Back to all available

MRI radiomics and hematological inflammatory features-based nomogram for early prediction of pelvic lymph node metastasis in patients with cervical cancer

gynecology-and-obstetrics
oncology
radiology-and-medical-imaging
womens-health

Abstract

Objective: To investigate the evaluation of pelvic lymph node metastasis (PLNM) in patients with cervical cancer by a comprehensive nomogram based on radiomics signature extracted from the union diffusion kurtosis imaging (DKI) and T2-weighted imaging (T2WI) combined with fig.

Methods We obtained clinical characteristics, pathologic characteristics, and hematological inflammatory variables for all 510 included patients. Meanwhile, a total of 1316 radiomics features were extracted from both T2WI and DKI images, respectively. The least absolute shrinkage and selection operator (LASSO) method was used to select the relevant features for PLNM prediction with non-zero coefficients. The Receiver operating characteristic curves (ROCs) were established using radiomics signatures derived from DKI, T2WI, and joint DKI and T2WI, respectively, to evaluate the performance of distinguishing the cervical cancer patients with PLNM. Univariate and multivariate analyses were used to investigate the independent predictors associated with PLNM in clinical hematological inflammatory variables. A comprehensive nomogram was built by combining the selected radiomic features and clinical hematological inflammatory parameters based on multivariate logistic regression for PLNM prediction in patients with cervical cancer.

Results For DKI, T2WI, and joint DKI and T2WI, the radiomics signatures yielded an AUC of 0.895 (95％CI, 0.823-0.967) vs 0.893 (95％CI, 0.819-0.966) vs 0.933 (95％CI, 0.880-0.986), and 0.889 (95％CI, 0.770-1.000) vs 0.889 (95％CI, 0.758-1.000) vs 0.912 (95％CI, 0.813-1.000) respectively in the primary and validation cohorts. Univariate and multivariate analyses showed that SII (p<0.001) was an independent predictor of PLNM in patients with cervical cancer. The clinical-radiomics model integrating SII and the radiomics signatures from joint DKI and T2WI yielded a higher AUC than the clinical model or radiomics model alone.

Conclusions: The clinical-radiomics comprehensive nomogram based on the radiomics signatures from the joint DKI and T2WI and a readily available hematological factor (SII) showed superior performance in the evaluation of the risk of PLNM than the single clinical model or radiomics model in cervical cancer.

Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].