Magnetic Resonance Image under the Low-Rank Matrix Denoising Algorithm in Evaluating the Efficacy of Neoadjuvant Chemo-Radiotherapy for Rectal Cancer

被引:0
|
作者
Qi, Yulong [1 ,2 ]
Feng, Fei [1 ]
Zhang, Na [3 ]
Zhang, Hui [1 ]
Cheng, Guanxun [1 ,2 ]
机构
[1] Peking Univ Shenzhen Hosp, Med Imaging Ctr, Shenzhen 518036, Guangdong, Peoples R China
[2] Shantou Univ, Med Coll, Shantou 515041, Guangdong, Peoples R China
[3] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518055, Guangdong, Peoples R China
关键词
MANAGEMENT;
D O I
10.1155/2022/5299385
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
The is study was to explore the application value of magnetic resonance imaging (MRI) images obtained by low-rank matrix recovery algorithm (LRMR algorithm) in evaluating the curative effect of rectal cancer patients receiving the neoadjuvant chemoradiotherapy (nCRT). In this study, an image denoising model was designed based on the LRMR algorithm, the original low-rank data matrix was recovered from the error, and the low-rank matrix was restored by solving the optimal kernel norm, so as to effectively separate the image data information and the interference noise. In addition, the model was applied to 60 patients with rectal cancer who received nCRT to extract the texture parameters and lesion-related data from the MRI images. The results showed that the MRI images optimized by LRMR algorithm were clearer than the original images, contained less excess noise, and had improved imaging accuracy and image quality. The results of typical cases suggested that the front of the rectal wall membrane of a patient in the T-downstage group was not smooth before treatment, the internal angiography was blurred, and the wall membrane was thickened, but the wall membrane became thinner after treatment, the highest position was reduced from 1.46 cm to 0.38 cm, the average value of the apparent diffusion coefficient (ADC) increased from 0.732 x 10(-3) mm(2)/s to 1.196 x 10(-3) mm(2)/s, and the lesion tissue was thicker. It was found that the height, length, and ADC of the lesion after the nCRT showed statistically great difference in contrast to the values before the treatment (P < 0.05). Such results indicated that the nCRT showed obvious effects in the clinical treatment of rectal cancer. In short, the LRMR algorithm could remove the interference noise in the MRI image, and from the information about rectal cancer tumor lesions extracted from that, the height value and length value of tumor lesions in patients given neoadjuvant chemo-radiotherapy were reduced compared with those before treatment, and the apparent diffusion coefficient value was increased, indicating that neoadjuvant chemo-radiotherapy has a significant effect in the clinical treatment of rectal cancer.
引用
收藏
页数:10
相关论文
共 19 条
  • [1] RETRACTED: Analysis on Characteristics of Magnetic Resonance Imaging Image under Low-Rank Matrix Denoising Algorithm in the Diagnosis of Cerebral Aneurysm (Retracted Article)
    Li, Jun
    Li, Jin
    Hu, Qin
    [J]. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2021, 2021
  • [2] Magnetic Resonance Imaging Image under Low-Rank Matrix Denoising Algorithm in the Diagnosis and Evaluation of Tibial Plateau Fracture Combined with Meniscus Injury
    Fu, Qimao
    Huang, Chuizhi
    Chen, Yan
    Jia, Nailong
    Huang, Jinghui
    Lin, Changkun
    [J]. SCIENTIFIC PROGRAMMING, 2021, 2021
  • [3] Low-Rank Matrix Denoising Algorithm-Based MRI Image Feature for Therapeutic Effect Evaluation of NCRT on Rectal Cancer
    Hu, Qin
    Li, Jin
    Li, Jun
    [J]. JOURNAL OF HEALTHCARE ENGINEERING, 2021, 2021
  • [4] NEOADJUVANT CHEMOTHERAPY FOLLOWED BY CHEMO-RADIOTHERAPY FOR LOCALLY ADVANCED RECTAL CANCER IN THE VERY ELDERLY: EFFICACY AND TOLERABILITY
    Henderson, Daniel
    McKinna, Fiona
    Gilbert, Duncan
    [J]. ANNALS OF ONCOLOGY, 2012, 23 : 112 - 113
  • [5] Joint low-rank prior and difference of Gaussian filter for magnetic resonance image denoising
    Zhen Chen
    Zhiheng Zhou
    Saifullah Adnan
    [J]. Medical & Biological Engineering & Computing, 2021, 59 : 607 - 620
  • [6] A new nonlocal low-rank regularization method with applications to magnetic resonance image denoising
    Lu, Jian
    Xu, Chen
    Hu, Zhenwei
    Liu, Xiaoxia
    Jiang, Qingtang
    Meng, Deyu
    Lin, Zhouchen
    [J]. INVERSE PROBLEMS, 2022, 38 (06)
  • [7] Joint low-rank prior and difference of Gaussian filter for magnetic resonance image denoising
    Chen, Zhen
    Zhou, Zhiheng
    Adnan, Saifullah
    [J]. MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2021, 59 (03) : 607 - 620
  • [8] 3D magnetic resonance image denoising using low-rank tensor approximation
    Fu, Ying
    Dong, Weisheng
    [J]. NEUROCOMPUTING, 2016, 195 : 30 - 39
  • [9] Locally advanced rectal cancer: qualitative and quantitative evaluation of diffusion-weighted magnetic resonance imaging in restaging after neoadjuvant chemo-radiotherapy
    Napoletano, Maria
    Mazzucca, Daniele
    Prosperi, Enrico
    Aisa, Maria Cristina
    Lupattelli, Marco
    Aristei, Cynthia
    Scialpi, Michele
    [J]. ABDOMINAL RADIOLOGY, 2019, 44 (11) : 3664 - 3673
  • [10] Locally advanced rectal cancer: qualitative and quantitative evaluation of diffusion-weighted magnetic resonance imaging in restaging after neoadjuvant chemo-radiotherapy
    Maria Napoletano
    Daniele Mazzucca
    Enrico Prosperi
    Maria Cristina Aisa
    Marco Lupattelli
    Cynthia Aristei
    Michele Scialpi
    [J]. Abdominal Radiology, 2019, 44 : 3664 - 3673