Adversarial Policy Gradient for Deep Learning Image Augmentation

09/09/2019
by   Kaiyang Cheng, et al.
0

The use of semantic segmentation for masking and cropping input images has proven to be a significant aid in medical imaging classification tasks by decreasing the noise and variance of the training dataset. However, implementing this approach with classical methods is challenging: the cost of obtaining a dense segmentation is high, and the precise input area that is most crucial to the classification task is difficult to determine a-priori. We propose a novel joint-training deep reinforcement learning framework for image augmentation. A segmentation network, weakly supervised with policy gradient optimization, acts as an agent, and outputs masks as actions given samples as states, with the goal of maximizing reward signals from the classification network. In this way, the segmentation network learns to mask unimportant imaging features. Our method, Adversarial Policy Gradient Augmentation (APGA), shows promising results on Stanford's MURA dataset and on a hip fracture classification task with an increase in global accuracy of up to 7.33 improved performance over baseline methods in 9/10 tasks evaluated. We discuss the broad applicability of our joint training strategy to a variety of medical imaging tasks.

READ FULL TEXT
research
02/20/2019

Adversarial Augmentation for Enhancing Classification of Mammography Images

Supervised deep learning relies on the assumption that enough training d...
research
06/02/2022

Suggestive Annotation of Brain MR Images with Gradient-guided Sampling

Machine learning has been widely adopted for medical image analysis in r...
research
09/28/2022

Data Augmentation using Feature Generation for Volumetric Medical Images

Medical image classification is one of the most critical problems in the...
research
12/05/2019

Blind Inpainting of Large-scale Masks of Thin Structures with Adversarial and Reinforcement Learning

Several imaging applications (vessels, retina, plant roots, road network...
research
10/02/2020

Tubular Shape Aware Data Generation for Semantic Segmentation in Medical Imaging

Chest X-ray is one of the most widespread examinations of the human body...
research
11/15/2018

Orthogonal Policy Gradient and Autonomous Driving Application

One less addressed issue of deep reinforcement learning is the lack of g...
research
05/28/2021

About Explicit Variance Minimization: Training Neural Networks for Medical Imaging With Limited Data Annotations

Self-supervised learning methods for computer vision have demonstrated t...

Please sign up or login with your details

Forgot password? Click here to reset