Interpretable Prediction of Lymph Node Metastasis in Rectal Cancer MRI Using Variational Autoencoders

TL;DR

This study introduces a variational autoencoder-based model for interpretable lymph node metastasis prediction in rectal cancer MRI, achieving state-of-the-art accuracy and offering more meaningful feature representations than traditional CNNs.

Contribution

The paper proposes replacing CNNs with VAEs for lymph node metastasis prediction, enhancing interpretability through structured latent space and demonstrating superior performance on MRI data.

Findings

VAE-MLP achieved AUC 0.86, sensitivity 0.79, specificity 0.85.

The VAE provides more interpretable features than CNNs.

Model outperforms existing approaches on the dataset.

Abstract

Effective treatment for rectal cancer relies on accurate lymph node metastasis (LNM) staging. However, radiological criteria based on lymph node (LN) size, shape and texture morphology have limited diagnostic accuracy. In this work, we investigate applying a Variational Autoencoder (VAE) as a feature encoder model to replace the large pre-trained Convolutional Neural Network (CNN) used in existing approaches. The motivation for using a VAE is that the generative model aims to reconstruct the images, so it directly encodes visual features and meaningful patterns across the data. This leads to a disentangled and structured latent space which can be more interpretable than a CNN. Models are deployed on an in-house MRI dataset with 168 patients who did not undergo neo-adjuvant treatment. The post-operative pathological N stage was used as the ground truth to evaluate model predictions. Our proposed model 'VAE-MLP' achieved state-of-the-art performance on the MRI dataset, with cross-validated metrics of AUC 0.86 +/- 0.05, Sensitivity 0.79 +/- 0.06, and Specificity 0.85 +/- 0.05. Code is available at: https://github.com/benkeel/Lymph_Node_Classification_MIUA.