Deep learning architecture for scatter estimation in cone-beam computed tomography head imaging with varying field-of-measurement settings

医学 锥束ct 主管(地质) 计算机断层摄影术 断层摄影术 Cone(正式语言) 人工智能 医学物理学 放射科 算法 地貌学 计算机科学 地质学
作者
Harshit Agrawal,Ari Hietanen,Simo Särkkä
出处
期刊:Journal of medical imaging [SPIE - International Society for Optical Engineering]
卷期号:11 (05)
标识
DOI:10.1117/1.jmi.11.5.053501
摘要

PurposeX-ray scatter causes considerable degradation in the cone-beam computed tomography (CBCT) image quality. To estimate the scatter, deep learning–based methods have been demonstrated to be effective. Modern CBCT systems can scan a wide range of field-of-measurement (FOM) sizes. Variations in the size of FOM can cause a major shift in the scatter-to-primary ratio in CBCT. However, the scatter estimation performance of deep learning networks has not been extensively evaluated under varying FOMs. Therefore, we train the state-of-the-art scatter estimation neural networks for varying FOMs and develop a method to utilize FOM size information to improve performance.ApproachWe used FOM size information as additional features by converting it into two channels and then concatenating it to the encoder of the networks. We compared our approach for a U-Net, Spline-Net, and DSE-Net, by training them with and without the FOM information. We utilized a Monte Carlo–simulated dataset to train the networks on 18 FOM sizes and test on 30 unseen FOM sizes. In addition, we evaluated the models on the water phantoms and real clinical CBCT scans.ResultsThe simulation study demonstrates that our method reduced average mean-absolute-percentage-error for U-Net by 38%, Spline-Net by 40%, and DSE-net by 33% for the scatter estimation in the 2D projection domain. Furthermore, the root-mean-square error on the 3D reconstructed volumes was improved for U-Net by 43%, Spline-Net by 30%, and DSE-Net by 23%. Furthermore, our method improved contrast and image quality on real datasets such as water phantom and clinical data.ConclusionProviding additional information about FOM size improves the robustness of the neural networks for scatter estimation. Our approach is not limited to utilizing only FOM size information; more variables such as tube voltage, scanning geometry, and patient size can be added to improve the robustness of a single network.
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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
美好芷波发布了新的文献求助10
1秒前
SciGPT应助科研通管家采纳,获得10
1秒前
风归云隐应助科研通管家采纳,获得20
1秒前
丘比特应助科研通管家采纳,获得10
2秒前
华仔应助科研通管家采纳,获得30
2秒前
Orange应助科研通管家采纳,获得10
2秒前
Akim应助科研通管家采纳,获得30
2秒前
平常的凡白完成签到 ,获得积分10
3秒前
善学以致用应助QYQ7采纳,获得10
3秒前
nicol.z完成签到 ,获得积分10
3秒前
5秒前
bemyself完成签到,获得积分10
6秒前
7秒前
8秒前
学习吧完成签到 ,获得积分10
8秒前
材化小将军完成签到,获得积分10
9秒前
10秒前
10秒前
一朵棉花糖完成签到,获得积分10
11秒前
QYQ7完成签到,获得积分20
11秒前
喜悦的半青完成签到,获得积分10
11秒前
hcd12138完成签到,获得积分10
12秒前
浣熊小呆发布了新的文献求助20
12秒前
万能图书馆应助端庄煎饼采纳,获得10
12秒前
12秒前
13秒前
NexusExplorer应助起帆采纳,获得10
13秒前
1404154936发布了新的文献求助10
14秒前
小郭完成签到,获得积分10
15秒前
16秒前
鲤鱼凝云发布了新的文献求助10
16秒前
ding应助jialin采纳,获得10
17秒前
111应助GeoY采纳,获得10
18秒前
搜集达人应助泥头车司机采纳,获得10
19秒前
向晚关注了科研通微信公众号
19秒前
19秒前
领导范儿应助郦涔采纳,获得10
20秒前
21秒前
一桶雪碧完成签到,获得积分10
21秒前
D-raise完成签到,获得积分10
21秒前
高分求助中
【此为提示信息,请勿应助】请按要求发布求助,避免被关 20000
【本贴是提醒信息,请勿应助】请在求助之前详细阅读求助说明!!!! 20000
Evolution 5000
좌파는 어떻게 좌파가 됐나:한국 급진노동운동의 형성과 궤적 2500
Sustainability in Tides Chemistry 1500
La Chine révolutionnaire d'aujourd'hui / Van Min, Kang Hsin 1000
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3044554
求助须知:如何正确求助?哪些是违规求助? 2701739
关于积分的说明 7384800
捐赠科研通 2345718
什么是DOI,文献DOI怎么找? 1241583
科研通“疑难数据库(出版商)”最低求助积分说明 603979
版权声明 595503