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

by   Dakai Jin, et al.

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.


page 2

page 6

page 7


LGAN: Lung Segmentation in CT Scans Using Generative Adversarial Network

Lung segmentation in computerized tomography (CT) images is an important...

Progressive and Multi-Path Holistically Nested Neural Networks for Pathological Lung Segmentation from CT Images

Pathological lung segmentation (PLS) is an important, yet challenging, m...

Accurate 2D soft segmentation of medical image via SoftGAN network

Accurate 2D lung nodules segmentation from medical Computed Tomography (...

Class-Aware Adversarial Lung Nodule Synthesis in CT Images

Though large-scale datasets are essential for training deep learning sys...

CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning

In 2018, clinics and hospitals were hit with numerous attacks leading to...

How to Fool Radiologists with Generative Adversarial Networks? A Visual Turing Test for Lung Cancer Diagnosis

Discriminating lung nodules as malignant or benign is still an underlyin...

Lung CT Imaging Sign Classification through Deep Learning on Small Data

The annotated medical images are usually expensive to be collected. This...

Please sign up or login with your details

Forgot password? Click here to reset