Log In Sign Up

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

by   Youbao Tang, et al.

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 second GAN generates a higher resolution image with enhanced boundaries and high contrast. To make up for the absence of high quality CT images, we detail how to synthesize a large number of low- and high-quality natural images and use transfer learning with progressively larger amounts of CT images. We apply both the classic GrabCut method and the modern holistically nested network (HNN) to lesion segmentation, testing whether SGAN can yield improved lesion segmentation. Experimental results on the DeepLesion dataset demonstrate that the SGAN enhancements alone can push GrabCut performance over HNN trained on original images. We also demonstrate that HNN + SGAN performs best compared against four other enhancement methods, including when using only a single GAN.


page 2

page 6


Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images

Data augmentation can effectively resolve a scarcity of images when trai...

Accurate 2D soft segmentation of medical image via SoftGAN network

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

Generation of Artificial CT Images using Patch-based Conditional Generative Adversarial Networks

Deep learning has a great potential to alleviate diagnosis and prognosis...

Synthesis of Positron Emission Tomography (PET) Images via Multi-channel Generative Adversarial Networks (GANs)

Positron emission tomography (PET) image synthesis plays an important ro...

Contrast Phase Classification with a Generative Adversarial Network

Dynamic contrast enhanced computed tomography (CT) is an imaging techniq...

X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks

Computed tomography (CT) can provide a 3D view of the patient's internal...

Multi-organ Segmentation Network with Adversarial Performance Validator

CT organ segmentation on computed tomography (CT) images becomes a signi...