# Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection

## TL;DR

This paper introduces a 3D multi-conditional GAN to generate realistic lung nodules in CT images, significantly improving 3D object detection sensitivity and addressing data scarcity in medical imaging.

## Contribution

It presents the first 3D multi-conditional GAN for lung nodule augmentation, enhancing detection performance across various nodule sizes and attenuations.

## Key findings

- Improved detection sensitivity across nodule sizes and attenuations.
- Generated nodules are indistinguishable from real ones in Visual Turing Tests.
- Addresses data scarcity in medical imaging with realistic synthetic nodules.

## Abstract

Accurate Computer-Assisted Diagnosis, relying on large-scale annotated pathological images, can alleviate the risk of overlooking the diagnosis. Unfortunately, in medical imaging, most available datasets are small/fragmented. To tackle this, as a Data Augmentation (DA) method, 3D conditional Generative Adversarial Networks (GANs) can synthesize desired realistic/diverse 3D images as additional training data. However, no 3D conditional GAN-based DA approach exists for general bounding box-based 3D object detection, while it can locate disease areas with physicians' minimum annotation cost, unlike rigorous 3D segmentation. Moreover, since lesions vary in position/size/attenuation, further GAN-based DA performance requires multiple conditions. Therefore, we propose 3D Multi-Conditional GAN (MCGAN) to generate realistic/diverse 32 X 32 X 32 nodules placed naturally on lung Computed Tomography images to boost sensitivity in 3D object detection. Our MCGAN adopts two discriminators for conditioning: the context discriminator learns to classify real vs synthetic nodule/surrounding pairs with noise box-centered surroundings; the nodule discriminator attempts to classify real vs synthetic nodules with size/attenuation conditions. The results show that 3D Convolutional Neural Network-based detection can achieve higher sensitivity under any nodule size/attenuation at fixed False Positive rates and overcome the medical data paucity with the MCGAN-generated realistic nodules---even expert physicians fail to distinguish them from the real ones in Visual Turing Test.