CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentation

TL;DR

This paper introduces a 3D conditional GAN to generate realistic lung nodules for augmenting training data, significantly improving the robustness of lung segmentation models in challenging CT scan scenarios.

Contribution

The work presents a novel 3D GAN with a multi-mask reconstruction loss for realistic nodule synthesis, enhancing lung segmentation under data scarcity and challenging conditions.

Findings

Generated nodules improve segmentation accuracy on border cases

Qualitative results show high realism of synthetic nodules

Quantitative metrics indicate better model robustness

Abstract

Data availability plays a critical role for the performance of deep learning systems. This challenge is especially acute within the medical image domain, particularly when pathologies are involved, due to two factors: 1) limited number of cases, and 2) large variations in location, scale, and appearance. In this work, we investigate whether augmenting a dataset with artificially generated lung nodules can improve the robustness of the progressive holistically nested network (P-HNN) model for pathological lung segmentation of CT scans. To achieve this goal, we develop a 3D generative adversarial network (GAN) that effectively learns lung nodule property distributions in 3D space. In order to embed the nodules within their background context, we condition the GAN based on a volume of interest whose central part containing the nodule has been erased. To further improve realism and blending with the background, we propose a novel multi-mask reconstruction loss. We train our method on over 1000 nodules from the LIDC dataset. Qualitative results demonstrate the effectiveness of our method compared to the state-of-art. We then use our GAN to generate simulated training images where nodules lie on the lung border, which are cases where the published P-HNN model struggles. Qualitative and quantitative results demonstrate that armed with these simulated images, the P-HNN model learns to better segment lung regions under these challenging situations. As a result, our system provides a promising means to help overcome the data paucity that commonly afflicts medical imaging.