Class-Aware Adversarial Lung Nodule Synthesis in CT Images

TL;DR

This paper introduces a class-aware adversarial framework for synthesizing diverse lung nodules in CT images to augment datasets and improve lung nodule malignancy classification accuracy.

Contribution

It presents a novel coarse-to-fine patch in-painter with class-aware discriminators for realistic nodule synthesis conditioned on labels.

Findings

Synthetic nodules improve classification AUC by 2%

Framework generates diverse nodules conditioned on labels

Enhances dataset size and class balance for training

Abstract

Though large-scale datasets are essential for training deep learning systems, it is expensive to scale up the collection of medical imaging datasets. Synthesizing the objects of interests, such as lung nodules, in medical images based on the distribution of annotated datasets can be helpful for improving the supervised learning tasks, especially when the datasets are limited by size and class balance. In this paper, we propose the class-aware adversarial synthesis framework to synthesize lung nodules in CT images. The framework is built with a coarse-to-fine patch in-painter (generator) and two class-aware discriminators. By conditioning on the random latent variables and the target nodule labels, the trained networks are able to generate diverse nodules given the same context. By evaluating on the public LIDC-IDRI dataset, we demonstrate an example application of the proposed framework for improving the accuracy of the lung nodule malignancy estimation as a binary classification problem, which is important in the lung screening scenario. We show that combining the real image patches and the synthetic lung nodules in the training set can improve the mean AUC classification score across different network architectures by 2%.