Saved in:
Bibliographic Details
Main Authors: Kim, Kyungsu, Oh, Seong Je, Lim, Chae Yeon, Lee, Ju Hwan, Kim, Tae Uk, Chung, Myung Jin
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2207.10324
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911918692761600
author Kim, Kyungsu
Oh, Seong Je
Lim, Chae Yeon
Lee, Ju Hwan
Kim, Tae Uk
Chung, Myung Jin
author_facet Kim, Kyungsu
Oh, Seong Je
Lim, Chae Yeon
Lee, Ju Hwan
Kim, Tae Uk
Chung, Myung Jin
contents Image translation based on a generative adversarial network (GAN-IT) is a promising method for the precise localization of abnormal regions in chest X-ray images (AL-CXR) even without the pixel-level annotation. However, heterogeneous unpaired datasets undermine existing methods to extract key features and distinguish normal from abnormal cases, resulting in inaccurate and unstable AL-CXR. To address this problem, we propose an improved two-stage GAN-IT involving registration and data augmentation. For the first stage, we introduce an advanced deep-learning-based registration technique that virtually and reasonably converts unpaired data into paired data for learning registration maps, by sequentially utilizing linear-based global and uniform coordinate transformation and AI-based non-linear coordinate fine-tuning. This approach enables independent and complex coordinate transformation of each detailed location of the lung while recognizing the entire lung structure, thereby achieving higher registration performance with resolving inherent artifacts caused by unpaired conditions. For the second stage, we apply data augmentation to diversify anomaly locations by swapping the left and right lung regions on the uniform registered frames, further improving the performance by alleviating imbalance in data distribution showing left and right lung lesions. The proposed method is model agnostic and shows consistent AL-CXR performance improvement in representative AI models. Therefore, we believe GAN-IT for AL-CXR can be clinically implemented by using our basis framework, even if learning data are scarce or difficult for the pixel-level disease annotation.
format Preprint
id arxiv_https___arxiv_org_abs_2207_10324
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Enhancing Generative Networks for Chest Anomaly Localization through Automatic Registration-Based Unpaired-to-Pseudo-Paired Training Data Translation
Kim, Kyungsu
Oh, Seong Je
Lim, Chae Yeon
Lee, Ju Hwan
Kim, Tae Uk
Chung, Myung Jin
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Image translation based on a generative adversarial network (GAN-IT) is a promising method for the precise localization of abnormal regions in chest X-ray images (AL-CXR) even without the pixel-level annotation. However, heterogeneous unpaired datasets undermine existing methods to extract key features and distinguish normal from abnormal cases, resulting in inaccurate and unstable AL-CXR. To address this problem, we propose an improved two-stage GAN-IT involving registration and data augmentation. For the first stage, we introduce an advanced deep-learning-based registration technique that virtually and reasonably converts unpaired data into paired data for learning registration maps, by sequentially utilizing linear-based global and uniform coordinate transformation and AI-based non-linear coordinate fine-tuning. This approach enables independent and complex coordinate transformation of each detailed location of the lung while recognizing the entire lung structure, thereby achieving higher registration performance with resolving inherent artifacts caused by unpaired conditions. For the second stage, we apply data augmentation to diversify anomaly locations by swapping the left and right lung regions on the uniform registered frames, further improving the performance by alleviating imbalance in data distribution showing left and right lung lesions. The proposed method is model agnostic and shows consistent AL-CXR performance improvement in representative AI models. Therefore, we believe GAN-IT for AL-CXR can be clinically implemented by using our basis framework, even if learning data are scarce or difficult for the pixel-level disease annotation.
title Enhancing Generative Networks for Chest Anomaly Localization through Automatic Registration-Based Unpaired-to-Pseudo-Paired Training Data Translation
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2207.10324