南方医科大学学报

南方医科大学学报 ›› 2024, Vol. 44 ›› Issue (1): 83-92.doi: 10.12122/j.issn.1673-4254.2024.01.10

• • 上一篇    下一篇

多期相CT合成辅助的腹部多器官图像分割

黄品瑜，钟丽明，郑楷宜，陈泽立，肖若琳，全显跃，阳 维   

  1. 南方医科大学生物医学工程学院//广东省医学图像处理重点实验室，广东 广州 510515；南方医科大学珠江医院影像诊断科，广东 广州 510282
  • 发布日期:2024-01-24

Multi-phase CT synthesis-assisted segmentation of abdominal organs

HUANG Pinyu, ZHONG Liming, ZHENG Kaiyi, CHEN Zeli, XIAO Ruolin, QUAN Xianyue, YANG Wei   

  1. School of Biomedical Engineering, Southern Medical University//Guangdong Provincial Key Laboratory of Medical Image Processing, Guangzhou 510515, China; Department of Radiology, Zhujiang Hospital, Southern Medical University, Guangzhou 510282, China
  • Published:2024-01-24

RichHTML

22

PDF

215

摘要： 目的 提出并探讨使用多期相CT合成辅助腹部多器官分割方法。方法 提出多期相CT合成辅助腹部多器官分割，多期相CT能够充分提供同一器官不同的图像细节，从而为分割模型提供充分的全面的语义信息，提升腹部多个器官分割的性能。提出基于多头自注意力感知的多期相CT合成方法，引入基于多头自注意力机制的Transformer模块，提升合成网络捕捉长距离语义信息的能力，扩大网络的感受野，并且引入感知损失，在特征层面对合成图像与真实图像特征之间的差异最小化，与Transformer模块有协同作用，从而合成出更清晰、更高质量的多期相CT图像。结果 使用南方医院的多期相CT数据集训练模型。其中用526例多期相CT训练合成模型，利用动脉期增强动脉CT（A.CECT）合成出平扫CT（NECT）、静脉期CECT（V.CECT）、延迟期CECT（D.CECT）的平均最大化绝对误差（MAE）分别为19.192±3.381、20.140±2.676、22.538±2.874，结合统计学对比，本文方法优于对比的其他图像合成方法（P<0.05）。多期相CT合成辅助的腹部多器官分割方法验证在内部验证集上进行验证平均Dice系数（DSC）为0.847，在外部验证集上进行验证平均DSC为0.823。结论 本文方法能够合成出高质量的多期相CT图像以有效缓解不同期相CT之间存在的配准无法解决的误差问题，同时提高腹部13器官的分割性能，具有良好的泛化性能。

关键词: 腹部多器官分割；多期相CT合成；对抗生成网络；Transformer

Abstract: Objective To propose a method for abdominal multi-organ segmentation assisted by multi-phase CT synthesis. Methods Multi-phase CT synthesis for synthesizing high-quality CT images was used to increase the information details for image segmentation. A transformer block was introduced to help to capture long-range semantic information in cooperation with perceptual loss to minimize the differences between the real image and synthesized image. Results The model was trained using multi-phase CT dataset of 526 total cases from Nanfang Hospital. The mean maximum absolute error (MAE) of the synthesized non-contrast CT, venous phase contrast- enhanced CT (CECT), and delay phase CECT images from arterial phase CECT was 19.192±3.381, 20.140±2.676 and 22.538±2.874, respectively, which were better than those of images synthesized using other methods. Validation of the multi-phase CT synthesis-assisted abdominal multi-organ segmentation method showed an average dice coefficient of 0.847 for the internal validation set and 0.823 for the external validation set. Conclusion The propose method is capable of synthesizing high-quality multi-phase CT images to effectively reduce the errors in registration between different phase CT images and improve the performance for segmentation of 13 abdominal organs.

Key words: abdominal multi-organ segmentation; multi-phase CT synthesis; adversarial generative networks; Transformer