AUTHOR=Wang Junqing , Chen Bingqian , Zhu Jing , Zhang Junfeng , Jiang Rui 

TITLE=Intelligent diagnosis value of preoperative T staging of colorectal cancer based on MR medical imaging

JOURNAL=Frontiers in Genetics

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2023.1119990

DOI=10.3389/fgene.2023.1119990

ISSN=1664-8021

ABSTRACT=Colorectal cancer is a common malignant tumor in clinical medicine. With the changes in people's diet, living environment and living habits, the incidence has risen sharply in recent years, posing a great threat to the health and quality of life of contemporary people. The purpose of this article is to explore the pathogenesis of colorectal cancer and improve the efficiency of clinical diagnosis and treatment. This article proposes using MR medical imaging to intelligently diagnose the preoperative T staging of colorectal cancer, and analyzes the application of MR medical imaging in the treatment of colorectal cancer. This article first introduces the MR medical imaging technology and the related theories of colorectal cancer through the literature investigation method, and then applies the MR technology to the preoperative T staging of colorectal cancer. Through the use of our hospital from January 2019 to January 2020 150 cases of colorectal cancer patients admitted each month were the research objects, and the application experiment of MR medical imaging in the intelligent diagnosis of colorectal cancer preoperative T staging was carried out to explore the diagnostic sensitivity, specificity and sensitivity of MR staging and histopathological T staging diagnostic coincidence rate. The final result is that there is no statistical difference in the general information of patients in T1-2, T3 and T4 stages (P>0.05); For patients with colorectal cancer at preoperative T staging, the overall diagnostic coincidence rate of MR is 89.73%., indicating that it has a high degree of coincidence with the pathological T staging. Compared with MR staging, the total diagnosis coincidence rate of CT for the preoperative T staging of patients with colorectal cancer is 86.73%, which is generally consistent with the diagnosis of pathological T staging. At the same time, this research suggests three distinct dictionary learning depth techniques to address the drawbacks of long MR scanning time and slow imaging speed.