CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvement

@inproceedings{Tang2018CTIE,
  title={CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvement},
  author={Youbao Tang and Jinzheng Cai and Le Lu and Adam P. Harrison and Ke Yan and Jing Xiao and L. Yang and Ronald M. Summers},
  booktitle={MLMI@MICCAI},
  year={2018}
}
Automated lesion segmentation from computed tomography (CT) is an important and challenging task in medical image analysis. While many advancements have been made, there is room for continued improvements. One hurdle is that CT images can exhibit high noise and low contrast, particularly in lower dosages. To address this, we focus on a preprocessing method for CT images that uses stacked generative adversarial networks (SGAN) approach. The first GAN reduces the noise in the CT image and the… 
Accurate 2D soft segmentation of medical image via SoftGAN network
TLDR
A novel Cascaded Generative Adversarial Network (CasGAN) to cope with CT images super-resolution and segmentation tasks, in which the semantic soft segmentation form on precise lesion representation is introduced for the first time according to the knowledge.
CT-realistic data augmentation using generative adversarial network for robust lymph node segmentation
TLDR
Experimental results on NIH lymph node dataset demonstrate that the proposed data augmentation approach can produce realistic CT images and the lymph node segmentation performance is improved effectively using the additional augmented data, e.g. the Dice score increased about 2.2%.
Medical Image Generation using Generative Adversarial Networks
TLDR
This chapter provides state-of-the-art progress in GANs-based clinical application in medical image generation, and cross-modality synthesis, and future research directions in the area have been covered.
Deep Generative Adversarial Networks: Applications in Musculoskeletal Imaging.
TLDR
This review introduces the key architectures of GANs as well as their technical background and challenges, and an overview is provided of the key issues wherein clinical applicability is challenging to capture with conventional performance metrics and expert evaluation.
Weakly Supervised Lesion Co-Segmentation on Ct Scans
TLDR
A weakly-supervised co-segmentation model is proposed that first generates pseudo-masks from the RECIST slices and uses these as training labels for an attention-based convolutional neural network capable of segmenting common lesions from a pair of CT scans.
Weakly-supervised lesion segmentation on CT scans using co-segmentation
TLDR
A convolutional neural network (CNN) based weakly-supervised lesion segmentation method, which first generates the initial lesion masks from the RECIST measurements and then utilizes co-segmentation to leverage lesion similarities and refine the initial masks.
Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss
TLDR
This paper presents a novel weakly-supervised universal lesion segmentation method by building an attention enhanced model based on the High-Resolution Network (HRNet), named AHRNet, and proposes a regional level set (RLS) loss for optimizing lesion boundary delineation.
Combination of generative adversarial network and convolutional neural network for automatic subcentimeter pulmonary adenocarcinoma classification.
TLDR
An automatic classification system for subcentimeter pulmonary adenocarcinoma, combining a convolutional neural network (CNN) and a generative adversarial network (GAN) to optimize clinical decision-making and to provide small dataset algorithm design ideas is proposed.
...
...

References

SHOWING 1-10 OF 19 REFERENCES
CT-Realistic Lung Nodule Simulation from 3D Conditional Generative Adversarial Networks for Robust Lung Segmentation
TLDR
This work develops a 3D generative adversarial network (GAN) that effectively learns lung nodule property distributions in 3D space and proposes a novel multi-mask reconstruction loss to improve realism and blending with the background.
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
TLDR
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.
Accurate Weakly-Supervised Deep Lesion Segmentation using Large-Scale Clinical Annotations: Slice-Propagated 3D Mask Generation from 2D RECIST
TLDR
A convolutional neural network based weakly supervised slice-propagated segmentation (WSSS) method is introduced to generate the initial lesion segmentation on the axial RECIST-slice and extrapolate to segment the whole lesion slice by slice to finally obtain a volumetric segmentation.
Semi-Automatic RECIST Labeling on CT Scans with Cascaded Convolutional Neural Networks
TLDR
When judged against the inter-reader variability of two additional radiologist raters, the proposed cascaded convolutional neural network based method performs more stably and with less variability, suggesting that RECIST annotations can be reliably obtained with reduced labor and time.
Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
TLDR
The results show that CFCN-based semantic liver and lesion segmentation achieves Dice scores over \(94\,\%\) for liver with computation times below 100 s per volume.
Attention-Guided Curriculum Learning for Weakly Supervised Classification and Localization of Thoracic Diseases on Chest Radiographs
TLDR
A convolutional neural network (CNN) based attention-guided curriculum learning (AGCL) framework is presented, which leverages the severity-level attributes mined from radiology reports to improve the classification and localization performance of thoracic diseases from chest radiographs.
Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database
TLDR
A triplet network is utilized to learn lesion embeddings with a sequential sampling strategy to depict their hierarchical similarity structure and results show promising qualitative and quantitative results on lesion retrieval, clustering, and classification.
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
TLDR
This paper presents the first convolutional neural network capable of real-time SR of 1080p videos on a single K2 GPU and introduces an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output.
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
TLDR
This paper investigates the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image Denoising, and uses residual learning and batch normalization to speed up the training process as well as boost theDenoising performance.
Holistically-Nested Edge Detection
  • Saining Xie, Z. Tu
  • Computer Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
TLDR
HED performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets, and automatically learns rich hierarchical representations that are important in order to resolve the challenging ambiguity in edge and object boundary detection.
...
...