清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

Inter-crystal scattering recovery of light-sharing PET detectors using convolutional neural networks

探测器 卷积神经网络 光电探测器 Crystal(编程语言) 光子 光学 散射 康普顿散射 蒙特卡罗方法 溶血酶- 计算机科学 物理 人工智能 光电子学 材料科学 闪烁体 数学 统计 程序设计语言
作者
Seung‐Eun Lee,Jae Sung Lee
出处
期刊:Physics in Medicine and Biology [IOP Publishing]
卷期号:66 (18): 185004-185004 被引量:17
标识
DOI:10.1088/1361-6560/ac215d
摘要

Inter-crystal scattering (ICS) is a type of Compton scattering of photons from one crystal to adjacent crystals and causes inaccurate assignment of the annihilation photon interaction position in positron emission tomography (PET). Because ICS frequently occurs in highly light-shared PET detectors, its recovery is crucial for the spatial resolution improvement. In this study, we propose two different convolutional neural networks (CNNs) for ICS recovery, exploiting the good pattern recognition ability of CNN techniques. Using the signal distribution of a photosensor array as input, one network estimates the energy deposition in each crystal (ICS-eNet) and another network chooses the first-interacted crystal (ICS-cNet). We performed GATE Monte Carlo simulations with optical photon tracking to test PET detectors comprising different crystal arrays (8 × 8 to 21 × 21) with lengths of 20 mm and the same photosensor array (3 mm 8 × 8 array) covering an area of 25.8 × 25.8 mm2. For each detector design, we trained ICS-eNet and ICS-cNet and evaluated their respective performance. ICS-eNet accurately identified whether the events were ICS (accuracy > 90%) and selected interacted crystals (accuracy > 60%) with appropriate energy estimation performance (R2 > 0.7) in the 8 × 8, 12 × 12, and 16 × 16 arrays. ICS-cNet also exhibited satisfactory performance, which was less dependent on the crystal-to-sensor ratio, with an accuracy enhancement that exceeds 10% in selecting the first-interacted crystal and a reduction in error distances compared when no recovery was applied. Both ICS-eNet and ICS-cNet exhibited consistent performances under various optical property settings of the crystals. For spatial resolution measurements in PET rings, both networks achieved significant enhancements particularly for highly pixelated arrays. We also discuss approaches for training the networks in an actual experimental setup. This proof-of-concept study demonstrated the feasibility of CNNs for ICS recovery in various light-sharing designs to efficiently improve the spatial resolution of PET in various applications.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
cadcae完成签到,获得积分10
27秒前
GYQ完成签到,获得积分20
27秒前
光合作用完成签到,获得积分10
30秒前
yueyueyahoo完成签到,获得积分10
40秒前
46秒前
呆呆的猕猴桃完成签到 ,获得积分10
1分钟前
1111完成签到 ,获得积分10
1分钟前
今后应助傲娇的夜山采纳,获得10
1分钟前
cgs完成签到 ,获得积分10
1分钟前
zpc猪猪完成签到,获得积分10
1分钟前
科研通AI2S应助科研通管家采纳,获得10
1分钟前
Akim应助科研通管家采纳,获得10
1分钟前
柯伊达完成签到 ,获得积分10
2分钟前
elisa828完成签到,获得积分10
2分钟前
2分钟前
2分钟前
喵叽发布了新的文献求助10
2分钟前
桐桐应助喵叽采纳,获得10
3分钟前
平平平平完成签到 ,获得积分10
3分钟前
rockyshi完成签到 ,获得积分10
3分钟前
3分钟前
新新新新新发顶刊完成签到 ,获得积分10
3分钟前
科目三应助科研通管家采纳,获得10
3分钟前
柚子完成签到 ,获得积分20
4分钟前
柚子关注了科研通微信公众号
4分钟前
猪嗝铁铁完成签到,获得积分10
4分钟前
文静如南完成签到 ,获得积分10
4分钟前
003完成签到,获得积分10
4分钟前
5分钟前
5分钟前
无悔完成签到 ,获得积分10
5分钟前
001完成签到,获得积分10
5分钟前
5分钟前
5分钟前
喵叽发布了新的文献求助10
5分钟前
锅包肉完成签到 ,获得积分10
5分钟前
002完成签到,获得积分10
5分钟前
5分钟前
科研通AI2S应助科研通管家采纳,获得10
5分钟前
CodeCraft应助科研通管家采纳,获得10
5分钟前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968520
求助须知:如何正确求助?哪些是违规求助? 3513331
关于积分的说明 11167298
捐赠科研通 3248700
什么是DOI,文献DOI怎么找? 1794417
邀请新用户注册赠送积分活动 875030
科研通“疑难数据库(出版商)”最低求助积分说明 804664