CBCT-Based Synthetic CT Image Generation Using Conditional Denoising Diffusion Probabilistic Model

图像去噪 降噪 概率逻辑 计算机科学 人工智能 计算机视觉 模式识别(心理学)
作者
Junbo Peng,Richard L. J. Qiu,Jacob Wynne,Chih‐Wei Chang,Shaoyan Pan,Tonghe Wang,Justin Roper,Tian Liu,Pretesh Patel,David S. Yu,Xiaofeng Yang
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2303.02649
摘要

Background: Daily or weekly cone-beam computed tomography (CBCT) scans are commonly used for accurate patient positioning during the image-guided radiotherapy (IGRT) process, making it an ideal option for adaptive radiotherapy (ART) replanning. However, the presence of severe artifacts and inaccurate Hounsfield unit (HU) values prevent its use for quantitative applications such as organ segmentation and dose calculation. To enable the clinical practice of online ART, it is crucial to obtain CBCT scans with a quality comparable to that of a CT scan. Purpose: This work aims to develop a conditional diffusion model to perform image translation from the CBCT to the CT domain for the image quality improvement of CBCT. Methods: The proposed method is a conditional denoising diffusion probabilistic model (DDPM) that utilizes a time-embedded U-net architecture with residual and attention blocks to gradually transform standard Gaussian noise to the target CT distribution conditioned on the CBCT. The model was trained on deformed planning CT (dpCT) and CBCT image pairs, and its feasibility was verified in brain patient study and head-and-neck (H&N) patient study. The performance of the proposed algorithm was evaluated using mean absolute error (MAE), peak signal-to-noise ratio (PSNR) and normalized cross-correlation (NCC) metrics on generated synthetic CT (sCT) samples. The proposed method was also compared to four other diffusion model-based sCT generation methods. Conclusions: The proposed conditional DDPM method can generate sCT from CBCT with accurate HU numbers and reduced artifacts, enabling accurate CBCT-based organ segmentation and dose calculation for online ART.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
frank发布了新的文献求助10
1秒前
1秒前
1秒前
1秒前
感谢超帅冬易转发科研通微信,获得积分50
2秒前
2秒前
3秒前
3秒前
lixia完成签到 ,获得积分10
3秒前
3秒前
4秒前
在水一方应助jy采纳,获得10
5秒前
5秒前
Lucas完成签到,获得积分10
6秒前
6秒前
NorthWang发布了新的文献求助10
6秒前
薄哼哼完成签到,获得积分10
6秒前
troubadourelf完成签到,获得积分10
6秒前
科研小白菜完成签到,获得积分20
7秒前
淡定的思松应助12采纳,获得10
7秒前
lan发布了新的文献求助10
7秒前
韩金龙发布了新的文献求助10
8秒前
8秒前
小飞七应助红毛兔采纳,获得10
8秒前
小仙虎殿下完成签到 ,获得积分10
8秒前
Ethan完成签到,获得积分10
9秒前
9秒前
10秒前
感谢抹茶芋泥小圆子转发科研通微信,获得积分50
10秒前
子春完成签到 ,获得积分10
10秒前
平常的纸飞机完成签到,获得积分10
10秒前
soso完成签到 ,获得积分10
12秒前
12秒前
狗狗应助跳跃乘风采纳,获得20
13秒前
小油条应助Amai采纳,获得20
13秒前
科研通AI5应助clear采纳,获得10
13秒前
韩金龙完成签到,获得积分10
14秒前
科研通AI2S应助LiShin采纳,获得10
14秒前
希望天下0贩的0应助尘雾采纳,获得10
16秒前
16秒前
高分求助中
Continuum Thermodynamics and Material Modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Social media impact on athlete mental health: #RealityCheck 1020
Ensartinib (Ensacove) for Non-Small Cell Lung Cancer 1000
Unseen Mendieta: The Unpublished Works of Ana Mendieta 1000
Bacterial collagenases and their clinical applications 800
El viaje de una vida: Memorias de María Lecea 800
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3527884
求助须知:如何正确求助?哪些是违规求助? 3108006
关于积分的说明 9287444
捐赠科研通 2805757
什么是DOI,文献DOI怎么找? 1540033
邀请新用户注册赠送积分活动 716904
科研通“疑难数据库(出版商)”最低求助积分说明 709794