EUVIMEDScopri EUVIMED
Crossref

Preoperative prediction of lymph node metastasis in colorectal cancer using 18 F‐FDG PET/CT peritumoral radiomics analysis

Yan Wang, Hongyue Zhao, Peng Fu, Lin Tian, Yexin Su, Zhehao Lyu, Wenchao Gu, Yang Wang, Shan Liu, Xi Wang, Han Zheng, Jingjing Du and 1 more

Medical Physics · 2024-08 · 51 (8) · 5214-5225

DOI: 10.1002/mp.17193 ↗

At a glance

Journal article in Medical Physics, published online on 2024-05-27. Written by Yan Wang and 12 co-authors. Institution: Department of Nuclear Medicine, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, China. Major MEDLINE topics: Colorectal Neoplasms, Fluorodeoxyglucose F18, Positron Emission Tomography Computed Tomography, Lymphatic Metastasis. Cited 7 times so far (Crossref); 51 references. Funded by: National Natural Science Foundation of China, 2022 Innovation Fund for Heilongjiang Provincial Institutions of Higher Learning, Natural Science Foundation of Heilongjiang Province.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

Radiomics has been used in the diagnosis of tumor lymph node metastasis (LNM). However, to date, most studies have been based on intratumoral radiomics. Few studies have focused on the use of 18 F‐fluorodeoxyglucose positron emission computed tomography ( 18 F‐FDG PET/CT) peritumoral radiomics for the diagnosis of LNM in colorectal cancer (CRC).

Purpose

Determining the value of radiomics features extracted from 18 F‐FDG PET/CT images of the peritumoral region in predicting LNM in patients with CRC.

Methods

The clinical data and preoperative 18 F‐FDG PET/CT images of 244 CRC patients were retrospectively analyzed. Intratumoral and peritumoral radiomics features were screened using the mutual information method, and least absolute shrinkage and selection operator regression. Based on the selected radiomics features, a radiomics score (Rad‐score) was calculated, and independent risk factors obtained from univariate and multivariate logistic regression analyses were used to construct clinical and combined (Radiomics + Clinical) models. The performance of these models was evaluated using the DeLong test, while their clinical utility was assessed by decision curve analysis. Finally, a nomogram was constructed to visualize the predictive model.

Results

The most optimal set of features retained by the feature filtering process were all peritumoral radiomic features. Carcinoembryonic antigen levels, PET/CT‐reported lymph node status and Rad‐score were found to be independent risk factors for LNM. All three LNM risk assessment models exhibited good predictive performance, with the combined model showing the best classification results, with areas under the curve of 0.85 and 0.76 in the training and validation groups, respectively. The DeLong test revealed that the performance of the combined model was superior to that of the clinical and radiomics models in both the training and validation groups, although this difference was only statistically significant in the training group. DCA indicated that the combined model displayed better clinical utility.

Conclusions

18 F‐FDG PET/CT peritumoral radiomics is uniquely suited to predict the presence of LNM in patients with CRC. In particular, the predictive efficacy of LNM for precision therapy and individualized patient management can be improved by using a combination of clinical risk factors.

Subjects

MeSH terms (MEDLINE)

Colorectal NeoplasmsFluorodeoxyglucose F18Positron Emission Tomography Computed TomographyLymphatic MetastasisHumansMaleFemaleMiddle AgedAgedPreoperative PeriodImage Processing, Computer-AssistedRetrospective StudiesAdultAged, 80 and overRadiomics

Author keywords

colorectal cancerlymph node metastasisperitumoral regionpositron emission/computed tomographyradiomics

Substances

Fluorodeoxyglucose F18

Authors and institutions

  • Department of Nuclear Medicine, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, China.
  • Department of Pathology, The First Affiliated Hospital of Harbin Medical University, Harbin, Heilongjiang, China.
  • Department of Diagnostic and Interventional Radiology, University of Tsukuba, Tsukuba, Ibaraki, Japan.
  • Department of Magnetic Resonance, The First Hospital of Qiqihar, Qiqihar, Heilongjiang, China.

Funding

  • National Natural Science Foundation of China
  • 2022 Innovation Fund for Heilongjiang Provincial Institutions of Higher Learning
  • Natural Science Foundation of Heilongjiang Province
  • Scientific Research and Innovation Fund of the First Affiliated Hospital of Harbin Medical University

Cite

APA

Wang, Y., Zhao, H., Fu, P., Tian, L., Su, Y., Lyu, Z., Gu, W., Wang, Y., Liu, S., Wang, X., Zheng, H., Du, J., & Zhang, R. (2024). Preoperative prediction of lymph node metastasis in colorectal cancer using 18 F‐FDG PET/CT peritumoral radiomics analysis. Medical Physics, 51(8), 5214-5225. https://doi.org/10.1002/mp.17193

Vancouver

Wang Y, Zhao H, Fu P, Tian L, Su Y, Lyu Z, et al. Preoperative prediction of lymph node metastasis in colorectal cancer using 18 F‐FDG PET/CT peritumoral radiomics analysis. Medical Physics. 2024;51(8):5214-5225. doi:10.1002/mp.17193

BibTeX
@article{Wang2024,
  author = {Wang, Yan and Zhao, Hongyue and Fu, Peng and Tian, Lin and Su, Yexin and Lyu, Zhehao and Gu, Wenchao and Wang, Yang and Liu, Shan and Wang, Xi and Zheng, Han and Du, Jingjing and Zhang, Rui},
  title = {Preoperative prediction of lymph node metastasis in colorectal cancer using 18 F‐FDG PET/CT peritumoral radiomics analysis},
  journal = {Medical Physics},
  year = {2024},
  volume = {51},
  number = {8},
  pages = {5214--5225},
  doi = {10.1002/mp.17193}
}
Start for free →