[1]姚纯,熊波,杨桂汉,等.MRI深度学习量化预测进展期胃癌隐匿性腹膜转移[J].中国医学物理学杂志,2026,43(7):980-986.[doi:DOI:10.3969/j.issn.1005-202X.2026.07.020]
　YAO Chun,XIONG Bo,YANG Guihan,et al.MRI-based deep learning models for quantitative prediction of occult peritoneal metastasis in advanced gastric cancer[J].Chinese Journal of Medical Physics,2026,43(7):980-986.[doi:DOI:10.3969/j.issn.1005-202X.2026.07.020]
点击复制

MRI深度学习量化预测进展期胃癌隐匿性腹膜转移()

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
43卷
期数:
2026年第7期
页码:
980-986
栏目:
医学人工智能
出版日期:
2026-07-22

文章信息/Info

Title:
MRI-based deep learning models for quantitative prediction of occult peritoneal metastasis in advanced gastric cancer
文章编号:
1005-202X（2026）07-0980-07
作者:
姚纯; 熊波; 杨桂汉; 梁月梅; 黎健辉; 杨志企
梅州市人民医院医学影像中心， 广东 梅州 514031
Author(s):
YAO Chun;  XIONG Bo;  YANG Guihan;  LIANG Yuemei;  LI Jianhui;  YANG Zhiqi
Medical Imaging Center, Meizhou Peoples Hospital, Meizhou 514031, China
关键词:
胃癌; 隐匿性腹膜转移; 磁共振成像; 深度学习
Keywords:
Keywords: gastric cancer occult peritoneal metastasis magnetic resonance imaging deep learning
分类号:
R318；R735.2
DOI:
DOI:10.3969/j.issn.1005-202X.2026.07.020
文献标志码:
A
摘要:
目的：探讨基于MRI的多种深度学习（DL）模型预测进展期胃癌隐匿性腹膜转移（OPM）的可行性及价值。方法：回顾性纳入476例术前MRI诊断为腹膜转移阴性、经手术病理确诊的进展期胃癌患者，按7:3随机分为训练集（334例）和测试集（142例）。在T2WI-FS序列上手动勾画肿瘤三维感兴趣区，训练ResNet50、Med-ViT和TP-Mamba 3种DL模型，采用受试者工作特征曲线下面积（AUC）、敏感度、特异度、DeLong检验、综合判别改进指数（IDI）及临床决策曲线（DCA）评估效能。结果：Med-ViT模型（训练集AUC=0.860；测试集AUC=0.763）预测OPM的效能均优于TP-Mamba（训练集AUC=0.767；测试集AUC=0.652）及ResNet50模型（训练集AUC=0.528；测试集AUC=0.570）。在训练集及测试集中，DeLong检验显示Med-ViT的AUC值均显著高于其余模型（P<0.05），IDI分析显示Med-ViT模型综合判别改善能力最优，DCA表明其净获益最高。结论：基于自注意力机制的Med-ViT深度学习模型可准确预测进展期胃癌OPM风险，效能显著优于ResNet50与TP-Mamba，有望成为术前无创筛查OPM高危患者的辅助工具。
Abstract:
Abstract: Objective To explore the feasibility and value of multiple deep learning models based on magnetic resonance imaging (MRI) for the prediction of occult peritoneal metastasis (OPM) in advanced gastric cancer. Methods A retrospective analysis was conducted on 476 patients with pathologically confirmed advanced gastric cancer and negative preoperative MRI findings for peritoneal metastasis. All patients were randomly divided into a training set (n=334) and a test set (n=142) at a ratio of 7:3. Three-dimensional tumor regions of interest were manually delineated on T2WI-FS sequences. Three deep learning models, including ResNet50, Med-ViT, and TP-Mamba, were trained, and their performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, the DeLong test, integrated discrimination improvement, and decision curve analysis. Results Med-ViT model (training set AUC=0.860 test set AUC=0.763) exhibited superior performance in predicting OPM compared with TP-Mamba model (training set AUC=0.767 test set AUC=0.652) and ResNet50 model (training set AUC=0.528 test set AUC=0.570). In both the training and test sets, the DeLong test showed that Med-ViT had significantly higher AUC values than the other two models (P<0.05). Integrated discrimination improvement analysis demonstrated that Med-ViT model achieved the optimal comprehensive discrimination improvement ability, and decision curve analysis reflected its greatest net benefit. Conclusion The self-attention mechanism-based Med-ViT deep learning model can accurately predict the risk of OPM in advanced gastric cancer and outperforms ResNet50 and TP-Mamba. Therefore, it is expected to serve as a reliable auxiliary tool for non-invasive preoperative screening of patients at high risk of OPM.

相似文献/References:

[1]易伟松,刘文强,陆 东,等.高光谱成像结合化学计量学诊断胃癌组织[J].中国医学物理学杂志,2015,32(01):124.[doi:10.3969/j.issn.1005-202X.2015.01.028]
[2]宋威,赵迪,鹿红,等.胃癌术后调强放疗射野角度优化的剂量学[J].中国医学物理学杂志,2015,32(06):815.[doi:doi:10.3969/j.issn.1005-202X.2015.06.012]
　[J].Chinese Journal of Medical Physics,2015,32(7):815.[doi:doi:10.3969/j.issn.1005-202X.2015.06.012]
[3]易伟松,钱辉跃,江厚敏.光纤和显微拉曼光谱结合化学计量学鉴别胃癌组织[J].中国医学物理学杂志,2016,33(2):134.[doi:10.3969/j.issn.1005-202X.2016.02.006]
[4]卢晓光,刘细友,郑言宏,等.胃癌术后不同IMRT布野方式对剂量分布的影响[J].中国医学物理学杂志,2016,33(7):664.[doi:10.3969/j.issn.1005-202X.2016.07.004]
[5]刘光波,刘志坤,闫慧娟,等.不同照射技术在全胃癌放疗中的剂量学比较与分析[J].中国医学物理学杂志,2016,33(11):1111.[doi:10.3969/j.issn.1005-202X.2016.11.006]
　[J].Chinese Journal of Medical Physics,2016,33(7):1111.[doi:10.3969/j.issn.1005-202X.2016.11.006]
[6]蒋大振,刘晖,戴静,等. 胃癌调强放疗中多叶光栅3种状态的剂量学比较[J].中国医学物理学杂志,2019,36(2):166.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.009]
　JIANG Dazhen,LIU Hui,DAI Jing,et al. Dosimetric comparison among split-field, fixed-jaw and rotating multi-leaf collimator in the radiotherapy of gastric carcinoma[J].Chinese Journal of Medical Physics,2019,36(7):166.[doi:DOI:10.3969/j.issn.1005-202X.2019.02.009]
[7]胡志纲,刘勇强,任建,等.胃癌术后不同布野方案对调强放疗剂量分布的影响[J].中国医学物理学杂志,2019,36(12):1400.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.007]
　HU Zhigang,LIU Yongqiang,REN Jian,et al.Effects of different field arrangements on the dose distribution of postoperative intensity-modulated radiotherapy for gastric cancer[J].Chinese Journal of Medical Physics,2019,36(7):1400.[doi:DOI:10.3969/j.issn.1005-202X.2019.12.007]
[8]范显文,何二松,林昌荣,等.胃癌患者身体质量指数对腹腔镜术式选择及效果的影响[J].中国医学物理学杂志,2020,37(4):498.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.018]
　FAN Xianwen,HE Ersong,LIN Changrong,et al.Effects of body mass index on the selection and efficacy of laparoscopic surgery in patients with gastric cancer[J].Chinese Journal of Medical Physics,2020,37(7):498.[doi:DOI:10.3969/j.issn.1005-202X.2020.04.018]
[9]赵呈陆,方志军,高永彬,等.基于改进型V-net卷积神经网络的胃壁分割方法[J].中国医学物理学杂志,2021,38(10):1243.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.011]
　ZHAO Chenglu,FANG Zhijun,GAO Yongbin,et al.Gastric wall segmentation based on improved V-net convolutional neural network[J].Chinese Journal of Medical Physics,2021,38(7):1243.[doi:DOI:10.3969/j.issn.1005-202X.2021.10.011]
[10]张育,赵轶峰,苏卓彬,等.基于卷积神经网络的胃癌癌前病变图像分类方法[J].中国医学物理学杂志,2022,39(2):209.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.014]
　ZHANG Yu,ZHAO Yifeng,SU Zhuobin,et al.Image classification of gastric precancerous lesions based on convolutional neural network[J].Chinese Journal of Medical Physics,2022,39(7):209.[doi:DOI:10.3969/j.issn.1005-202X.2022.02.014]

备注/Memo

备注/Memo:
【收稿日期】2025-12-03 【基金项目】广东省医学科研基金（B2023445）；梅州市社会发展科技计划项目（2023B19） 【作者简介】姚纯，副主任医师，研究方向：消化系统影像诊断，E-mail: 164225090@qq.com 【通信作者】杨志企，硕士，主任医师，研究方向：消化系统影像诊断，E-mail: y13643090854@163.com
更新日期/Last Update: 2026-07-23