基于锥束CT的合成CT的软组织区域图像质量提升方法  

Methods for enhancing image quality of soft tissue regions in synthetic CT based on cone-beam CT

作　　者：付紫维 朱叶晨 张子健[3] 高欣[2,4] FU Ziwei;ZHU Yechen;ZHANG Zijian;GAO Xin(Division of Life Sciences and Medicine,School of Biomedical Engineering(Suzhou),University of Science and Technology of China,Hefei 230026,P.R.China;Suzhou Institute of Biomedical Engineering and Technology,Chinese Academy of Sciences,Suzhou,Jiangsu 215163,P.R.China;Xiangya Hospital,Central South University,Changsha 410008,P.R.China;Jinan Guoke Medical Engineering and Technology Development Co.,Ltd.,Jinan 250101,P.R.China)

机构地区：[1]中国科学技术大学生物医学工程学院(苏州)生命科学与医学部,合肥230026 [2]中国科学院苏州生物医学工程技术研究所,江苏苏州215163 [3]中南大学湘雅医院,长沙410008 [4]济南国科医工科技发展有限公司,济南250101

出　　处：《生物医学工程学杂志》2025年第1期113-122,共10页Journal of Biomedical Engineering

基　　金：国家自然科学基金项目(82372052);国家重点研发计划项目(2022YFC2408400);泰山产业创新领军人才(tscx202312131);山东省重点研发计划项目(2021SFGC0104);苏州市先进生物医学成像技术重点实验室(SZS2022008)。

摘　　要：基于CBCT生成的合成CT(sCT)能够有效抑制伪影并提高CT值准确性,借此可精确计算放射剂量。然而,sCT图像不同组织区域的生成质量严重不均衡,软组织区域与其他区域相比生成质量较差。为此,本文提出了一种基于VGG-16的多任务注意力网络(MuTA-Net),重点提升sCT软组织区域的图像质量。首先,引入多任务学习策略将sCT生成任务分为全局图像生成、软组织区域生成和骨区域分割三个子任务,保证全局图像生成质量的同时,强化网络对软组织区域特征提取和生成的关注程度,并利用骨区域分割任务引导后续结果融合;然后,设计注意力模块进一步优化网络的特征提取能力,引导网络从全局特征中提取子任务特征;最后,借助结果融合模块整合各个子任务的生成结果,实现高质量的sCT图像生成。在头颈部CBCT上的实验结果显示,与ResNet、U-Net和U-Net++三种对比方法中的最优结果相比,基于本文所提方法生成的sCT图像在软组织区域的平均绝对误差下降了12.52%。MuTA-Net在CBCT引导的自适应放疗领域具有潜在的应用价值。Synthetic CT(sCT)generated from CBCT has proven effective in artifact reduction and CT number correction,facilitating precise radiation dose calculation.However,the quality of different regions in sCT images is severely imbalanced,with soft tissue region exhibiting notably inferior quality compared to others.To address this imbalance,we proposed a Multi-Task Attention Network(MuTA-Net)based on VGG-16,specifically focusing the enhancement of image quality in soft tissue region of sCT.First,we introduced a multi-task learning strategy that divides the sCT generation task into three sub-tasks:global image generation,soft tissue region generation and bone region segmentation.This approach ensured the quality of overall sCT image while enhancing the network’s focus on feature extraction and generation for soft tissues region.The result of bone region segmentation task guided the fusion of subtasks results.Then,we designed an attention module to further optimize feature extraction capabilities of the network.Finally,by employing a results fusion module,the results of three sub-tasks were integrated,generating a high-quality sCT image.Experimental results on head and neck CBCT demonstrated that the sCT images generated by the proposed MuTA-Net exhibited a 12.52%reduction in mean absolute error in soft tissue region,compared to the best performance among the three comparative methods,including ResNet,U-Net,and U-Net++.It can be seen that MuTA-Net is suitable for high-quality sCT image generation and has potential application value in the field of CBCT guided adaptive radiation therapy.

关 键 词：自适应放疗 锥束CT 合成CT 多任务学习 

分 类 号：R816[医药卫生—放射医学] TP391.41[医药卫生—临床医学]