Lymph Node Graph Neural Networks for Cancer Metastasis Prediction

Predicting outcomes, such as survival or metastasis for individual cancer patients is a crucial component of precision oncology. Machine learning (ML) offers a promising way to exploit rich multi-modal data, including clinical information and imaging to learn predictors of disease trajectory and help inform clinical decision making. In this paper, we present a novel graph-based approach to incorporate imaging characteristics of existing cancer spread to local lymph nodes (LNs) as well as their connectivity patterns in a prognostic ML model. We trained an edge-gated Graph Convolutional Network (Gated-GCN) to accurately predict the risk of distant metastasis (DM) by propagating information across the LN graph with the aid of soft edge attention mechanism. In a cohort of 1570 head and neck cancer patients, the Gated-GCN achieves AUROC of 0.757 for 2-year DM classification and C-index of 0.725 for lifetime DM risk prediction, outperforming current prognostic factors as well as previous approaches based on aggregated LN features. We also explored the importance of graph structure and individual lymph nodes through ablation experiments and interpretability studies, highlighting the importance of considering individual LN characteristics as well as the relationships between regions of cancer spread.

[1]  Anne L. Martel,et al.  A margin sharpness measurement for the diagnosis of breast cancer from magnetic resonance imaging examinations. , 2011, Academic radiology.

[2]  Ankur Taly,et al.  Axiomatic Attribution for Deep Networks , 2017, ICML.

[3]  Pietro Liò,et al.  On Graph Classification Networks, Datasets and Baselines , 2019, ArXiv.

[4]  Wei Xu,et al.  Deintensification candidate subgroups in human papillomavirus-related oropharyngeal cancer according to minimal risk of distant metastasis. , 2013, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[5]  Quynh-Thu Le,et al.  Delineation of the neck node levels for head and neck tumors: a 2013 update. DAHANCA, EORTC, HKNPCSG, NCIC CTG, NCRI, RTOG, TROG consensus guidelines. , 2014, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[6]  B. Judson,et al.  Patterns of failure in high-metastatic node number human papillomavirus-positive oropharyngeal carcinoma. , 2018, Oral oncology.

[7]  Anna Goldenberg,et al.  What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use , 2019, MLHC.

[8]  Jan Eric Lenssen,et al.  Fast Graph Representation Learning with PyTorch Geometric , 2019, ArXiv.

[9]  Adam P. Harrison,et al.  Lymph Node Gross Tumor Volume Detection in Oncology Imaging via Relationship Learning Using Graph Neural Network , 2020, MICCAI.

[10]  Xavier Bresson,et al.  Benchmarking Graph Neural Networks , 2020, ArXiv.

[11]  Ruijiang Li,et al.  Integrating Tumor and Nodal Imaging Characteristics at Baseline and Mid-Treatment Computed Tomography Scans to Predict Distant Metastasis in Oropharyngeal Cancer Treated With Concurrent Chemoradiotherapy. , 2019, International journal of radiation oncology, biology, physics.

[12]  R. Fisher,et al.  Head and Neck Squamous Cell Carcinoma , 2020, Definitions.

[13]  Russell Greiner,et al.  Learning Patient-Specific Cancer Survival Distributions as a Sequence of Dependent Regressors , 2011, NIPS.

[14]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[15]  F. Harrell,et al.  Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors , 2005 .

[16]  Xavier Bresson,et al.  Residual Gated Graph ConvNets , 2017, ArXiv.

[17]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[18]  Andriy Fedorov,et al.  Computational Radiomics System to Decode the Radiographic Phenotype. , 2017, Cancer research.

[19]  Michael F. Milosevic,et al.  A Machine Learning Challenge for Prognostic Modelling in Head and Neck Cancer Using Multi-modal Data , 2021, ArXiv.

[20]  Issam El-Naqa,et al.  Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer , 2017, Scientific Reports.

[21]  O. Riesterer,et al.  Combined CT radiomics of primary tumor and metastatic lymph nodes improves prediction of loco-regional control in head and neck cancer , 2019, Scientific Reports.

[22]  Stephane Fotso,et al.  Deep Neural Networks for Survival Analysis Based on a Multi-Task Framework , 2018, ArXiv.

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.