| 引用本文: | 肖宁,肖小娇,强彦,李克勤,李硕,廉建红.基于条件对抗时空编码器的肺部肿瘤纵向预测方法.软件学报,2023,34(9):4392-4406 |
| |
|
| |
|
|
| 本文已被：浏览 1429次 下载 4089次 |
码上扫一扫！ |
|
|
| 基于条件对抗时空编码器的肺部肿瘤纵向预测方法 |
|
肖宁1, 肖小娇1, 强彦1, 李克勤2,3, 李硕4, 廉建红5
|
|
1.太原理工大学 信息与计算机学院, 山西 太原 030600;2.湖南大学 信息科学与工程学院, 湖南 长沙 410082;3.Department of Computer Science, State University of New York, New York 10041 NY 212, USA;4.Department of Medical Imaging and Medical Biophysics, Western University, London N6A 3K7, Canada;5.山西省肿瘤医院 胸外科, 山西 太原 030013
|
|
| 摘要: |
| 肿瘤位置以及生长变化的观测是肿瘤治疗方案的制定中的重要环节. 基于医学图像的干预手段以一种非侵入方式, 能够直观地观察到患者体内肿瘤状态, 来预测肿瘤的生长情况, 从而帮助医师建立适应于患者特定的治疗方案. 提出了一种全新的深度网络模型——条件对抗时空编码器模型来预测肿瘤生长情况. 该模型主要分为3个部分, 肿瘤预测生成器, 相似度得分鉴别器以及由患者个人情况组成的条件. 肿瘤预测生成器会根据两个时期的肿瘤图像预测出下一个时期的肿瘤, 相似度得分鉴别器用来计算预测出的肿瘤与真实肿瘤之间的相似性, 另外, 使用了患者的个人情况作为条件加入到肿瘤生长预测过程中. 该模型在收集到的两个医学数据集上进行实验验证, 实验结果的召回率达到了76.10%, 精准率达到了91.70%, Dice系数达到了82.4%, 表明该模型可以精准地预测出下一个时期的肿瘤影像. |
| 关键词: 生成对抗网络 自动编码器 肿瘤生长预测 医学图像 纵向研究 |
| DOI：10.13328/j.cnki.jos.006656 |
| 分类号:TP391 |
| 基金项目:国家自然科学基金(61872261); 山西省自然科学基金(201901D111319) |
|
| Longitudinal Prediction of Lung Tumor Based on Conditional Adversarial Spatiotemporal Encoder |
|
XIAO Ning1, XIAO Xiao-Jiao1, QIANG Yan1, LI Ke-Qin2,3, LI Shuo4, LIAN Jian-Hong5
|
|
1.College of Information and Computer, Taiyuan University of Technology, Taiyuan 030600, China;2.College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China;3.Department of Computer Science, State University of New York, New York 10041 NY 212, USA;4.Department of Medical Imaging and Medical Biophysics, Western University, London N6A 3K7, Canada;5.Thoracic Surgery, Shanxi Provincial Cancer Hospital, Taiyuan 030013, China
|
| Abstract: |
| The observation of tumor location and growth is an important link in the formulation of tumor treatment plans. Intervention methods based on medical images can be employed to visually observe the status of the tumor in the patient in a non-invasive way, predict the growth of the tumor, and ultimately help physicians develop a treatment plan specific to the patient. This study proposes a new deep network model, namely the conditional adversarial spatiotemporal encoder model, to predict tumor growth. This model mainly consists of three parts: the tumor prediction generator, the similarity score discriminator, and conditions composed of the patient’s personal situations. The tumor prediction generator predicts the tumor in the next period according to the tumor images of two periods. The similarity score discriminator is used to calculate the similarity between the predicted tumor and the real one. In addition, this study adds the patient’s personal situations as conditions to the tumor growth prediction process. The proposed model is experimentally verified on two collected medical datasets. The experimental results achieve a recall rate of 76.10%, an accuracy rate of 91.70%, and a Dice coefficient of 82.4%, indicating that the proposed model can accurately predict the tumor images of the next period. |
| Key words: generative adversarial network (GAN) auto-encoder tumor growth prediction medical image longitudinal research |
|
|
|
|
