科学 ›› 2026, Vol. 53 ›› Issue (4): 284-290.doi: 10.11896/jsjkx.250600188
汪少东1, 李柳军2, 李蕊1, 苏中振2, 陆遥1
WANG Shaodong1, LI Liujun2, LI Rui1, SU Zhongzhen2, LU Yao1
摘要： 微血管侵犯(MVI)作为肝细胞癌(HCC)术后复发和生存率低的关键预后因素,其术前精准定位对治疗决策至关重要。针对现有放射组学方法特征泛化弱、可解释性差且忽略瘤周MVI空间分布的问题,提出通过病理全切片(WSI)与三维超声(3D US)的空间融合实现MVI三维定位,并设计特征张量融合深度学习模型(融合多尺度特征、特征张量及正交化损失函数)提取瘤周MVI分布语义特征。在收集的数据集上开展了详细的对比分析和消融实验研究,使用受试者工作特征曲线下的面积(AUC)、准确度(Accuracy)和F1分数等指标证明了该模型的有效性。实验验证了该模型性能优异(AUC:0.910,ACC:0.930,F1 score:0.852),证实了其在术前MVI精确诊断中的临床潜力。
中图分类号:
| [1]SUNG H,FERLAY J,SIEGEL R L,et al.Global cancer statistics 2020:GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J].CA:A Cancer Journal for Clinicians,2021,71(3):209-249. [2]VILLANUEVA A.Hepatocellular carcinoma.reply[J].TheNew England journal of medicine,2019,381(1):e2. [3]VITALE A,PECK-RADOSAVLJEVIC M,GIANNINI E G,et al.Personalized treatment of patients with very early hepatocellular carcinoma[J].Journal of Hepatology,2017,66(2):412-423. [4]ZHOU J,SUN H,WANG Z,et al.Guidelines for the diagnosis and treatment of hepatocellularcarcinoma(2019 edition)[J].Liver Cancer,2020,9(6):682-720. [5]NJEI B,ROTMAN Y,DITAH I,et al.Emerging trends in hepatocellular carcinoma incidence and mortality[J].Hepatology,2015,61(1):191-199. [6]MARENGO A,ROSSO C,BUGIANESI E.Liver cancer:con-nections with obesity,fatty liver,and cirrhosis[J].Annual Review of Medicine,2016,67(1):103-117. [7]LAI C L,RATZIU V,YUEN M F,et al.Viral hepatitis B[J].The Lancet,2003,362(9401):2089-2094. [8]YANG L,GU D,WEI J,et al.A radiomics nomogram for preoperative prediction of microvascular invasion in hepatocellular carcinoma[J].Liver Cancer,2019,8(5):373-386. [9]CHAN A W H,ZHONG J,BERHANE S,et al.Development ofpre and post-operative models to predict early recurrence of hepatocellular carcinoma after surgical resection[J].Journal of Hepatology,2018,69(6):1284-1293. [10]CHEN Z H,ZHANG X P,FENG J K,et al.Actual long-term survival in hepatocellular carcinoma patients with microvascular invasion:a multicenter study from China[J].Hepatology International,2021,15:642-650. [11]DONG Y,WANG Q M,LI Q,et al.Preoperative prediction of microvascular invasion of hepatocellular carcinoma:radiomics algorithm based on ultrasound original radio frequency signals[J].Frontiers in Oncology,2019,9:1203. [12]XU X,ZHANG H L,LIU Q P,et al.Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma[J].Journal of Hepatology,2019,70(6):1133-1144. [13]NITTA H,ALLARD M A,SEBAGH M,et al.Prognostic value and prediction of extratumoral microvascular invasion for hepatocellular carcinoma[J].Annals of Surgical Oncology,2019,26:2568-2576. [14]LI S,ZENG Q,LIANG R,et al.Using systemic inflammatorymarkers to predict microvascular invasion before surgery in patients with hepatocellular carcinoma[J].Frontiers in Surgery,2022,9:833779. [15]MAO S,YU X,YANG Y,et al.Preoperative nomogram for microvascular invasion prediction based on clinical database in hepatocellular carcinoma[J].Scientific Reports,2021,11(1):13999. [16]SHI L,QU Z,YANG Y,et al.Analysis of Related Risk Factors of Microvascular Invasion in Hepatocellular Carcinoma[J].Computational and Mathematical Methods in Medicine,2022,2022(1):8195512. [17]ZHOU Q,ZHOU C,YIN Y,et al.Development and validation of a nomogram combining hematological and imaging features for preoperative prediction of microvascular invasion in hepatocellular carcinoma patients[J].Annals of Translational Medicine,2021,9(5):402. [18]COMEN E A,BOWMAN R L,KLEPPE M.Underlying causes and therapeutic targeting of the inflammatory tumor microenvironment[J].Frontiers in Cell and Developmental Biology,2018,6:56. [19]WANG H,LU Y,LIU R,et al.A non-invasive nomogram for preoperative prediction of microvascular invasion risk in hepatocellular carcinoma[J].Frontiers in Oncology,2021,11:745085. [20]ZHAN J,WANG J,ZHANG Z,et al.Noninvasive diagnosis of significant liver inflammation in patients with chronic hepatitis B in the indeterminate phase[J].Virulence,2023,14(1):2268497. [21]CHONG H H,YANG L,SHENG R F,et al.Multi-scale and multi-parametric radiomics of gadoxetate disodium-enhanced MRI predicts microvascular invasion and outcome in patients with solitary hepatocellular carcinoma≤ 5 cm[J].European Radiology,2021,31:4824-4838. [22]ABI-JAOUDEH N,KRUECKER J,KADOURY S,et al.Multimodality image fusion-guided procedures:technique,accuracy,and applications[J].Cardiovascular and Interventional Radiology,2012,35:986-998. [23]CARCINOMA VILLANUEVA A.Hepatocellular[J].The New England Journal of Medicine,2019,380:1450-1462. [24]ZHANG R,XU L,WEN X,et al.A nomogram based on bi-regional radiomics features from multimodal magnetic resonance imaging for preoperative prediction of microvascular invasion in hepatocellular carcinoma[J].Quantitative Imaging in Medicine and Surgery,2019,9(9):1503. [25]LIU B,ZENG Q,HUANG J,et al.IVIM using convolutional neural networks predicts microvascular invasion in HCC[J].European Radiology,2022,32(10):7185-7195. [26]WANG L,WU M,LI R,et al.MVI-Mind:a novel deep-learning strategy using computed tomography(CT)-based radiomics for end-to-end high efficiency prediction of microvascular invasion in hepatocellular carcinoma[J].Cancers,2022,14(12):2956. [27]PERCIE DU SERT N,HURST V,AHLUWALIA A,et al.The ARRIVE guidelines 2.0:Updated guidelines for reporting animal research[J].Journal of Cerebral Blood Flow & Metabolism,2020,40(9):1769-1777. [28]BEUTEL J.Handbook of medical imaging[M].Spie Press,2000. [29]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010. |
| [1] | 尹创, 刘建毅, 张茹. 跨模态融合的少样本勒索软件分类器:基于预训练模型的多模态编码 Cross-modal Fusion Few-sample Ransomware Classifier:Multimodal Encoding Based on Pre-trained Models 计算机科学, 2026, 53(4): 435-444. https://doi.org/10.11896/jsjkx.250500078 |
| [2] | 徐成, 刘宇轩, 王欣, 张铖, 姚登峰, 袁家政. 大语言模型驱动的言语障碍评估方法综述 Review of Speech Disorder Assessment Methods Driven by Large Language Models 计算机科学, 2026, 53(3): 307-320. https://doi.org/10.11896/jsjkx.250300125 |
| [3] | 杜剑彤, 管泽礼, 薛哲. 基于多任务学习的眼科视频特征融合与多维画像 Multi-task Learning-based Ophthalmic Video Feature Fusion and Multi-dimensional Profiling 计算机科学, 2026, 53(3): 383-391. https://doi.org/10.11896/jsjkx.260200058 |
| [4] | 卓铁农, 英迪, 赵晖. 融合跨模态注意力与角色交互的学生课堂专注度研究 Research on Student Classroom Concentration Integrating Cross-modal Attention and Role Interaction 计算机科学, 2026, 53(2): 67-77. https://doi.org/10.11896/jsjkx.250300026 |
| [5] | 陈海涛, 梁俊威, 陈晨, 王宇帆, 周宇. 基于多模态体育教育数据的图空间融合动作识别方法 Multimodal Physical Education Data Fusion via Graph Alignment for Action Recognition 计算机科学, 2026, 53(2): 89-98. https://doi.org/10.11896/jsjkx.250800007 |
| [6] | 黄靖, 王腾, 刘健, 胡凯, 彭鑫, 黄亚敏, 文元桥. 多模态水声图像目标视觉检测 Multimodal Visual Detection for Underwater Sonar Target Images 计算机科学, 2026, 53(2): 227-235. https://doi.org/10.11896/jsjkx.241200082 |
| [7] | 万盛华, 徐兴业, 甘乐, 詹德川. 基于多模态大模型辅助视频动作生成的预训练世界模型 Pre-training World Models from Videos with Generated Actions by Multi-modal Large Models 计算机科学, 2026, 53(1): 51-57. https://doi.org/10.11896/jsjkx.250800033 |
| [8] | 赵文豪, 梅萌, 王小平, 罗航宇. PKHOI:利用先验知识增强人-物交互检测算法 PKHOI:Enhancing Human-Object Interaction Detection Algorithms with Prior Knowledge 计算机科学, 2026, 53(1): 141-152. https://doi.org/10.11896/jsjkx.250100086 |
| [9] | 卜韵阳, 齐彬廷, 卜凡亮. 跨模态不一致感知下双视角交互融合的多模态情感分析 Multimodal Sentiment Analysis for Interactive Fusion of Dual Perspectives Under Cross-modalInconsistent Perception 计算机科学, 2026, 53(1): 187-194. https://doi.org/10.11896/jsjkx.241100029 |
| [10] | 范家斌, 王宝会, 陈继轩. 基于文本-图像多模态融合的变电所布局图纸图符检测方法 Method for Symbol Detection in Substation Layout Diagrams Based on Text-Image MultimodalFusion 计算机科学, 2026, 53(1): 206-215. https://doi.org/10.11896/jsjkx.250200090 |
| [11] | 宋志超, 张建平, 张其阳, 方玺, 谢良, 宋少莉, 胡战利. 面向肿瘤早期诊断的延迟PET图像重建:多模态PET/CT核矩阵约束延迟成像算法 Delayed PET Reconstruction for Early Tumor Diagnosis:Multimodal PET/CT Nuclear Matrix- constrained Delayed Imaging Algorithm 计算机科学, 2025, 52(9): 119-127. https://doi.org/10.11896/jsjkx.250400037 |
| [12] | 刘威, 许勇, 方娟, 李城, 祝玉军, 方群, 何昕. 基于雷达和视觉融合的多模态空中手写体识别 Multimodal Air-writing Gesture Recognition Based on Radar-Vision Fusion 计算机科学, 2025, 52(9): 259-268. https://doi.org/10.11896/jsjkx.240400143 |
| [13] | 高龙, 李旸, 王素格. 基于分步协作融合表示的情感分类方法 Sentiment Classification Method Based on Stepwise Cooperative Fusion Representation 计算机科学, 2025, 52(9): 313-319. https://doi.org/10.11896/jsjkx.240700161 |
| [14] | 刘健, 姚任远, 高楠, 梁荣华, 陈朋. VSRI:基于视觉语义关系交互的图像字幕生成方法 VSRI:Visual Semantic Relational Interactor for Image Caption 计算机科学, 2025, 52(8): 222-231. https://doi.org/10.11896/jsjkx.240600082 |
| [15] | 岳彩通, 叶文豪, 张颖洁, 梁静, 林泓宇. 基于局部中心解聚类的多模态多目标优化算法 Multimodal Multiobjective Optimization Algorithm Based on Local Center Clustering 计算机科学, 2025, 52(8): 288-299. https://doi.org/10.11896/jsjkx.240700094 |
|
||
首页