Aiming at the problems of incomplete use of patient data and rough data combination in deep learning methods for survival prediction of patients with stomach cancer, a multimodal data fusion survival prediction model for patients with stomach cancer was proposed. Firstly, multimodal data including clinical data, gene expression data and medical images of the same patient were preprocessed. Secondly, the multimodal data was input into the graph attention network (GAT) to make the multimodal data merge with each other under the attention mechanism. Thirdly, the medical images processed by convolutional neural network were introduced to work with the output of graph attention network to predict the results. Finally, ten-fold cross-validation was used to prove the stability of the model performance, and the results were compared with other methods using the same dataset. The results showed that the model proposed in this paper achieves a leading accuracy.
癌症基因组图谱(The cancer genome atlas,TCGA)是最大的癌症相关信息存储库之一。本文从TCGA官方网站(https:∥portal.gdc.cancer.gov)获取了所有必要的数据。本文使用其中的STAD数据集,STAD是TCGA内专门为胃癌研究量身定制的项目,包括超过443个患者的20 000多个不同类型的文件。
HuangS, YangJ, FongS, et al. Artificial intelligence in cancer diagnosis and prognosis: Opportunities and challenges[J]. Cancer Letters, 2020, 471: 61-71.
[2]
SungH, FerlayJ, SiegelR 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.
[3]
GuanW L, HeY, XuR H. Gastric cancer treatment: recent progress and future perspectives[J]. Journal of Hematology & Oncology, 2023, 16(1): 57-84.
QinLi-li, MaXiao-bo, ZhaoTian-ye, et al. Effects of MMP-9 and TIMP-1 expressions on prognostic evaluation of gastric cancer patients after radical gastrectomy[J]. Journal of Jilin University (Medicine Edition), 2022, 48(1): 163-171.
CuiHai-kang, ZhangXu-dong, LiXiao-ning, et al. Bioinformatics analysis on predition effect of subtypes of cell pyroptosis and APOD on prognosis of gastric cancer patients[J]. Journal of Jilin University (Medicine Edition), 2023, 49(5): 1268-1279.
[8]
BoornH G, EngelhardtE G, KleefJ, et al. Prediction models for patients with esophageal or gastric cancer: a systematic review and meta-analysis[J]. Plos One, 2018, 13(2): No.e0192310.
[9]
HosnyA, ParmarC, QuackenbushJ, et al. Artificial intelligence in radiology[J]. Springer Science and Business Media LLC, 2018, 18: 500-510.
[10]
TranK A, KondrashovaO, BradleyA, et al. Deep learning in cancer diagnosis, prognosis and treatment selection[J]. Genome Medicine, 2021, 13(1): 152-168.
[11]
KrizhevskyA, SutskeverI, HintonG E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[12]
LecunY, BengioY, HintonG. Deep learning[J]. Nature, 2015, 521: 436-444.
[13]
KatzmanJ L, ShahamU, CloningerA, et al. Deepsurv: personalized treatment recommender system using a cox proportional hazards deep neural network[J]. BMC Medical Research Methodology, 2018, 18(1): 24-35.
[14]
ChoiS, KimS. Artificial intelligence in the pathology of gastric cancer[J]. Journal of Gastric Cancer, 2023, 23(3): 410-427.
[15]
DeepaP, GunavathiC. A systematic review on machine learning and deep learning techniques in cancer survival prediction[J]. Progress in Biophysics and Molecular Biology, 2022, 174: 62-71.
[16]
LipkovaJ, ChenR J, ChenB, et al. Artificial intelligence for multimodal data integration in oncology[J]. Cancer Cell, 2022, 40(10): 1095-1110.
[17]
BoehmK M, KhosraviP, VanguriR, et al. Harnessing multimodal data integration to advance precision oncology[J]. Nature Reviews Cancer, 2021, 22(2): 114-126.
[18]
WeiT, YuanX, GaoR, et al. Survival prediction of stomach cancer using expression data and deep learning models with histopathological images[J]. Cancer Science, 2022, 114(2): 690-701.
[19]
CoxD R. Regression models and life-tables[J]. Journal of the Royal Statistical Society, Series B (Statistical Methodology), 1972, 34(2): 187-202.
TarkhanA, SimonN, BengtssonT, et al. Survival prediction using deep learning[C]∥Proceedings of AAAI Spring Symposium on Survival Prediction–Algorithms, Challenges, and Applications, Virtual, USA, 2021: 1-8.
[22]
LiH, LinD, YuZ, et al. A nomogram model based on the number of examined lymph nodes–related signature to predict prognosis and guide clinical therapy in gastric cancer[J]. Frontiers in Immunology, 2022, 13: No.947802.
[23]
WuJ, WangX, WangN, et al. Identification of novel antioxidant gene signature to predict the prognosis of patients with gastric cancer[J]. World Journal of Surgical Oncology, 2021, 19(1): No.1901219.
[24]
DaiW, XiaoY, TangW, et al. Identification of an emt-related gene signature for predicting overall survival in gastric cancer[J]. Frontiers in Genetics, 2021, 12: No. 661306.
[25]
WangM, JingJ, LiH, et al. The expression characteristics and prognostic roles of autophagy-related genes in gastric cancer[J]. PeerJ, 2021, 9: No.e10814.
[26]
LiuM, LiJ, HuangZ, et al. Gastric cancer risk-scoring system based on analysis of a competing endogenous RNA network[J]. Translational Cancer Research, 2020, 9(6): 3889-3902.
[27]
KourouK, ExarchosT P, ExarchosK P, et al. Machine learning applications in cancer prognosis and prediction[J]. Computational and Structural Biotechnology Journal, 2015, 13: 8-17.
[28]
ShivaswamyP K, ChuW, JanscheM. A support vector approach to censored targets[C]∥ Proceedings of Seventh IEEE International Conference on Data Mining, Omaha, USA, 2007: 655-660.
[29]
IshwaranH, KogalurU B, BlackstoneE H, et al. Random survival forests[J]. Annals of Applied Statistics, 2008, 2: No.AOAS169.
[30]
ChenT, GuestrinC. XGBoost: a scalable tree boosting system[C]∥Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, USA, 2016: 785-794.
[31]
LiuP, FuB, YangS X, et al. Optimizing survival analysis of xgboost for ties to predict disease progression of breast cancer[J]. Institute of Electrical and Electronics Engineers, 2021, 68: 148-160.
[32]
MaB, YanG, ChaiB, et al. XGBLC: an improved survival prediction model based on XGBoost[J]. Bioinformatics, 2021, 38(2): 410-418.
[33]
LiG, HuoD, GuoN, et al. Integrating multiple machine learning algorithms for prognostic prediction of gastric cancer based on immune-related lncRNAs[J]. Frontiers in Genetics, 2023, 14: No.1106724.
[34]
ChaiH, ZhouX, ZhangZ, et al. Integrating multi-omics data through deep learning for accurate cancer prognosis prediction[J]. Computers in Biology and Medicine, 2021, 134: No.104481.
[35]
WangY, ZhangZ, ChaiH, et al. Multi-omics cancer prognosis analysis based on graph convolution network[C]∥Proceedings of IEEE International Conference on Bioinformatics and Biomedicine, Houston, USA, 2021: 1564-1568.
[36]
ZhangY, XiongS, WangZ, et al. Local augmented graph neural network for multi-omics cancer prognosis prediction and analysis[J]. Methods, 2023, 213: 1-9.
[37]
AvelarP H C, TavaresA R, SilveiraT L T, et al. Superpixel image classification with graph attention networks[C]∥Proceedings of 33rd SIBGRAPI Conference on Graphics, Patterns and Images, Porto de Galinhas, Brazil, 2020: 203-209.
[38]
VelickovicP, CucurullG, CasanovaA, et al. Graph Attention Networks[EB/OL]. [2023-11-04].
[39]
FuX, PatrickE, YangJ Y H, et al. Deep multimodal graph-based network for survival prediction from highly multiplexed images and patient variables[J]. Computers in Biology and Medicine, 2023, 154: No.106576.
[40]
DuanM, WangY, ZhaoD, et al. Orchestrating information across tissues via a novel multitask GAT framework to improve quantitative gene regulation relation modeling for survival analysis[J]. Briefings in Bioinformatics, 2023, 24(4): 1-10.
[41]
YeL, ZhangY, YangX, et al. An ovarian cancer susceptible gene prediction method based on deep learning methods[J]. Frontiers in Cell and Developmental Biology, 2021, 9: No.730475.
[42]
AdeoyeJ, HuiL, KoohiM M, et al. Comparison of time-to-event machine learning models in predicting oral cavity cancer prognosis[J]. International Journal of Medical Informatics, 2022, 157: No.104635.
[43]
LerademacherJ, WangX. Time-to-event data: an overview and analysis considerations[J]. Journal of Thoracic Oncology, 2021, 16(7): 1067-1074.
[44]
AminM B, GreeneF L, EdgeS B, et al. The eighth edition AJCC cancer staging manual: continuing to build a bridge from a population-based to a more "personalized" approach to cancer staging[J]. CA-A Cancer Journal for Clinicians, 2017, 67(2): 93-99.
[45]
MarcoliniA, BussolaN, ArbitrioE, et al. Histolab: a python library for reproducible digital pathology preprocessing with automated testing[J]. Software X, 2020, 20: No.101237.
[46]
HeK, ZhangX, RenS, et al. Deep residual learning for image recognition[C]∥Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 770-778.
[47]
BrentnallA R, CuzickJ. Use of the concordance index for predictors of censored survival data[J]. Statistical Methods in Medical Research, 2018, 27(8): 2359-2373.
[48]
KaplanE L, MeierP. Nonparametric estimation from incomplete observations[J]. Journal of the American Statistical Association, 1958, 53(282): 457-481.
[49]
PanQ K, XuX X, QiC, et al. Feature fusion: graph attention network and cnn combing for hyperspectral image classification[C]∥Proceedings of the 5th International Conference on Control and Computer Vision, New York, USA, 2022: 171-178.
[50]
XieY, NiuG, DaQ, et al. Survival prediction for gastric cancer via multimodal learning of whole slide images and gene expression[C]∥Proceedings of 2022 IEEE International Conference on Bioinformatics and Biomedicine, Las Vegas, USA, 2022: 1311-1316.
ZhangDe-hong, ZhengMing-zhu, LiJia-qiu, et al. Bioinformatics analysis based on expressions of MSR1 mRNA and protein in pan-cancer tissue and its significance[J]. Journal of Jilin University (Medicine Edition), 2023, 49(2): 425-439.
[53]
SelvarajuR R, CogswellM, DasA, et al. Grad-CAM:visual explanations from deep networks via gradient-based localization[C]∥2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 618-626.
[54]
KrzyzińskiM, SpytekM, BanieckiH, et al. Survshap(t): time-dependent explanations of machine learning survival models[J]. Knowledge-Based Systems, 2023, 262: 110234.