[1]冯二燕,秦品乐,柴 锐,等.面向急性缺血性脑卒中 CT 到 MRI 的图像生成[J].计算机技术与发展,2023,33(10):135-142.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 021]
 FENG Er-yan,QIN Pin-le,CHAI Rui,et al.Image Generation of CT to MRI for Acute Ischemic Stroke[J].,2023,33(10):135-142.[doi:10. 3969 / j. issn. 1673-629X. 2023. 10. 021]
点击复制

面向急性缺血性脑卒中 CT 到 MRI 的图像生成()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年10期
页码:
135-142
栏目:
人工智能
出版日期:
2023-10-10

文章信息/Info

Title:
Image Generation of CT to MRI for Acute Ischemic Stroke
文章编号:
1673-629X(2023)10-0135-08
作者:
冯二燕12 秦品乐12 柴 锐12 曾建朝12 孟延锋3
1. 山西省医学影像与数据分析工程研究中心(中北大学),山西 太原 030051;
2. 中北大学 计算机科学与技术学院,山西 太原 030051;
3. 山西医科大学 附属太原中心医院,山西 太原 030009
Author(s):
FENG Er-yan12 QIN Pin-le12 CHAI Rui12 ZENG Jian-chao12 MENG Yan-feng3
1. Shanxi Medical Imaging and Data Analysis Engineering Research Center ( North University of China) ,Taiyuan 030051,China;
2. School of Data Science and Technology,North University of China,Taiyuan 030051,China;
3. Taiyuan Central Hospital,Shanxi Medical University,Taiyuan 030009,China
关键词:
医学图像生成影像组学生成对抗网络计算机断层扫描( CT) 磁共振成像( MRI) 跨模态图像生成
Keywords:
medical image generation radiomics generative adversarial networks ( GAN ) computed tomography ( CT ) magneticresonance imaging ( MRI) cross-modal image generation
分类号:
TP183
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 10. 021
摘要:
急性缺血性脑卒中病灶很容易在磁共振成像( MRI) 上表现为高信号区域。 相较于 MRI,计算机断层扫描( CT) 成像速度快、价格低,不易受金属植入物干扰,但 CT 对缺血
性脑卒中病灶不敏感,通常在 CT 上难以确定病灶的位置,且 CT包含的信息量比 MRI 少。 考虑到速度与可用性的提升以及成本的降低,为了以 CT 生成的 MRI 代替真实的 MRI 对急性缺血性脑卒中进行诊断,提出一种 CT 到 MRI 的跨模态图像生成算法。 首先,利用影像组学在 CT 上确定病灶区域并提取影像组学特征,筛选出信息增益最大的特征并可视化,然后将该特征图与 CT 一同作为生成对抗网络的输入。 生成对抗网络在 pix2pix 生成器中引入残差块,鉴别器采用 PatchGAN。 最后在损失函数中引入病灶特征相似性损失函数,更加关注病灶区域的相似性。 经两名放射科医生的主观判断与评估指标的客观分析,结果表明,该算法生成的 MRI 与真实 MRI 相似性极高,且病灶位置正确,形状相似,可为医生的诊疗提供帮助。
Abstract:
Acute ischemic stroke lesion is easily represented as hyperintense areas on Magnetic Resonance Imaging ( MRI) . Compared toMRI,Computed Tomography ( CT)
?is faster,less expensive,and less susceptible to interference from metal implants. However,CT is notsensitive to acute ischemic stroke lesion and contains less information than MRI. Usually,it is difficult to determine the location of lesionson CT. Considering the improvement of speed and usability and the reduction of cost,
in order to replace real MRI with MRI generatedfrom CT for the diagnosis of acute ischemic stroke,a cross- modal image generation algorithm from CT to MRI is proposed. Firstly,radiomics is used to determine the lesion area on CT and extract radiomics features,and the feature with the largest information gain isscreened?
out and visualized,and then the feature map is used together with the real CT as the input of the generative adversarial network.The generated adversarial network introduces residual block in pix2pix generator,and the discriminator adopts PatchGAN. Finally,thelesion feature similarity loss function is introduced in the loss function,paying more attention to the similarity of the lesion area. After thesubjective judgment of two radiologists and the objective analysis of evaluation indicators,
the results show that the MRI generated by thealgorithm is very similar to the real MRI,and the location of the lesion is correct and the shape is similar,which can provide assistance fordoctors’ diagnosis and treatment.

相似文献/References:

[1]张美美,秦品乐,柴 锐,等.急性缺血性脑卒中 CT 生成 MRI 算法——基于影像组学的边缘感知扩散 GAN[J].计算机技术与发展,2024,34(03):170.[doi:10. 3969 / j. issn. 1673-629X. 2024. 03. 025]
 ZHANG Mei-mei,QIN Pin-le,CHAI Rui,et al.Acute Ischemic Stroke CT-to-MRI Conversion Algorithm——Radiomics-based Edge-aware DiffusionGAN[J].,2024,34(10):170.[doi:10. 3969 / j. issn. 1673-629X. 2024. 03. 025]

更新日期/Last Update: 2023-10-10