[1]陈宇亭,周飞宇,张富利,等.兆伏级CT图像引导自适应放疗中生成合成CT研究[J].中国医学物理学杂志,2024,41(7):813-820.[doi:DOI:10.3969/j.issn.1005-202X.2024.07.005]
　CHEN Yuting,ZHOU Feiyu,et al.Generating synthetic CT in megavoltage CT image-guided adaptive radiotherapy[J].Chinese Journal of Medical Physics,2024,41(7):813-820.[doi:DOI:10.3969/j.issn.1005-202X.2024.07.005]
点击复制

兆伏级CT图像引导自适应放疗中生成合成CT研究()
分享到：

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
41卷
期数:
2024年第7期
页码:
813-820
栏目:
医学放射物理
出版日期:
2024-07-25

文章信息/Info

Title:
Generating synthetic CT in megavoltage CT image-guided adaptive radiotherapy
文章编号:
1005-202X（2024）07-0813-08
作者:
陈宇亭1; 2; 周飞宇1; 2; 张富利2; 蒋华勇2; 陈点点2; 高彦祥2; 郁艳军2; 乐小云1; 路娜2
1.北京航空航天大学物理学院， 北京 100191； 2.解放军总医院肿瘤学部第七医学中心放疗科， 北京 100700
Author(s):
CHEN Yuting1;  2;  ZHOU Feiyu1;  2;  ZHANG Fuli2;  JIANG Huayong2;  CHEN Diandian2;  GAO Yanxiang2;  YU Yanjun2;  LE Xiaoyun1;  LU Na2
1. School of Physics, Beihang University, Beijing 100191, China 2. Department of Radiotherapy, the 7th Medical Center, Department of Oncology, Chinese PLA General Hospital, Beijing 100700, China
关键词:
循环生成对抗网络; MVCT; 合成CT; 图像引导放疗; 图像质量
Keywords:
Keywords: cyclic generative adversarial network megavoltage computed tomography synthetic computed tomography image-guided radiotherapy image quality
分类号:
R737.33
DOI:
DOI:10.3969/j.issn.1005-202X.2024.07.005
文献标志码:
A
摘要:
目的：开发一种基于深度学习神经网络的方法将宫颈癌MVCT图像转换为具有高信噪比和高对比度的伪kVCT图像，从而提供宫颈癌自适应放疗需要的患者三维解剖图像和定位信息，引导加速器实现精确放疗。方法：收集54例宫颈癌患者的MVCT和kVCT图像组成数据集，随机选择44例样本作为训练集，并将剩下的10例样本作为测试集。采用加入门控机制和多通道数据输入的循环生成对抗网络（CycleGAN）基于MVCT合成伪kVCT图像。采用平均绝对误差（MAE）、峰值信噪比（PSNR）和结构相似度指数（SSIM）等影像学成像质量评估参数，评估网络训练效果。结果：5通道MVCT-5通道kVCT图像与MVCT图像对比，MAE从（24.9±0.7） HU降至（17.8±0.3） HU，PSNR从（29.8±0.2） dB升至（30.7±0.2） dB，SSIM从0.841± 0.007升至0.898±0.003。结论：该方法生成的伪kVCT在降噪和增强对比度方面具有优势，同时能够减少剂量计算中对额外MV-kVCT电子密度校准的需求。伪kVCT的剂量计算能力与MVCT相当，为伪kVCT影像应用于图像引导自适应放疗提供了可能。
Abstract:
Abstract: Objective To propose a deep learning neural network approach for transforming megavoltage computed tomography (MVCT) images of cervical cancer into pseudo kilovoltage computed tomography (kVCT) images with high signal-to-noise ratio and contrast-to-noise ratio, thus providing three-dimensional anatomical images and localization information required for adaptive radiotherapy of cervical cancer, and guiding the accelerator to achieve precise treatment. Methods The MVCT and kVCT images of 54 patients treated with cervical cancer radiotherapy were collected, with 44 cases randomly selected as the training set, and the remaining 10 cases as the test set. A cyclic generative adversarial network with gating mechanism and multi-channel data input was used to synthesize pseudo-kVCT images from MVCT images. The network training results were evaluated with imaging quality evaluation parameters, such as mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM). Results The MAE, PSNR, and SSIM of MVCT images vs pseudo-kVCT (5:5) images were (24.9±0.7) HU vs (17.8±0.3) HU, (29.8±0.2) dB vs (30.7±0.2) dB, and 0.841±0.007 vs 0.898±0.003, respectively. Conclusion The generated pseudo-kVCT images have advantages in noise reduction and contrast enhancement, and can reduce the need for additional MV-kVCT electron density calibration in dose calculations. The dose calculation ability of pseudo-kVCT is comparable to that of MVCT, providing a possibility for the application of pseudo-kVCT images in image-guided adaptive radiotherapy.

相似文献/References:

[1]黄栋,田晓云,刘海,等.鼻咽癌螺旋断层放疗MegaVoltage CT引导下摆位误差分析[J].中国医学物理学杂志,2016,33(2):204.[doi:10.3969/j.issn.1005-202X.2016.02.020]
[2]全科润,程品晶,陈榕钦,等.基于循环生成对抗网络的鼻咽癌CBCT图像修正[J].中国医学物理学杂志,2021,38(5):582.[doi:DOI:10.3969/j.issn.1005-202X.2021.05.011]
　QUAN Kerun,CHENG Pinjing,CHEN Rongqin,et al.CBCT image correction for nasopharyngeal carcinoma based on cycle-consistent generative adversarial network[J].Chinese Journal of Medical Physics,2021,38(7):582.[doi:DOI:10.3969/j.issn.1005-202X.2021.05.011]

备注/Memo

备注/Memo:
【收稿日期】2024-02-25 【基金项目】解放军总医院第七医学中心创新培育基金（qzx-2023-12） 【作者简介】陈宇亭，硕士研究生，研究方向：医学物理，E-mail: wibx_95@163.com 【通信作者】路娜，硕士，主治医师，研究方向：肿瘤放射治疗学，E-mail: 13910033806@139.com
更新日期/Last Update: 2024-07-12