Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule Augmentation and Detection

TL;DR

This paper introduces a novel GAN-based framework for synthesizing realistic lung nodules in chest X-ray images with controllable attributes, significantly improving data augmentation and nodule detection accuracy.

Contribution

It proposes a disentangled attribute-based nodule synthesis method with shape, size, and texture control, enhancing realism and diversity for better data augmentation.

Findings

Improved image quality and diversity of synthesized nodules.

Enhanced nodule detection performance with augmented data.

Effective control over nodule attributes in generated images.

Abstract

Lung nodule detection in chest X-ray (CXR) images is common to early screening of lung cancers. Deep-learning-based Computer-Assisted Diagnosis (CAD) systems can support radiologists for nodule screening in CXR. However, it requires large-scale and diverse medical data with high-quality annotations to train such robust and accurate CADs. To alleviate the limited availability of such datasets, lung nodule synthesis methods are proposed for the sake of data augmentation. Nevertheless, previous methods lack the ability to generate nodules that are realistic with the size attribute desired by the detector. To address this issue, we introduce a novel lung nodule synthesis framework in this paper, which decomposes nodule attributes into three main aspects including shape, size, and texture, respectively. A GAN-based Shape Generator firstly models nodule shapes by generating diverse shape masks. The following Size Modulation then enables quantitative control on the diameters of the generated nodule shapes in pixel-level granularity. A coarse-to-fine gated convolutional Texture Generator finally synthesizes visually plausible nodule textures conditioned on the modulated shape masks. Moreover, we propose to synthesize nodule CXR images by controlling the disentangled nodule attributes for data augmentation, in order to better compensate for the nodules that are easily missed in the detection task. Our experiments demonstrate the enhanced image quality, diversity, and controllability of the proposed lung nodule synthesis framework. We also validate the effectiveness of our data augmentation on greatly improving nodule detection performance.