Feedback Assisted Adversarial Learning to Improve the Quality of Cone-beam CT Images Takumi Hase1 Megumi Nakao1 Mitsuhiro Nakamura2 and Tetsuya Matsuda1

2025-05-06 0 0 2.85MB 9 页 10玖币

侵权投诉

Feedback Assisted Adversarial Learning to

Improve the Quality of Cone-beam CT Images

Takumi Hase1, Megumi Nakao1, Mitsuhiro Nakamura2, and Tetsuya Matsuda1

1Graduate School of Informatics, Kyoto University, Kyoto, Japan.

megumi@i.kyoto-u.ac.jp

2Graduate School of Medicine, Human Health Sciences, Kyoto University, Kyoto,

Japan.

Abstract. Unsupervised image translation using adversarial learning

has been attracting attention to improve the image quality of medical

images. However, adversarial training based on the global evaluation val-

ues of discriminators does not provide suﬃcient translation performance

for locally diﬀerent image features. We propose adversarial learning with

a feedback mechanism from a discriminator to improve the quality of

CBCT images. This framework employs U-net as the discriminator and

outputs a probability map representing the local discrimination results.

The probability map is fed back to the generator and used for training to

improve the image translation. Our experiments using 76 corresponding

CT-CBCT images conﬁrmed that the proposed framework could cap-

ture more diverse image features than conventional adversarial learning

frameworks and produced synthetic images with pixel values close to the

reference image and a correlation coeﬃcient of 0.93.

Keywords: Adversarial learning, image synthesis, CBCT images

1 Introduction

Cone-beam computed tomography (CBCT) has been increasingly used for 3D

imaging in clinical medicine. Because the device is compact and movable, 3D

images can be acquired from the patient during surgery or radiotherapy. Con-

versely, CBCT, in which X-rays are irradiated in a conical shape and signals are

obtained by a two-dimensional detector, is more susceptible to scattering than

CT. Signals cannot be obtained from a certain range of directions because of

the physical constraints of the rotation angle. These diﬀerences in signal char-

acteristics result in a wide range and variety of artifacts in the reconstructed

image [1]. Due to the eﬀect of these artifacts, the CBCT images’ pixel values

are inaccurate compared to CT images, which is a factor that reduces the image

quality and accuracy of medical image analysis.

There are many examples of research into using deep learning to improve the

quality of medical images [2]. Attempts have been made to improve the quality

of CBCT images by scattering correction [3]. Several methods are based on

supervised learning and require CT images that perfectly match the anatomical

arXiv:2210.12578v1 [eess.IV] 23 Oct 2022

2 Takumi Hase, Megumi Nakao, Mitsuhiro Nakamura, and Tetsuya Matsuda

structures in the CBCT images. However, it is diﬃcult to obtain a set of images

with perfectly matched structures for the same patient, and the opportunities for

using this technique are limited. To address this issue, unsupervised learning that

does not assume a one-to-one correspondence between target images has been

widely studied, especially by applying Generative Adversarial Networks (GANs)

[4]. The CycleGAN is reportedly eﬀective in reducing dental metal artifacts in

CT images [5][6], and artifacts in craniocervical CBCT images [7].

Artifacts in CBCT images exhibit various image features and are present over

a wide area of the image. Therefore, cases occur in which existing adversarial

training and regularization of the loss function [8][9] inadequately improve image

quality. A reason for this limitation on image translation performance is that

the discriminator in conventional GANs evaluates whether or not an image is

a target image based on a global evaluation value alone. Reportedly, a global

evaluation does not provide suﬃcient translation performance for image features

with diﬀerent local characteristics [10]. To obtain adversarial learning and image

translation that generates a variety of images while capturing locally diﬀerent

image features remains a challenge.

In this study, we propose adversarial learning with a feedback mechanism

from the discriminator as a new unsupervised learning framework to improve

the quality of CBCT images. With conventional GANs, adversarial learning is

performed based on the global discrimination results output by the discrimina-

tor, but with the proposed method, the discriminator is extended to output a

probability map. A probability map is an image in which the probability that the

input image belongs to the target image sets is calculated on a pixel basis. This

map aims to obtain a local evaluation of the diﬀerences in image features found

between the synthetic image and the target image. In addition, the proposed

adversarial learning framework introduces a feedback mechanism that inputs

the probability map output by the discriminator to the generator. By providing

the generator with information about attention and image features, we aim to

improve the image-translation performance by inducing the generator to acquire

the ability to generate more diverse image features.

In our experiments, adversarial learning was conducted using planning CT

images for 76 patients who underwent radiotherapy for prostate cancer and

CBCT images taken on the day of radiotherapy. We investigated the image

translation performance by comparing the proposed framework with the two

existing methods. The contributions of this study are as follows.

–A new adversarial learning scheme with a feedback mechanism

–Analysis of the impact of a probability map generated from the discriminator

–Application of the methods to improve the quality of CBCT images

2 Methods

2.1 Adversarial Learning with a Feedback Mechanism

In a conventional GAN, the global discrimination result of the discriminator is

calculated as a scalar between 0 and 1 for the synthetic image and is used only for

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

10 玖币 0人已下载

立即下载

摘要：

FeedbackAssistedAdversarialLearningtoImprovetheQualityofCone-beamCTImagesTakumiHase1,MegumiNakao1,MitsuhiroNakamura2,andTetsuyaMatsuda11GraduateSchoolofInformatics,KyotoUniversity,Kyoto,Japan.megumi@i.kyoto-u.ac.jp2GraduateSchoolofMedicine,HumanHealthSciences,KyotoUniversity,Kyoto,Japan.Abstract.Uns...

展开>> 收起<<

Feedback Assisted Adversarial Learning to Improve the Quality of Cone-beam CT Images Takumi Hase1 Megumi Nakao1 Mitsuhiro Nakamura2 and Tetsuya Matsuda1.pdf

共9页,预览2页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

Feedback Assisted Adversarial Learning to Improve the Quality of Cone-beam CT Images Takumi Hase1 Megumi Nakao1 Mitsuhiro Nakamura2 and Tetsuya Matsuda1

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: