MRI-based radiomics and ADC values are related to recurrence of endometrial carcinoma: a preliminary analysis

Abstract

Background To identify predictive value of apparent diffusion coefficient (ADC) values and magnetic resonance imaging (MRI)-based radiomics for all recurrences in patients with endometrial carcinoma (EC). Methods One hundred and seventy-four EC patients who were treated with operation and followed up in our institution were retrospectively reviewed, and the patients were divided into training and test group. Baseline clinicopathological features and mean ADC (ADCmean), minimum ADC (ADCmin), and maximum ADC (ADCmax) were analyzed. Radiomic parameters were extracted on T2 weighted images and screened by logistic regression, and then a radiomics signature was developed to calculate the radiomic score (radscore). In training group, Kaplan–Meier analysis was performed and a Cox regression model was used to evaluate the correlation between clinicopathological features, ADC values and radscore with recurrence, and verified in the test group. Results ADCmean showed inverse correlation with recurrence, while radscore was positively associated with recurrence. In univariate analyses, FIGO stage, pathological types, myometrial invasion, ADCmean, ADCmin and radscore were associated with recurrence. In the training group, multivariate Cox analysis showed that pathological types, ADCmean and radscore were independent risk factors for recurrence, which were verified in the test group. Conclusions ADCmean value and radscore were independent predictors of recurrence of EC, which can supplement prognostic information in addition to clinicopathological information and provide basis for individualized treatment and follow-up plan.

Preoperative Prediction Value of Pelvic Lymph Node Metastasis of Endometrial Cancer: Combining of ADC Value and Radiomics Features of the Primary Lesion and Clinical Parameters

“…It evaluates the inhomogeneity of image signals by quantifying the inhomogeneity and regularity of pixel gray values in normal and pathological tissues, through which it can reflect the microscopic heterogeneity at the histopathological level. Radiomics is potentially valuable for assessing tumor efficacy and predicting recurrence and metastasis [12][13][14][15]. Our study attempted to establish a predictive model for preoperative prediction of PLNM by combining the ADC value, MRI-based 3D radiomics features of EC primary lesion, and clinical parameters of patients.…”

A Radiomic-Based Machine Learning Model Predicts Endometrial Cancer Recurrence Using Preoperative CT Radiomic Features: A Pilot Study

“…In terms of DFS in EC, few studies have been published. Nakajo et al created a [ 18 F]-FDG PET-based radiomic ML model and obtained an AUC of 0.89 for the prediction of PFS [ 59 ], while other studies using MRI-based models alone or combined with clinical data obtained mean AUCs varying between 0.62 and 0.85 [ 67 , 68 , 69 ]. To complete this knowledge gap, our study aimed to evaluate the efficacy of CT-based radiomics in predicting recurrences in EC.…”

Construction and validation of a prediction model for preoperative prediction of Ki-67 expression in endometrial cancer patients by apparent diffusion coefficient

“…Currently, hysteroscopic localized biopsy or hysteroscopy combined with segmental diagnostic scraping is recommended as the "gold standard" for the diagnosis of endometrial cancer [8,9] . However, it is demanding, prone to infection, bleeding and even uterine perforation, and difficult to adequately reflect the biological behavior and characteristics of the tumor [10] .The development of a preoperative noninvasive and comprehensive method for the assessment of Ki-67 expression levels in EC patients is particularly important in the clinical setting. MRI has the advantage of high soft-tissue resolution and powerful functional imaging, which can clearly show the anatomical structure and adjacency of pelvic organs [11,12] .Among them, diffusion weighted imaging (DWI) is a functional imaging technique sensitive to the Brownian motion of water molecules, which reflects the functional status of water molecule exchange in human tissues in pathophysiological states [13] .…”