An MRI-based radiomics nomogram for preoperative prediction of Ki-67 index in nasopharyngeal carcinoma: a two-center study
2024

MRI-based nomogram predicts Ki-67 index in nasopharyngeal carcinoma

Sample size: 133 publication 10 minutes Evidence: moderate

Author Information

Author(s): Wang Yao, Zhang Jing, Li Qiyuan, Sun Li, Zheng Yingmei, Gao Chuanping, Dong Cheng

Primary Institution: Affiliated Hospital of Qingdao University, Qingdao, China

Hypothesis

Can an MRI-based radiomics nomogram effectively predict the Ki-67 index in nasopharyngeal carcinoma patients?

Conclusion

The MRI-based radiomics nomogram effectively predicts the pre-surgical expression level of Ki-67 in nasopharyngeal carcinoma patients.

Supporting Evidence

  • The radiomics nomogram showed an AUC of 0.841 in the test set.
  • Decision curve analysis indicated that the nomogram outperformed a clinical model.
  • Five radiomics features were identified as significant predictors of Ki-67 index.

Takeaway

Doctors can use MRI scans to help guess how aggressive a nasopharyngeal cancer is by looking at a special score called the Ki-67 index, which tells them how fast the cancer cells are growing.

Methodology

The study involved 133 patients with nasopharyngeal carcinoma who underwent MRI, with data split into training and test sets to develop and validate a radiomics nomogram using logistic regression.

Potential Biases

Manual segmentation of MRI images may introduce bias.

Limitations

The study had a relatively small sample size and potential selection bias due to its retrospective nature.

Participant Demographics

The study included 133 patients, with 74 men and 31 women in the training set, and 18 men and 10 women in the test set.

Statistical Information

P-Value

p = 0.035 for lymphatic necrosis, p = 0.048 for lymphatic spread

Confidence Interval

95% CI: 0.654 – 0.951

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.3389/fonc.2024.1423304

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication