Zaiyi Liu

Prediction of platinum resistance for advanced high-grade serous ovarian carcinoma using MRI-based radiomics nomogram

This study aimed to explore the value of a radiomics nomogram to identify platinum resistance and predict the progression-free survival (PFS) of patients with advanced high-grade serous ovarian carcinoma (HGSOC). In this multicenter retrospective study, 301 patients with advanced HGSOC underwent radiomics features extraction from the whole primary tumor on contrast-enhanced T1WI and T2WI. The radiomics features were selected by the support vector machine-based recursive feature elimination method, and then the radiomics signature was generated. Furthermore, a radiomics nomogram was developed using the radiomics signature and clinical characteristics by multivariable logistic regression. The predictive performance was evaluated using receiver operating characteristic analysis. The net reclassification index (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA) were used to compare the clinical utility and benefits of different models. Five features significantly correlated with platinum resistance were selected to construct the radiomics model. The radiomics nomogram, combining radiomics signatures with three clinical characteristics (FIGO stage, CA-125, and residual tumor), had a higher area under the curve (AUC) compared with the clinical model alone (AUC: 0.799 vs 0.747), with positive NRI and IDI. The net benefit of the radiomics nomogram is typically higher than clinical-only and radiomics-only models. Kaplan-Meier survival analysis showed that the radiomics nomogram-defined high-risk groups had shorter PFS compared with the low-risk groups in patients with advanced HGSOC. The radiomics nomogram can identify platinum resistance and predict PFS. It helps make the personalized management of advanced HGSOC. • The radiomics-based approach has the potential to identify platinum resistance and can help make the personalized management of advanced HGSOC. • The radiomics-clinical nomogram showed improved performance compared with either of them alone for predicting platinum-resistant HGSOC. • The proposed nomogram performed well in predicting the PFS time of patients with low-risk and high-risk HGSOC in both training and testing cohorts.

Diffusion‐Weighted Magnetic Resonance Imaging and Morphological Characteristics Evaluation for Outcome Prediction of Primary Debulking Surgery for Advanced High‐Grade Serous Ovarian Carcinoma

BackgroundPreoperative assessment of whether a successful primary debulking surgery (PDS) can be performed in patients with advanced high‐grade serous ovarian carcinoma (HGSOC) remains a challenge. A reliable model to precisely predict resectability is highly demanded.PurposeTo investigate the value of diffusion‐weighted MRI (DW‐MRI) combined with morphological characteristics to predict the PDS outcome in advanced HGSOC patients.Study TypeProspective.SubjectsA total of 95 consecutive patients with histopathologically confirmed advanced HGSOC (ranged from 39 to 77 years).Fields Strength/SequenceA 3.0 T, readout‐segmented echo‐planar DWI.AssessmentThe MRI morphological characteristics of the primary ovarian tumor, a peritoneal carcinomatosis index (PCI) derived from DWI (DWI‐PCI) and histogram analysis of the primary ovarian tumor and the largest peritoneal carcinomatosis were assessed by three radiologists. Three different models were developed to predict the resectability, including a clinicoradiologic model combing MRI morphological characteristic with ascites and CA125 level; DWI‐PCI alone; and a fusion model combining the clinical‐morphological information and DWI‐PCI.Statistical TestsMultivariate logistic regression analyses, receiver operating characteristic (ROC) curve, net reclassification index (NRI) and integrated discrimination improvement (IDI) were used. A P < 0.05 was considered to be statistically significant.ResultsSixty‐seven cases appeared as a definite mass, whereas 28 cases as an infiltrative mass. The morphological characteristics and DWI‐PCI were independent factors for predicting the resectability, with an AUC of 0.724 and 0.824, respectively. The multivariable predictive model consisted of morphological characteristics, CA‐125, and the amount of ascites, with an incremental AUC of 0.818. Combining the application of a clinicoradiologic model and DWI‐PCI showed significantly higher AUC of 0.863 than the ones of each of them implemented alone, with a positive NRI and IDI.Data ConclusionsThe combination of two clinical factors, MRI morphological characteristics and DWI‐PCI provide a reliable and valuable paradigm for the noninvasive prediction of the outcome of PDS.Evidence Level2Technical EfficacyStage 2