Journal
MEDICAL IMAGE ANALYSIS
Volume 69, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.media.2021.101976
Keywords
Gadolinium-enhanced liver tumor imaging; Deep reinforcement learning; Graph convolution; Pixel-level agents; Complementary reward
Ask authors/readers for more resources
By utilizing a novel pixel-level graph reinforcement learning method (Pix-GRL), traditional nonenhanced liver images can be synthesized into AI-enhanced liver tumor images without the need for contrast agents. This method offers a safe, efficient, and cost-effective clinical alternative for liver tumor diagnosis and treatment, with the potential to significantly benefit global healthcare systems.
If successful, synthesis of gadolinium (Gd)-enhanced liver tumors on nonenhanced liver MR images will be critical for liver tumor diagnosis and treatment. This synthesis will offer a safe, efficient, and lowcost clinical alternative to eliminate the use of contrast agents in the current clinical workflow and significantly benefit global healthcare systems. In this study, we propose a novel pixel-level graph reinforcement learning method (Pix-GRL). This method directly takes regular nonenhanced liver images as input and outputs AI-enhanced liver tumor images, thereby making them comparable to traditional Gdenhanced liver tumor images. In Pix-GRL, each pixel has a pixel-level agent, and the agent explores the pixels features and outputs a pixel-level action to iteratively change the pixel value, ultimately generating AI-enhanced liver tumor images. Most importantly, Pix-GRL creatively embeds a graph convolution to represent all the pixel-level agents. A graph convolution is deployed to the agent for feature exploration to improve the effectiveness through the aggregation of long-range contextual features, as well as outputting the action to enhance the efficiency through shared parameter training between agents. Moreover, in our Pix-GRL method, a novel reward is used to measure pixel-level action to significantly improve the performance by considering the improvement in each action in each pixel with its own future state, as well as those of neighboring pixels. Pix-GRL significantly upgrades the existing medical DRL methods from a single agent to multiple pixel-level agents, becoming the first DRL method for medical image synthesis. Comprehensive experiments on three types of liver tumor datasets (benign, cancerous, and healthy controls) with 325 patients (24,375 images) show that our novel Pix-GRL method outperforms existing medical image synthesis learning methods. It achieved an SSIM of 0.85 +/- 0.06 and a Pearson correlation coefficient of 0.92 in terms of the tumor size. These results prove that the potential exists to develop a successful clinical alternative to Gd-enhanced liver MR imaging. (c) 2021 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available