Free-form tumor synthesis in computed tomography images via richer generative adversarial network

Abstract

The insufficiency of annotated medical imaging scans for cancer makes it challenging to train and validate data-hungry deep learning models in precision oncology. We propose a new richer generative adversarial network for free-form 3D tumor/lesion synthesis in computed tomography (CT) images. The network is composed of a new richer convolutional feature enhanced dilated-gated generator (RicherDG) and a hybrid loss function. The RicherDG has dilated-gated convolution layers to enable tumor-painting and to enlarge perceptive fields; and it has a novel richer convolutional feature association branch to recover multi-scale convolutional features especially from uncertain boundaries between tumor and surrounding healthy tissues. The hybrid loss function, which consists of a diverse range of losses, is designed to aggregate complementary information to improve optimization. We perform a comprehensive evaluation of the synthesis results on a wide range of public CT image datasets covering the liver, kidney tumors, and lung nodules. The qualitative and quantitative evaluations and ablation study demonstrated improved synthesizing results over advanced tumor synthesis methods.

References in corpus (20)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Attention U-Net: Learning Where to Look for the Pancreas
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• U${}^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
• Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge
• The Liver Tumor Segmentation Benchmark (LiTS)
• Domain-adversarial neural networks to address the appearance variability of histopathology images
• Data Augmentation Generative Adversarial Networks
• Richer Convolutional Features for Edge Detection
• EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
• Med3D: Transfer Learning for 3D Medical Image Analysis
• The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes
• BAGAN: Data Augmentation with Balancing GAN
• Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images
• Synthetic Medical Images from Dual Generative Adversarial Networks
• Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation
• Learnable Gated Temporal Shift Module for Deep Video Inpainting
• Blood Vessel Geometry Synthesis using Generative Adversarial Networks
• Class-Aware Adversarial Lung Nodule Synthesis in CT Images

Cited by in corpus (1)

• Deep learning-based conditional inpainting for restoration of artifact-affected 4D CT images