A Multi-modal Fusion Framework Based on Multi-task Correlation Learning for Cancer Prognosis Prediction

Morphological attributes from histopathological images and molecular profiles from genomic data are important information to drive diagnosis, prognosis, and therapy of cancers. By integrating these heterogeneous but complementary data, many multi-modal methods are proposed to study the complex mechanisms of cancers, and most of them achieve comparable or better results from previous single-modal methods. However, these multi-modal methods are restricted to a single task (e.g., survival analysis or grade classification), and thus neglect the correlation between different tasks. In this study, we present a multi-modal fusion framework based on multi-task correlation learning (MultiCoFusion) for survival analysis and cancer grade classification, which combines the power of multiple modalities and multiple tasks. Specifically, a pre-trained ResNet-152 and a sparse graph convolutional network (SGCN) are used to learn the representations of histopathological images and mRNA expression data respectively. Then these representations are fused by a fully connected neural network (FCNN), which is also a multi-task shared network. Finally, the results of survival analysis and cancer grade classification output simultaneously. The framework is trained by an alternate scheme. We systematically evaluate our framework using glioma datasets from The Cancer Genome Atlas (TCGA). Results demonstrate that MultiCoFusion learns better representations than traditional feature extraction methods. With the help of multi-task alternating learning, even simple multi-modal concatenation can achieve better performance than other deep learning and traditional methods. Multi-task learning can improve the performance of multiple tasks not just one of them, and it is effective in both single-modal and multi-modal data.

[1]  Haleh Yasrebi,et al.  SurvJamda: an R package to predict patients' survival and risk assessment using joint analysis of microarray gene expression data , 2011, Bioinform..

[2]  Tianwei Yu,et al.  A graph‐embedded deep feedforward network for disease outcome classification and feature selection using gene expression data , 2018, Bioinform..

[3]  Jason Weston,et al.  Semi-supervised multi-task learning for predicting interactions between HIV-1 and human proteins , 2010, Bioinform..

[4]  Gang Wang,et al.  Automatic grading of prostate cancer in digitized histopathology images: Learning from multiple experts , 2018, Medical Image Anal..

[5]  Rameswar Panda,et al.  AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning , 2020, NeurIPS.

[6]  Paul M. Thompson,et al.  Brain Imaging Genomics: Integrated Analysis and Machine Learning , 2020, Proceedings of the IEEE.

[7]  Jaegul Choo,et al.  End-to-end Multi-task Learning of Missing Value Imputation and Forecasting in Time-Series Data , 2021, 2020 25th International Conference on Pattern Recognition (ICPR).

[8]  Ya Zhang,et al.  A Novel MKL Method for GBM Prognosis Prediction by Integrating Histopathological Image and Multi-Omics Data , 2020, IEEE Journal of Biomedical and Health Informatics.

[9]  Benjamin E. Gross,et al.  Integrative Analysis of Complex Cancer Genomics and Clinical Profiles Using the cBioPortal , 2013, Science Signaling.

[10]  Shu Yang,et al.  Domain-Adversarial Multi-Task Framework for Novel Therapeutic Property Prediction of Compounds , 2018, Bioinform..

[11]  Roberto Cipolla,et al.  Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[12]  Lei Du,et al.  Identifying progressive imaging genetic patterns via multi-task sparse canonical correlation analysis: a longitudinal study of the ADNI cohort , 2019, Bioinform..

[13]  Qing Xiao,et al.  Integrative analysis of cross-modal features for the prognosis prediction of clear cell renal cell carcinoma , 2020, Bioinform..

[14]  Jianhui Chen,et al.  Automated grading of breast cancer histopathology using cascaded ensemble with combination of multi-level image features , 2017, Neurocomputing.

[15]  S. Levine,et al.  Gradient Surgery for Multi-Task Learning , 2020, NeurIPS.

[16]  Wei Kong,et al.  Integrating multiple genomic imaging data for the study of lung metastasis in sarcomas using multi-dimensional constrained joint non-negative matrix factorization , 2021, Inf. Sci..

[17]  C. V. Jawahar,et al.  Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images using deep learning , 2019, Scientific Reports.

[18]  Mingon Kang,et al.  PAGE-Net: Interpretable and Integrative Deep Learning for Survival Analysis Using HistopathologicalImages and Genomic Data , 2019, PSB.

[19]  Andrew J. Davison,et al.  End-To-End Multi-Task Learning With Attention , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Benjamin E. Gross,et al.  The cBio cancer genomics portal: an open platform for exploring multidimensional cancer genomics data. , 2012, Cancer discovery.

[21]  Ivano Lauriola,et al.  MKLpy: a python-based framework for Multiple Kernel Learning , 2020, ArXiv.

[22]  Marco Körner,et al.  Auxiliary Tasks in Multi-task Learning , 2018, ArXiv.

[23]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[24]  Chao Tu,et al.  Multiscale Context-Cascaded Ensemble Framework (MsC2EF): Application to Breast Histopathological Image , 2019, IEEE Access.

[25]  Dongdong Sun,et al.  Integrating genomic data and pathological images to effectively predict breast cancer clinical outcome , 2018, Comput. Methods Programs Biomed..

[26]  Jun Cheng,et al.  Integrative Analysis of Pathological Images and Multi-Dimensional Genomic Data for Early-Stage Cancer Prognosis , 2020, IEEE Transactions on Medical Imaging.

[27]  Oznur Tastan,et al.  PAMOGK: a pathway graph kernel-based multiomics approach for patient clustering , 2020, Bioinform..

[28]  Gilles Louppe,et al.  Independent consultant , 2013 .

[29]  Zhuowen Tu,et al.  Similarity network fusion for aggregating data types on a genomic scale , 2014, Nature Methods.

[30]  Jian Guo,et al.  Multi-Constrained Joint Non-Negative Matrix Factorization With Application to Imaging Genomic Study of Lung Metastasis in Soft Tissue Sarcomas , 2019, IEEE Transactions on Biomedical Engineering.

[31]  G. Reifenberger,et al.  The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary , 2016, Acta Neuropathologica.

[32]  M. Khalid Khan,et al.  Visually Meaningful Histopathological Features for Automatic Grading of Prostate Cancer , 2017, IEEE Journal of Biomedical and Health Informatics.

[33]  Ming Y. Lu,et al.  Pathomic Fusion: An Integrated Framework for Fusing Histopathology and Genomic Features for Cancer Diagnosis and Prognosis , 2019, IEEE Transactions on Medical Imaging.

[34]  Yu Zhang,et al.  Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning , 2018, bioRxiv.

[35]  May D. Wang,et al.  Multimodal deep learning models for early detection of Alzheimer’s disease stage , 2021, Scientific Reports.

[36]  Ellery Wulczyn,et al.  Deep learning-based survival prediction for multiple cancer types using histopathology images , 2019, PloS one.

[37]  Junhee Seok,et al.  Prediction of survival risks with adjusted gene expression through risk-gene networks , 2019, Bioinform..

[38]  Shoubin Dong,et al.  A Hierarchical Graph Convolution Network for Representation Learning of Gene Expression Data , 2021, IEEE Journal of Biomedical and Health Informatics.

[39]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[40]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Haiyuan Yu,et al.  HINT: High-quality protein interactomes and their applications in understanding human disease , 2012, BMC Systems Biology.

[42]  Anne L. Martel,et al.  Deep neural network models for computational histopathology: A survey , 2019, Medical Image Anal..

[43]  Qianjin Feng,et al.  Integrative Analysis of Histopathological Images and Genomic Data Predicts Clear Cell Renal Cell Carcinoma Prognosis. , 2017, Cancer research.

[44]  Tu Bao Ho,et al.  Simple but effective methods for combining kernels in computational biology , 2008, 2008 IEEE International Conference on Research, Innovation and Vision for the Future in Computing and Communication Technologies.

[45]  Olivier Gevaert,et al.  Deep learning with multimodal representation for pancancer prognosis prediction , 2019, bioRxiv.

[46]  D. Brat,et al.  Predicting cancer outcomes from histology and genomics using convolutional networks , 2017, Proceedings of the National Academy of Sciences.