Ultrasound-based radiomics for predicting different pathological subtypes of epithelial ovarian cancer before surgery
Open Access
- 22 August 2022
- journal article
- research article
- Published by Springer Nature in BMC Medical Imaging
- Vol. 22 (1) , 1-13
Abstract
Objective: To evaluate the value of ultrasound-based radiomics in the preoperative prediction of type I and type II epithelial ovarian cancer. Methods: A total of 154 patients with epithelial ovarian cancer were enrolled retrospectively. There were 102 unilateral lesions and 52 bilateral lesions among a total of 206 lesions. The data for the 206 lesions were randomly divided into a training set (53 type I + 71 type II) and a test set (36 type I + 46 type II) by random sampling. ITK-SNAP software was used to manually outline the boundary of the tumor, that is, the region of interest, and 4976 features were extracted. The quantitative expression values of the radiomics features were normalized by the Z-score method, and the 7 features with the most differences were screened by using the Lasso regression tenfold cross-validation method. The radiomics model was established by logistic regression. The training set was used to construct the model, and the test set was used to evaluate the predictive efficiency of the model. On the basis of multifactor logistic regression analysis, combined with the radiomics score of each patient, a comprehensive prediction model was established, the nomogram was drawn, and the prediction effect was evaluated by analyzing the area under the receiver operating characteristic curve (AUC), calibration curve and decision curve. Results: The AUCs of the training set and test set in the radiomics model and comprehensive model were 0.817 and 0.731 and 0.982 and 0.886, respectively. The calibration curve showed that the two models were in good agreement. The clinical decision curve showed that both methods had good clinical practicability. Conclusion: The radiomics model based on ultrasound images has a good predictive effect for the preoperative differential diagnosis of type I and type II epithelial ovarian cancer. The comprehensive model has higher prediction efficiency.Keywords
This publication has 30 references indexed in Scilit:
- Data Science in Radiology: A Path ForwardClinical Cancer Research, 2018
- Computational Radiomics System to Decode the Radiographic PhenotypeCancer Research, 2017
- Radiomics: the bridge between medical imaging and personalized medicineNature Reviews Clinical Oncology, 2017
- European Society of Gynaecological Oncology (ESGO) Guidelines for Ovarian Cancer SurgeryInternational Journal of Gynecological Cancer, 2017
- Ovarian Cancer, Version 1.2016, NCCN Clinical Practice Guidelines in OncologyJournal of the National Comprehensive Cancer Network, 2016
- Diagnosis and Management of Adnexal Masses.2016
- Ovarian cancer: role of ultrasound in preoperative diagnosis and population screeningUltrasound in Obstetrics & Gynecology, 2012
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012
- The Origin and Pathogenesis of Epithelial Ovarian Cancer: A Proposed Unifying TheoryAmerican Journal of Surgical Pathology, 2010
- Profiling Studies in Ovarian Cancer: A ReviewThe Oncologist, 2007