Graph Attention Network for Prostate Cancer Lymph Node Invasion Prediction

Maxence Larose, Nawar Touma, Nicolas Raymond, Danahé LeBlanc, Fatemeh Rasekh, Bertrand Neveu, Hélène Hovington, Martin Vallières, Frédéric Pouliot, Louis Archambault

Keywords: Graph Attention Network, Prostate cancer, Lymph node invasion, Outcome prediction, Multi-modal data, FDG-PET, CT, Radiomics

TL;DR: A graph attention network (GAT) model combining radiomics and clinical data to improve the performance and interpretability of lymph node invasion prediction in high-grade prostate cancer.

Abstract: This work proposes the use of a graph attention network (GAT) model combining radiomics and clinical data to improve the performance and interpretability of lymph node invasion (LNI) prediction in high-grade prostate cancer (PCa). Experiments were conducted using an in-house dataset of 170 high-grade PCa (Gleason $\geq8$), each with FDG-PET/CT images acquired prior to prostatectomy. To ensure interpretable connections between patients, the graph structure was constructed by merging the most important radiomic shape-based CT feature and first-order intensity-based PET feature to the clinically relevant features. The performance of the GAT model was compared to random forest (RF) and support vector machine (SVM) classifiers. On the 30 patients test set, the models reached {AUC=0.765, bACC= 0.705}, {AUC=0.748, bACC=0.66} and {AUC=0.725,bACC=0.725} for the GAT, RF and SVM models respectively. Even though SVM achieved higher balanced accuracy than GAT, the predictions made by the latter are more interpretable through the graph structure and attention mechanism.

Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.

Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.

Paper Type: novel methodological ideas without extensive validation

Primary Subject Area: Integration of Imaging and Clinical Data

Secondary Subject Area: Application: Radiology

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.